update

examples/flux/model_training/full/FLEX.2-preview.sh

@@ -0,0 +1,12 @@
+accelerate launch --config_file examples/flux/model_training/full/accelerate_config.yaml examples/flux/model_training/train.py \
+  --dataset_base_path data/example_image_dataset \
+  --dataset_metadata_path data/example_image_dataset/metadata.csv \
+  --max_pixels 1048576 \
+  --dataset_repeat 200 \
+  --model_id_with_origin_paths "ostris/Flex.2-preview:Flex.2-preview.safetensors,black-forest-labs/FLUX.1-dev:text_encoder/model.safetensors,black-forest-labs/FLUX.1-dev:text_encoder_2/*.safetensors,black-forest-labs/FLUX.1-dev:ae.safetensors" \
+  --learning_rate 1e-5 \
+  --num_epochs 1 \
+  --remove_prefix_in_ckpt "pipe.dit." \
+  --output_path "./models/train/FLEX.2-preview_full" \
+  --trainable_models "dit" \
+  --use_gradient_checkpointing

examples/flux/model_training/full/FLUX.1-Kontext-dev.sh

@@ -0,0 +1,14 @@
+accelerate launch --config_file examples/flux/model_training/full/accelerate_config.yaml examples/flux/model_training/train.py \
+  --dataset_base_path data/example_image_dataset \
+  --dataset_metadata_path data/example_image_dataset/metadata_kontext.csv \
+  --data_file_keys "image,kontext_images" \
+  --max_pixels 1048576 \
+  --dataset_repeat 400 \
+  --model_id_with_origin_paths "black-forest-labs/FLUX.1-Kontext-dev:flux1-kontext-dev.safetensors,black-forest-labs/FLUX.1-dev:text_encoder/model.safetensors,black-forest-labs/FLUX.1-dev:text_encoder_2/*.safetensors,black-forest-labs/FLUX.1-dev:ae.safetensors" \
+  --learning_rate 1e-5 \
+  --num_epochs 1 \
+  --remove_prefix_in_ckpt "pipe.dit." \
+  --output_path "./models/train/FLUX.1-Kontext-dev_full" \
+  --trainable_models "dit" \
+  --extra_inputs "kontext_images" \
+  --use_gradient_checkpointing

examples/flux/model_training/full/FLUX.1-Krea-dev.sh

@@ -0,0 +1,12 @@
+accelerate launch --config_file examples/flux/model_training/full/accelerate_config.yaml examples/flux/model_training/train.py \
+  --dataset_base_path data/example_image_dataset \
+  --dataset_metadata_path data/example_image_dataset/metadata.csv \
+  --max_pixels 1048576 \
+  --dataset_repeat 400 \
+  --model_id_with_origin_paths "black-forest-labs/FLUX.1-Krea-dev:flux1-krea-dev.safetensors,black-forest-labs/FLUX.1-dev:text_encoder/model.safetensors,black-forest-labs/FLUX.1-dev:text_encoder_2/*.safetensors,black-forest-labs/FLUX.1-dev:ae.safetensors" \
+  --learning_rate 1e-5 \
+  --num_epochs 1 \
+  --remove_prefix_in_ckpt "pipe.dit." \
+  --output_path "./models/train/FLUX.1-Krea-dev_full" \
+  --trainable_models "dit" \
+  --use_gradient_checkpointing

examples/flux/model_training/full/FLUX.1-dev-AttriCtrl.sh

@@ -0,0 +1,14 @@
+accelerate launch examples/flux/model_training/train.py \
+  --dataset_base_path data/example_image_dataset \
+  --dataset_metadata_path data/example_image_dataset/metadata_attrictrl.csv \
+  --data_file_keys "image" \
+  --max_pixels 1048576 \
+  --dataset_repeat 100 \
+  --model_id_with_origin_paths "black-forest-labs/FLUX.1-dev:flux1-dev.safetensors,black-forest-labs/FLUX.1-dev:text_encoder/model.safetensors,black-forest-labs/FLUX.1-dev:text_encoder_2/*.safetensors,black-forest-labs/FLUX.1-dev:ae.safetensors,DiffSynth-Studio/AttriCtrl-FLUX.1-Dev:models/brightness.safetensors" \
+  --learning_rate 1e-5 \
+  --num_epochs 1 \
+  --remove_prefix_in_ckpt "pipe.value_controller.encoders.0." \
+  --output_path "./models/train/FLUX.1-dev-AttriCtrl_full" \
+  --trainable_models "value_controller" \
+  --extra_inputs "value_controller_inputs" \
+  --use_gradient_checkpointing

examples/flux/model_training/full/FLUX.1-dev-Controlnet-Inpainting-Beta.sh

@@ -0,0 +1,14 @@
+accelerate launch --config_file examples/flux/model_training/full/accelerate_config.yaml examples/flux/model_training/train.py \
+  --dataset_base_path data/example_image_dataset \
+  --dataset_metadata_path data/example_image_dataset/metadata_controlnet_inpaint.csv \
+  --data_file_keys "image,controlnet_image,controlnet_inpaint_mask" \
+  --max_pixels 1048576 \
+  --dataset_repeat 400 \
+  --model_id_with_origin_paths "black-forest-labs/FLUX.1-dev:flux1-dev.safetensors,black-forest-labs/FLUX.1-dev:text_encoder/model.safetensors,black-forest-labs/FLUX.1-dev:text_encoder_2/*.safetensors,black-forest-labs/FLUX.1-dev:ae.safetensors,alimama-creative/FLUX.1-dev-Controlnet-Inpainting-Beta:diffusion_pytorch_model.safetensors" \
+  --learning_rate 1e-5 \
+  --num_epochs 1 \
+  --remove_prefix_in_ckpt "pipe.controlnet.models.0." \
+  --output_path "./models/train/FLUX.1-dev-Controlnet-Inpainting-Beta_full" \
+  --trainable_models "controlnet" \
+  --extra_inputs "controlnet_image,controlnet_inpaint_mask" \
+  --use_gradient_checkpointing

examples/flux/model_training/full/FLUX.1-dev-Controlnet-Union-alpha.sh

@@ -0,0 +1,14 @@
+accelerate launch --config_file examples/flux/model_training/full/accelerate_config.yaml examples/flux/model_training/train.py \
+  --dataset_base_path data/example_image_dataset \
+  --dataset_metadata_path data/example_image_dataset/metadata_controlnet_canny.csv \
+  --data_file_keys "image,controlnet_image" \
+  --max_pixels 1048576 \
+  --dataset_repeat 400 \
+  --model_id_with_origin_paths "black-forest-labs/FLUX.1-dev:flux1-dev.safetensors,black-forest-labs/FLUX.1-dev:text_encoder/model.safetensors,black-forest-labs/FLUX.1-dev:text_encoder_2/*.safetensors,black-forest-labs/FLUX.1-dev:ae.safetensors,InstantX/FLUX.1-dev-Controlnet-Union-alpha:diffusion_pytorch_model.safetensors" \
+  --learning_rate 1e-5 \
+  --num_epochs 1 \
+  --remove_prefix_in_ckpt "pipe.controlnet.models.0." \
+  --output_path "./models/train/FLUX.1-dev-Controlnet-Union-alpha_full" \
+  --trainable_models "controlnet" \
+  --extra_inputs "controlnet_image,controlnet_processor_id" \
+  --use_gradient_checkpointing

examples/flux/model_training/full/FLUX.1-dev-Controlnet-Upscaler.sh

@@ -0,0 +1,14 @@
+accelerate launch --config_file examples/flux/model_training/full/accelerate_config.yaml examples/flux/model_training/train.py \
+  --dataset_base_path data/example_image_dataset \
+  --dataset_metadata_path data/example_image_dataset/metadata_controlnet_upscale.csv \
+  --data_file_keys "image,controlnet_image" \
+  --max_pixels 1048576 \
+  --dataset_repeat 400 \
+  --model_id_with_origin_paths "black-forest-labs/FLUX.1-dev:flux1-dev.safetensors,black-forest-labs/FLUX.1-dev:text_encoder/model.safetensors,black-forest-labs/FLUX.1-dev:text_encoder_2/*.safetensors,black-forest-labs/FLUX.1-dev:ae.safetensors,jasperai/Flux.1-dev-Controlnet-Upscaler:diffusion_pytorch_model.safetensors" \
+  --learning_rate 1e-5 \
+  --num_epochs 1 \
+  --remove_prefix_in_ckpt "pipe.controlnet.models.0." \
+  --output_path "./models/train/FLUX.1-dev-Controlnet-Upscaler_full" \
+  --trainable_models "controlnet" \
+  --extra_inputs "controlnet_image" \
+  --use_gradient_checkpointing

examples/flux/model_training/full/FLUX.1-dev-IP-Adapter.sh

@@ -0,0 +1,14 @@
+accelerate launch examples/flux/model_training/train.py \
+  --dataset_base_path data/example_image_dataset \
+  --dataset_metadata_path data/example_image_dataset/metadata_ipadapter.csv \
+  --data_file_keys "image,ipadapter_images" \
+  --max_pixels 1048576 \
+  --dataset_repeat 100 \
+  --model_id_with_origin_paths "black-forest-labs/FLUX.1-dev:flux1-dev.safetensors,black-forest-labs/FLUX.1-dev:text_encoder/model.safetensors,black-forest-labs/FLUX.1-dev:text_encoder_2/*.safetensors,black-forest-labs/FLUX.1-dev:ae.safetensors,InstantX/FLUX.1-dev-IP-Adapter:ip-adapter.bin,google/siglip-so400m-patch14-384:" \
+  --learning_rate 1e-5 \
+  --num_epochs 1 \
+  --remove_prefix_in_ckpt "pipe.ipadapter." \
+  --output_path "./models/train/FLUX.1-dev-IP-Adapter_full" \
+  --trainable_models "ipadapter" \
+  --extra_inputs "ipadapter_images" \
+  --use_gradient_checkpointing

examples/flux/model_training/full/FLUX.1-dev-InfiniteYou.sh

@@ -0,0 +1,14 @@
+accelerate launch --config_file examples/flux/model_training/full/accelerate_config.yaml examples/flux/model_training/train.py \
+  --dataset_base_path data/example_image_dataset \
+  --dataset_metadata_path data/example_image_dataset/metadata_infiniteyou.csv \
+  --data_file_keys "image,controlnet_image,infinityou_id_image" \
+  --max_pixels 1048576 \
+  --dataset_repeat 400 \
+  --model_id_with_origin_paths "black-forest-labs/FLUX.1-dev:flux1-dev.safetensors,black-forest-labs/FLUX.1-dev:text_encoder/model.safetensors,black-forest-labs/FLUX.1-dev:text_encoder_2/*.safetensors,black-forest-labs/FLUX.1-dev:ae.safetensors,ByteDance/InfiniteYou:infu_flux_v1.0/aes_stage2/image_proj_model.bin,ByteDance/InfiniteYou:infu_flux_v1.0/aes_stage2/InfuseNetModel/*.safetensors" \
+  --learning_rate 1e-5 \
+  --num_epochs 1 \
+  --remove_prefix_in_ckpt "pipe." \
+  --output_path "./models/train/FLUX.1-dev-InfiniteYou_full" \
+  --trainable_models "controlnet,image_proj_model" \
+  --extra_inputs "controlnet_image,infinityou_id_image,infinityou_guidance" \
+  --use_gradient_checkpointing

examples/flux/model_training/full/FLUX.1-dev-LoRA-Encoder.sh

@@ -0,0 +1,14 @@
+accelerate launch examples/flux/model_training/train.py \
+  --dataset_base_path data/example_image_dataset \
+  --dataset_metadata_path data/example_image_dataset/metadata_lora_encoder.csv \
+  --data_file_keys "image" \
+  --max_pixels 1048576 \
+  --dataset_repeat 100 \
+  --model_id_with_origin_paths "black-forest-labs/FLUX.1-dev:flux1-dev.safetensors,black-forest-labs/FLUX.1-dev:text_encoder/model.safetensors,black-forest-labs/FLUX.1-dev:text_encoder_2/*.safetensors,black-forest-labs/FLUX.1-dev:ae.safetensors,DiffSynth-Studio/LoRA-Encoder-FLUX.1-Dev:model.safetensors" \
+  --learning_rate 1e-5 \
+  --num_epochs 1 \
+  --remove_prefix_in_ckpt "pipe.lora_encoder." \
+  --output_path "./models/train/FLUX.1-dev-LoRA-Encoder_full" \
+  --trainable_models "lora_encoder" \
+  --extra_inputs "lora_encoder_inputs" \
+  --use_gradient_checkpointing

examples/flux/model_training/full/FLUX.1-dev.sh

@@ -0,0 +1,12 @@
+accelerate launch --config_file examples/flux/model_training/full/accelerate_config.yaml examples/flux/model_training/train.py \
+  --dataset_base_path data/example_image_dataset \
+  --dataset_metadata_path data/example_image_dataset/metadata.csv \
+  --max_pixels 1048576 \
+  --dataset_repeat 400 \
+  --model_id_with_origin_paths "black-forest-labs/FLUX.1-dev:flux1-dev.safetensors,black-forest-labs/FLUX.1-dev:text_encoder/model.safetensors,black-forest-labs/FLUX.1-dev:text_encoder_2/*.safetensors,black-forest-labs/FLUX.1-dev:ae.safetensors" \
+  --learning_rate 1e-5 \
+  --num_epochs 1 \
+  --remove_prefix_in_ckpt "pipe.dit." \
+  --output_path "./models/train/FLUX.1-dev_full" \
+  --trainable_models "dit" \
+  --use_gradient_checkpointing

examples/flux/model_training/full/Nexus-Gen.sh

@@ -0,0 +1,14 @@
+accelerate launch --config_file examples/flux/model_training/full/accelerate_config_zero2offload.yaml examples/flux/model_training/train.py \
+  --dataset_base_path data/example_image_dataset \
+  --dataset_metadata_path data/example_image_dataset/metadata_nexusgen_edit.csv \
+  --data_file_keys "image,nexus_gen_reference_image" \
+  --max_pixels 262144 \
+  --dataset_repeat 400 \
+  --model_id_with_origin_paths "DiffSynth-Studio/Nexus-GenV2:model*.safetensors,DiffSynth-Studio/Nexus-GenV2:edit_decoder.bin,black-forest-labs/FLUX.1-dev:text_encoder/model.safetensors,black-forest-labs/FLUX.1-dev:text_encoder_2/*.safetensors,black-forest-labs/FLUX.1-dev:ae.safetensors" \
+  --learning_rate 1e-5 \
+  --num_epochs 1 \
+  --remove_prefix_in_ckpt "pipe.dit." \
+  --output_path "./models/train/FLUX.1-NexusGen-Edit_full" \
+  --trainable_models "dit" \
+  --extra_inputs "nexus_gen_reference_image" \
+  --use_gradient_checkpointing_offload

examples/flux/model_training/full/Step1X-Edit.sh

@@ -0,0 +1,14 @@
+accelerate launch --config_file examples/flux/model_training/full/accelerate_config.yaml examples/flux/model_training/train.py \
+  --dataset_base_path data/example_image_dataset \
+  --dataset_metadata_path data/example_image_dataset/metadata_step1x.csv \
+  --data_file_keys "image,step1x_reference_image" \
+  --max_pixels 1048576 \
+  --dataset_repeat 400 \
+  --model_id_with_origin_paths "Qwen/Qwen2.5-VL-7B-Instruct:,stepfun-ai/Step1X-Edit:step1x-edit-i1258.safetensors,stepfun-ai/Step1X-Edit:vae.safetensors" \
+  --learning_rate 1e-5 \
+  --num_epochs 1 \
+  --remove_prefix_in_ckpt "pipe.dit." \
+  --output_path "./models/train/Step1X-Edit_full" \
+  --trainable_models "dit" \
+  --extra_inputs "step1x_reference_image" \
+  --use_gradient_checkpointing_offload

examples/flux/model_training/full/accelerate_config.yaml

@@ -0,0 +1,22 @@
+compute_environment: LOCAL_MACHINE
+debug: false
+deepspeed_config:
+  gradient_accumulation_steps: 1
+  offload_optimizer_device: none
+  offload_param_device: none
+  zero3_init_flag: false
+  zero_stage: 2
+distributed_type: DEEPSPEED
+downcast_bf16: 'no'
+enable_cpu_affinity: false
+machine_rank: 0
+main_training_function: main
+mixed_precision: bf16
+num_machines: 1
+num_processes: 8
+rdzv_backend: static
+same_network: true
+tpu_env: []
+tpu_use_cluster: false
+tpu_use_sudo: false
+use_cpu: false

examples/flux/model_training/full/accelerate_config_zero2offload.yaml

@@ -0,0 +1,22 @@
+compute_environment: LOCAL_MACHINE
+debug: false
+deepspeed_config:
+  gradient_accumulation_steps: 1
+  offload_optimizer_device: 'cpu'
+  offload_param_device: 'cpu'
+  zero3_init_flag: false
+  zero_stage: 2
+distributed_type: DEEPSPEED
+downcast_bf16: 'no'
+enable_cpu_affinity: false
+machine_rank: 0
+main_training_function: main
+mixed_precision: bf16
+num_machines: 1
+num_processes: 8
+rdzv_backend: static
+same_network: true
+tpu_env: []
+tpu_use_cluster: false
+tpu_use_sudo: false
+use_cpu: false

examples/flux/model_training/lora/FLEX.2-preview.sh

@@ -0,0 +1,15 @@
+accelerate launch examples/flux/model_training/train.py \
+  --dataset_base_path data/example_image_dataset \
+  --dataset_metadata_path data/example_image_dataset/metadata.csv \
+  --max_pixels 1048576 \
+  --dataset_repeat 50 \
+  --model_id_with_origin_paths "ostris/Flex.2-preview:Flex.2-preview.safetensors,black-forest-labs/FLUX.1-dev:text_encoder/model.safetensors,black-forest-labs/FLUX.1-dev:text_encoder_2/*.safetensors,black-forest-labs/FLUX.1-dev:ae.safetensors" \
+  --learning_rate 1e-4 \
+  --num_epochs 5 \
+  --remove_prefix_in_ckpt "pipe.dit." \
+  --output_path "./models/train/FLEX.2-preview_lora" \
+  --lora_base_model "dit" \
+  --lora_target_modules "a_to_qkv,b_to_qkv,ff_a.0,ff_a.2,ff_b.0,ff_b.2,a_to_out,b_to_out,proj_out,norm.linear,norm1_a.linear,norm1_b.linear,to_qkv_mlp" \
+  --lora_rank 32 \
+  --align_to_opensource_format \
+  --use_gradient_checkpointing

examples/flux/model_training/lora/FLUX.1-Kontext-dev.sh

@@ -0,0 +1,17 @@
+accelerate launch examples/flux/model_training/train.py \
+  --dataset_base_path data/example_image_dataset \
+  --dataset_metadata_path data/example_image_dataset/metadata_kontext.csv \
+  --data_file_keys "image,kontext_images" \
+  --max_pixels 1048576 \
+  --dataset_repeat 400 \
+  --model_id_with_origin_paths "black-forest-labs/FLUX.1-Kontext-dev:flux1-kontext-dev.safetensors,black-forest-labs/FLUX.1-dev:text_encoder/model.safetensors,black-forest-labs/FLUX.1-dev:text_encoder_2/*.safetensors,black-forest-labs/FLUX.1-dev:ae.safetensors" \
+  --learning_rate 1e-4 \
+  --num_epochs 5 \
+  --remove_prefix_in_ckpt "pipe.dit." \
+  --output_path "./models/train/FLUX.1-Kontext-dev_lora" \
+  --lora_base_model "dit" \
+  --lora_target_modules "a_to_qkv,b_to_qkv,ff_a.0,ff_a.2,ff_b.0,ff_b.2,a_to_out,b_to_out,proj_out,norm.linear,norm1_a.linear,norm1_b.linear,to_qkv_mlp" \
+  --lora_rank 32 \
+  --align_to_opensource_format \
+  --extra_inputs "kontext_images" \
+  --use_gradient_checkpointing

examples/flux/model_training/lora/FLUX.1-Krea-dev.sh

@@ -0,0 +1,15 @@
+accelerate launch examples/flux/model_training/train.py \
+  --dataset_base_path data/example_image_dataset \
+  --dataset_metadata_path data/example_image_dataset/metadata.csv \
+  --max_pixels 1048576 \
+  --dataset_repeat 50 \
+  --model_id_with_origin_paths "black-forest-labs/FLUX.1-Krea-dev:flux1-krea-dev.safetensors,black-forest-labs/FLUX.1-dev:text_encoder/model.safetensors,black-forest-labs/FLUX.1-dev:text_encoder_2/*.safetensors,black-forest-labs/FLUX.1-dev:ae.safetensors" \
+  --learning_rate 1e-4 \
+  --num_epochs 5 \
+  --remove_prefix_in_ckpt "pipe.dit." \
+  --output_path "./models/train/FLUX.1-Krea-dev_lora" \
+  --lora_base_model "dit" \
+  --lora_target_modules "a_to_qkv,b_to_qkv,ff_a.0,ff_a.2,ff_b.0,ff_b.2,a_to_out,b_to_out,proj_out,norm.linear,norm1_a.linear,norm1_b.linear,to_qkv_mlp" \
+  --lora_rank 32 \
+  --align_to_opensource_format \
+  --use_gradient_checkpointing

examples/flux/model_training/lora/FLUX.1-dev-AttriCtrl.sh

@@ -0,0 +1,17 @@
+accelerate launch examples/flux/model_training/train.py \
+  --dataset_base_path data/example_image_dataset \
+  --dataset_metadata_path data/example_image_dataset/metadata_attrictrl.csv \
+  --data_file_keys "image" \
+  --max_pixels 1048576 \
+  --dataset_repeat 100 \
+  --model_id_with_origin_paths "black-forest-labs/FLUX.1-dev:flux1-dev.safetensors,black-forest-labs/FLUX.1-dev:text_encoder/model.safetensors,black-forest-labs/FLUX.1-dev:text_encoder_2/*.safetensors,black-forest-labs/FLUX.1-dev:ae.safetensors,DiffSynth-Studio/AttriCtrl-FLUX.1-Dev:models/brightness.safetensors" \
+  --learning_rate 1e-4 \
+  --num_epochs 5 \
+  --remove_prefix_in_ckpt "pipe.dit." \
+  --output_path "./models/train/FLUX.1-dev-AttriCtrl_lora" \
+  --lora_base_model "dit" \
+  --lora_target_modules "a_to_qkv,b_to_qkv,ff_a.0,ff_a.2,ff_b.0,ff_b.2,a_to_out,b_to_out,proj_out,norm.linear,norm1_a.linear,norm1_b.linear,to_qkv_mlp" \
+  --lora_rank 32 \
+  --extra_inputs "value_controller_inputs" \
+  --align_to_opensource_format \
+  --use_gradient_checkpointing

examples/flux/model_training/lora/FLUX.1-dev-Controlnet-Inpainting-Beta.sh

@@ -0,0 +1,17 @@
+accelerate launch examples/flux/model_training/train.py \
+  --dataset_base_path data/example_image_dataset \
+  --dataset_metadata_path data/example_image_dataset/metadata_controlnet_inpaint.csv \
+  --data_file_keys "image,controlnet_image,controlnet_inpaint_mask" \
+  --max_pixels 1048576 \
+  --dataset_repeat 100 \
+  --model_id_with_origin_paths "black-forest-labs/FLUX.1-dev:flux1-dev.safetensors,black-forest-labs/FLUX.1-dev:text_encoder/model.safetensors,black-forest-labs/FLUX.1-dev:text_encoder_2/*.safetensors,black-forest-labs/FLUX.1-dev:ae.safetensors,alimama-creative/FLUX.1-dev-Controlnet-Inpainting-Beta:diffusion_pytorch_model.safetensors" \
+  --learning_rate 1e-4 \
+  --num_epochs 5 \
+  --remove_prefix_in_ckpt "pipe.dit." \
+  --output_path "./models/train/FLUX.1-dev-Controlnet-Inpainting-Beta_lora" \
+  --lora_base_model "dit" \
+  --lora_target_modules "a_to_qkv,b_to_qkv,ff_a.0,ff_a.2,ff_b.0,ff_b.2,a_to_out,b_to_out,proj_out,norm.linear,norm1_a.linear,norm1_b.linear,to_qkv_mlp" \
+  --lora_rank 32 \
+  --extra_inputs "controlnet_image,controlnet_inpaint_mask" \
+  --align_to_opensource_format \
+  --use_gradient_checkpointing

examples/flux/model_training/lora/FLUX.1-dev-Controlnet-Union-alpha.sh

@@ -0,0 +1,17 @@
+accelerate launch examples/flux/model_training/train.py \
+  --dataset_base_path data/example_image_dataset \
+  --dataset_metadata_path data/example_image_dataset/metadata_controlnet_canny.csv \
+  --data_file_keys "image,controlnet_image" \
+  --max_pixels 1048576 \
+  --dataset_repeat 100 \
+  --model_id_with_origin_paths "black-forest-labs/FLUX.1-dev:flux1-dev.safetensors,black-forest-labs/FLUX.1-dev:text_encoder/model.safetensors,black-forest-labs/FLUX.1-dev:text_encoder_2/*.safetensors,black-forest-labs/FLUX.1-dev:ae.safetensors,InstantX/FLUX.1-dev-Controlnet-Union-alpha:diffusion_pytorch_model.safetensors" \
+  --learning_rate 1e-4 \
+  --num_epochs 5 \
+  --remove_prefix_in_ckpt "pipe.dit." \
+  --output_path "./models/train/FLUX.1-dev-Controlnet-Union-alpha_lora" \
+  --lora_base_model "dit" \
+  --lora_target_modules "a_to_qkv,b_to_qkv,ff_a.0,ff_a.2,ff_b.0,ff_b.2,a_to_out,b_to_out,proj_out,norm.linear,norm1_a.linear,norm1_b.linear,to_qkv_mlp" \
+  --lora_rank 32 \
+  --extra_inputs "controlnet_image,controlnet_processor_id" \
+  --align_to_opensource_format \
+  --use_gradient_checkpointing

examples/flux/model_training/lora/FLUX.1-dev-Controlnet-Upscaler.sh

@@ -0,0 +1,17 @@
+accelerate launch examples/flux/model_training/train.py \
+  --dataset_base_path data/example_image_dataset \
+  --dataset_metadata_path data/example_image_dataset/metadata_controlnet_upscale.csv \
+  --data_file_keys "image,controlnet_image" \
+  --max_pixels 1048576 \
+  --dataset_repeat 100 \
+  --model_id_with_origin_paths "black-forest-labs/FLUX.1-dev:flux1-dev.safetensors,black-forest-labs/FLUX.1-dev:text_encoder/model.safetensors,black-forest-labs/FLUX.1-dev:text_encoder_2/*.safetensors,black-forest-labs/FLUX.1-dev:ae.safetensors,jasperai/Flux.1-dev-Controlnet-Upscaler:diffusion_pytorch_model.safetensors" \
+  --learning_rate 1e-4 \
+  --num_epochs 5 \
+  --remove_prefix_in_ckpt "pipe.dit." \
+  --output_path "./models/train/FLUX.1-dev-Controlnet-Upscaler_lora" \
+  --lora_base_model "dit" \
+  --lora_target_modules "a_to_qkv,b_to_qkv,ff_a.0,ff_a.2,ff_b.0,ff_b.2,a_to_out,b_to_out,proj_out,norm.linear,norm1_a.linear,norm1_b.linear,to_qkv_mlp" \
+  --lora_rank 32 \
+  --extra_inputs "controlnet_image" \
+  --align_to_opensource_format \
+  --use_gradient_checkpointing

examples/flux/model_training/lora/FLUX.1-dev-EliGen.sh

@@ -0,0 +1,17 @@
+accelerate launch examples/flux/model_training/train.py \
+  --dataset_base_path data/example_image_dataset \
+  --dataset_metadata_path data/example_image_dataset/metadata_eligen.json \
+  --data_file_keys "image,eligen_entity_masks" \
+  --max_pixels 1048576 \
+  --dataset_repeat 50 \
+  --model_id_with_origin_paths "black-forest-labs/FLUX.1-dev:flux1-dev.safetensors,black-forest-labs/FLUX.1-dev:text_encoder/model.safetensors,black-forest-labs/FLUX.1-dev:text_encoder_2/*.safetensors,black-forest-labs/FLUX.1-dev:ae.safetensors" \
+  --learning_rate 1e-4 \
+  --num_epochs 5 \
+  --remove_prefix_in_ckpt "pipe.dit." \
+  --output_path "./models/train/FLUX.1-dev-EliGen_lora" \
+  --lora_base_model "dit" \
+  --lora_target_modules "a_to_qkv,b_to_qkv,ff_a.0,ff_a.2,ff_b.0,ff_b.2,a_to_out,b_to_out,proj_out,norm.linear,norm1_a.linear,norm1_b.linear,to_qkv_mlp" \
+  --lora_rank 32 \
+  --align_to_opensource_format \
+  --extra_inputs "eligen_entity_masks,eligen_entity_prompts" \
+  --use_gradient_checkpointing

examples/flux/model_training/lora/FLUX.1-dev-IP-Adapter.sh

@@ -0,0 +1,17 @@
+accelerate launch examples/flux/model_training/train.py \
+  --dataset_base_path data/example_image_dataset \
+  --dataset_metadata_path data/example_image_dataset/metadata_ipadapter.csv \
+  --data_file_keys "image,ipadapter_images" \
+  --max_pixels 1048576 \
+  --dataset_repeat 50 \
+  --model_id_with_origin_paths "black-forest-labs/FLUX.1-dev:flux1-dev.safetensors,black-forest-labs/FLUX.1-dev:text_encoder/model.safetensors,black-forest-labs/FLUX.1-dev:text_encoder_2/*.safetensors,black-forest-labs/FLUX.1-dev:ae.safetensors,InstantX/FLUX.1-dev-IP-Adapter:ip-adapter.bin,google/siglip-so400m-patch14-384:" \
+  --learning_rate 1e-4 \
+  --num_epochs 5 \
+  --remove_prefix_in_ckpt "pipe.dit." \
+  --output_path "./models/train/FLUX.1-dev-IP-Adapter_lora" \
+  --lora_base_model "dit" \
+  --lora_target_modules "a_to_qkv,b_to_qkv,ff_a.0,ff_a.2,ff_b.0,ff_b.2,a_to_out,b_to_out,proj_out,norm.linear,norm1_a.linear,norm1_b.linear,to_qkv_mlp" \
+  --lora_rank 32 \
+  --extra_inputs "ipadapter_images" \
+  --align_to_opensource_format \
+  --use_gradient_checkpointing

examples/flux/model_training/lora/FLUX.1-dev-InfiniteYou.sh

@@ -0,0 +1,17 @@
+accelerate launch examples/flux/model_training/train.py \
+  --dataset_base_path data/example_image_dataset \
+  --dataset_metadata_path data/example_image_dataset/metadata_infiniteyou.csv \
+  --data_file_keys "image,controlnet_image,infinityou_id_image" \
+  --max_pixels 1048576 \
+  --dataset_repeat 100 \
+  --model_id_with_origin_paths "black-forest-labs/FLUX.1-dev:flux1-dev.safetensors,black-forest-labs/FLUX.1-dev:text_encoder/model.safetensors,black-forest-labs/FLUX.1-dev:text_encoder_2/*.safetensors,black-forest-labs/FLUX.1-dev:ae.safetensors,ByteDance/InfiniteYou:infu_flux_v1.0/aes_stage2/image_proj_model.bin,ByteDance/InfiniteYou:infu_flux_v1.0/aes_stage2/InfuseNetModel/*.safetensors" \
+  --learning_rate 1e-4 \
+  --num_epochs 5 \
+  --remove_prefix_in_ckpt "pipe.dit." \
+  --output_path "./models/train/FLUX.1-dev-InfiniteYou_lora" \
+  --lora_base_model "dit" \
+  --lora_target_modules "a_to_qkv,b_to_qkv,ff_a.0,ff_a.2,ff_b.0,ff_b.2,a_to_out,b_to_out,proj_out,norm.linear,norm1_a.linear,norm1_b.linear,to_qkv_mlp" \
+  --lora_rank 32 \
+  --extra_inputs "controlnet_image,infinityou_id_image,infinityou_guidance" \
+  --align_to_opensource_format \
+  --use_gradient_checkpointing

examples/flux/model_training/lora/FLUX.1-dev.sh

@@ -0,0 +1,15 @@
+accelerate launch examples/flux/model_training/train.py \
+  --dataset_base_path data/example_image_dataset \
+  --dataset_metadata_path data/example_image_dataset/metadata.csv \
+  --max_pixels 1048576 \
+  --dataset_repeat 50 \
+  --model_id_with_origin_paths "black-forest-labs/FLUX.1-dev:flux1-dev.safetensors,black-forest-labs/FLUX.1-dev:text_encoder/model.safetensors,black-forest-labs/FLUX.1-dev:text_encoder_2/*.safetensors,black-forest-labs/FLUX.1-dev:ae.safetensors" \
+  --learning_rate 1e-4 \
+  --num_epochs 5 \
+  --remove_prefix_in_ckpt "pipe.dit." \
+  --output_path "./models/train/FLUX.1-dev_lora" \
+  --lora_base_model "dit" \
+  --lora_target_modules "a_to_qkv,b_to_qkv,ff_a.0,ff_a.2,ff_b.0,ff_b.2,a_to_out,b_to_out,proj_out,norm.linear,norm1_a.linear,norm1_b.linear,to_qkv_mlp" \
+  --lora_rank 32 \
+  --align_to_opensource_format \
+  --use_gradient_checkpointing

examples/flux/model_training/lora/Nexus-Gen.sh

@@ -0,0 +1,17 @@
+accelerate launch examples/flux/model_training/train.py \
+  --dataset_base_path data/example_image_dataset \
+  --dataset_metadata_path data/example_image_dataset/metadata_nexusgen_edit.csv \
+  --data_file_keys "image,nexus_gen_reference_image" \
+  --max_pixels 1048576 \
+  --dataset_repeat 400 \
+  --model_id_with_origin_paths "DiffSynth-Studio/Nexus-GenV2:model*.safetensors,DiffSynth-Studio/Nexus-GenV2:edit_decoder.bin,black-forest-labs/FLUX.1-dev:text_encoder/model.safetensors,black-forest-labs/FLUX.1-dev:text_encoder_2/*.safetensors,black-forest-labs/FLUX.1-dev:ae.safetensors" \
+  --learning_rate 1e-4 \
+  --num_epochs 5 \
+  --remove_prefix_in_ckpt "pipe.dit." \
+  --output_path "./models/train/FLUX.1-NexusGen-Edit_lora" \
+  --lora_base_model "dit" \
+  --lora_target_modules "a_to_qkv,b_to_qkv,ff_a.0,ff_a.2,ff_b.0,ff_b.2,a_to_out,b_to_out,proj_out,norm.linear,norm1_a.linear,norm1_b.linear,to_qkv_mlp" \
+  --lora_rank 32 \
+  --align_to_opensource_format \
+  --extra_inputs "nexus_gen_reference_image" \
+  --use_gradient_checkpointing

examples/flux/model_training/lora/Step1X-Edit.sh

@@ -0,0 +1,17 @@
+accelerate launch examples/flux/model_training/train.py \
+  --dataset_base_path data/example_image_dataset \
+  --dataset_metadata_path data/example_image_dataset/metadata_step1x.csv \
+  --data_file_keys "image,step1x_reference_image" \
+  --max_pixels 1048576 \
+  --dataset_repeat 50 \
+  --model_id_with_origin_paths "Qwen/Qwen2.5-VL-7B-Instruct:,stepfun-ai/Step1X-Edit:step1x-edit-i1258.safetensors,stepfun-ai/Step1X-Edit:vae.safetensors" \
+  --learning_rate 1e-4 \
+  --num_epochs 5 \
+  --remove_prefix_in_ckpt "pipe.dit." \
+  --output_path "./models/train/Step1X-Edit_lora" \
+  --lora_base_model "dit" \
+  --lora_target_modules "a_to_qkv,b_to_qkv,ff_a.0,ff_a.2,ff_b.0,ff_b.2,a_to_out,b_to_out,proj_out,norm.linear,norm1_a.linear,norm1_b.linear,to_qkv_mlp" \
+  --lora_rank 32 \
+  --extra_inputs "step1x_reference_image" \
+  --align_to_opensource_format \
+  --use_gradient_checkpointing

examples/flux/model_training/train.py

@@ -0,0 +1,193 @@
+import torch, os, argparse, accelerate
+from diffsynth.core import UnifiedDataset
+from diffsynth.pipelines.flux_image import FluxImagePipeline, ModelConfig
+from diffsynth.diffusion import *
+os.environ["TOKENIZERS_PARALLELISM"] = "false"
+
+
+class FluxTrainingModule(DiffusionTrainingModule):
+    def __init__(
+        self,
+        model_paths=None, model_id_with_origin_paths=None,
+        tokenizer_1_path=None, tokenizer_2_path=None,
+        trainable_models=None,
+        lora_base_model=None, lora_target_modules="", lora_rank=32, lora_checkpoint=None,
+        preset_lora_path=None, preset_lora_model=None,
+        use_gradient_checkpointing=True,
+        use_gradient_checkpointing_offload=False,
+        extra_inputs=None,
+        fp8_models=None,
+        offload_models=None,
+        device="cpu",
+        task="sft",
+    ):
+        super().__init__()
+        # Load models
+        model_configs = self.parse_model_configs(model_paths, model_id_with_origin_paths, fp8_models=fp8_models, offload_models=offload_models, device=device)
+        tokenizer_1_config = ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="tokenizer/") if tokenizer_1_path is None else ModelConfig(tokenizer_1_path)
+        tokenizer_2_config = ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="tokenizer_2/") if tokenizer_2_path is None else ModelConfig(tokenizer_2_path)
+        self.pipe = FluxImagePipeline.from_pretrained(torch_dtype=torch.bfloat16, device=device, model_configs=model_configs, tokenizer_1_config=tokenizer_1_config, tokenizer_2_config=tokenizer_2_config)
+        self.pipe = self.split_pipeline_units(task, self.pipe, trainable_models, lora_base_model)
+
+        # Training mode
+        self.switch_pipe_to_training_mode(
+            self.pipe, trainable_models,
+            lora_base_model, lora_target_modules, lora_rank, lora_checkpoint,
+            preset_lora_path, preset_lora_model,
+            task=task,
+        )
+        
+        # Other configs
+        self.use_gradient_checkpointing = use_gradient_checkpointing
+        self.use_gradient_checkpointing_offload = use_gradient_checkpointing_offload
+        self.extra_inputs = extra_inputs.split(",") if extra_inputs is not None else []
+        self.fp8_models = fp8_models
+        self.task = task
+        self.task_to_loss = {
+            "sft:data_process": lambda pipe, *args: args,
+            "direct_distill:data_process": lambda pipe, *args: args,
+            "sft": lambda pipe, inputs_shared, inputs_posi, inputs_nega: FlowMatchSFTLoss(pipe, **inputs_shared, **inputs_posi),
+            "sft:train": lambda pipe, inputs_shared, inputs_posi, inputs_nega: FlowMatchSFTLoss(pipe, **inputs_shared, **inputs_posi),
+            "direct_distill": lambda pipe, inputs_shared, inputs_posi, inputs_nega: DirectDistillLoss(pipe, **inputs_shared, **inputs_posi),
+            "direct_distill:train": lambda pipe, inputs_shared, inputs_posi, inputs_nega: DirectDistillLoss(pipe, **inputs_shared, **inputs_posi),
+        }
+        
+    def get_pipeline_inputs(self, data):
+        inputs_posi = {"prompt": data["prompt"]}
+        inputs_nega = {"negative_prompt": ""}
+        inputs_shared = {
+            # Assume you are using this pipeline for inference,
+            # please fill in the input parameters.
+            "input_image": data["image"],
+            "height": data["image"].size[1],
+            "width": data["image"].size[0],
+            # Please do not modify the following parameters
+            # unless you clearly know what this will cause.
+            "cfg_scale": 1,
+            "embedded_guidance": 1,
+            "t5_sequence_length": 512,
+            "tiled": False,
+            "rand_device": self.pipe.device,
+            "use_gradient_checkpointing": self.use_gradient_checkpointing,
+            "use_gradient_checkpointing_offload": self.use_gradient_checkpointing_offload,
+        }
+        inputs_shared = self.parse_extra_inputs(data, self.extra_inputs, inputs_shared)
+        return inputs_shared, inputs_posi, inputs_nega
+    
+    def forward(self, data, inputs=None):
+        if inputs is None: inputs = self.get_pipeline_inputs(data)
+        inputs = self.transfer_data_to_device(inputs, self.pipe.device, self.pipe.torch_dtype)
+        for unit in self.pipe.units:
+            inputs = self.pipe.unit_runner(unit, self.pipe, *inputs)
+        loss = self.task_to_loss[self.task](self.pipe, *inputs)
+        return loss
+
+
+def flux_parser():
+    parser = argparse.ArgumentParser(description="Simple example of a training script.")
+    parser = add_general_config(parser)
+    parser = add_image_size_config(parser)
+    parser.add_argument("--tokenizer_1_path", type=str, default=None, help="Path to CLIP tokenizer.")
+    parser.add_argument("--tokenizer_2_path", type=str, default=None, help="Path to T5 tokenizer.")
+    parser.add_argument("--align_to_opensource_format", default=False, action="store_true", help="Whether to align the lora format to opensource format. Only for DiT's LoRA.")
+    return parser
+
+
+def convert_lora_format(state_dict, alpha=None):
+    prefix_rename_dict = {
+        "single_blocks": "lora_unet_single_blocks",
+        "blocks": "lora_unet_double_blocks",
+    }
+    middle_rename_dict = {
+        "norm.linear": "modulation_lin",
+        "to_qkv_mlp": "linear1",
+        "proj_out": "linear2",
+        "norm1_a.linear": "img_mod_lin",
+        "norm1_b.linear": "txt_mod_lin",
+        "attn.a_to_qkv": "img_attn_qkv",
+        "attn.b_to_qkv": "txt_attn_qkv",
+        "attn.a_to_out": "img_attn_proj",
+        "attn.b_to_out": "txt_attn_proj",
+        "ff_a.0": "img_mlp_0",
+        "ff_a.2": "img_mlp_2",
+        "ff_b.0": "txt_mlp_0",
+        "ff_b.2": "txt_mlp_2",
+    }
+    suffix_rename_dict = {
+        "lora_B.weight": "lora_up.weight",
+        "lora_A.weight": "lora_down.weight",
+    }
+    state_dict_ = {}
+    for name, param in state_dict.items():
+        names = name.split(".")
+        if names[-2] != "lora_A" and names[-2] != "lora_B":
+            names.pop(-2)
+        prefix = names[0]
+        middle = ".".join(names[2:-2])
+        suffix = ".".join(names[-2:])
+        block_id = names[1]
+        if middle not in middle_rename_dict:
+            continue
+        rename = prefix_rename_dict[prefix] + "_" + block_id + "_" + middle_rename_dict[middle] + "." + suffix_rename_dict[suffix]
+        state_dict_[rename] = param
+        if rename.endswith("lora_up.weight"):
+            lora_alpha = alpha if alpha is not None else param.shape[-1]
+            state_dict_[rename.replace("lora_up.weight", "alpha")] = torch.tensor((lora_alpha,))[0]
+    return state_dict_
+
+
+if __name__ == "__main__":
+    parser = flux_parser()
+    args = parser.parse_args()
+    accelerator = accelerate.Accelerator(
+        gradient_accumulation_steps=args.gradient_accumulation_steps,
+        kwargs_handlers=[accelerate.DistributedDataParallelKwargs(find_unused_parameters=args.find_unused_parameters)],
+    )
+    dataset = UnifiedDataset(
+        base_path=args.dataset_base_path,
+        metadata_path=args.dataset_metadata_path,
+        repeat=args.dataset_repeat,
+        data_file_keys=args.data_file_keys.split(","),
+        main_data_operator=UnifiedDataset.default_image_operator(
+            base_path=args.dataset_base_path,
+            max_pixels=args.max_pixels,
+            height=args.height,
+            width=args.width,
+            height_division_factor=16,
+            width_division_factor=16,
+        )
+    )
+    model = FluxTrainingModule(
+        model_paths=args.model_paths,
+        model_id_with_origin_paths=args.model_id_with_origin_paths,
+        tokenizer_1_path=args.tokenizer_1_path,
+        tokenizer_2_path=args.tokenizer_2_path,
+        trainable_models=args.trainable_models,
+        lora_base_model=args.lora_base_model,
+        lora_target_modules=args.lora_target_modules,
+        lora_rank=args.lora_rank,
+        lora_checkpoint=args.lora_checkpoint,
+        preset_lora_path=args.preset_lora_path,
+        preset_lora_model=args.preset_lora_model,
+        use_gradient_checkpointing=args.use_gradient_checkpointing,
+        use_gradient_checkpointing_offload=args.use_gradient_checkpointing_offload,
+        extra_inputs=args.extra_inputs,
+        fp8_models=args.fp8_models,
+        offload_models=args.offload_models,
+        task=args.task,
+        device=accelerator.device,
+    )
+    model_logger = ModelLogger(
+        args.output_path,
+        remove_prefix_in_ckpt=args.remove_prefix_in_ckpt,
+        state_dict_converter=convert_lora_format if args.align_to_opensource_format else lambda x:x,
+    )
+    launcher_map = {
+        "sft:data_process": launch_data_process_task,
+        "direct_distill:data_process": launch_data_process_task,
+        "sft": launch_training_task,
+        "sft:train": launch_training_task,
+        "direct_distill": launch_training_task,
+        "direct_distill:train": launch_training_task,
+    }
+    launcher_map[args.task](accelerator, dataset, model, model_logger, args=args)

examples/flux/model_training/validate_full/FLEX.2-preview.py

@@ -0,0 +1,20 @@
+import torch
+from diffsynth.pipelines.flux_image import FluxImagePipeline, ModelConfig
+from diffsynth import load_state_dict
+
+
+pipe = FluxImagePipeline.from_pretrained(
+    torch_dtype=torch.bfloat16,
+    device="cuda",
+    model_configs=[
+        ModelConfig(model_id="ostris/Flex.2-preview", origin_file_pattern="Flex.2-preview.safetensors"),
+        ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="text_encoder/model.safetensors"),
+        ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="text_encoder_2/*.safetensors"),
+        ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="ae.safetensors"),
+    ],
+)
+state_dict = load_state_dict("models/train/FLEX.2-preview_full/epoch-0.safetensors")
+pipe.dit.load_state_dict(state_dict)
+
+image = pipe(prompt="dog,white and brown dog, sitting on wall, under pink flowers", seed=0)
+image.save("image_FLEX.2-preview_full.jpg")

examples/flux/model_training/validate_full/FLUX.1-Kontext-dev.py

@@ -0,0 +1,26 @@
+import torch
+from diffsynth.pipelines.flux_image import FluxImagePipeline, ModelConfig
+from diffsynth import load_state_dict
+from PIL import Image
+
+
+pipe = FluxImagePipeline.from_pretrained(
+    torch_dtype=torch.bfloat16,
+    device="cuda",
+    model_configs=[
+        ModelConfig(model_id="black-forest-labs/FLUX.1-Kontext-dev", origin_file_pattern="flux1-kontext-dev.safetensors"),
+        ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="text_encoder/model.safetensors"),
+        ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="text_encoder_2/*.safetensors"),
+        ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="ae.safetensors"),
+    ],
+)
+state_dict = load_state_dict("models/train/FLUX.1-Kontext-dev_full/epoch-0.safetensors")
+pipe.dit.load_state_dict(state_dict)
+
+image = pipe(
+    prompt="Make the dog turn its head around.",
+    kontext_images=Image.open("data/example_image_dataset/2.jpg").resize((768, 768)),
+    height=768, width=768,
+    seed=0
+)
+image.save("image_FLUX.1-Kontext-dev_full.jpg")

examples/flux/model_training/validate_full/FLUX.1-Krea-dev.py

@@ -0,0 +1,20 @@
+import torch
+from diffsynth.pipelines.flux_image import FluxImagePipeline, ModelConfig
+from diffsynth import load_state_dict
+
+
+pipe = FluxImagePipeline.from_pretrained(
+    torch_dtype=torch.bfloat16,
+    device="cuda",
+    model_configs=[
+        ModelConfig(model_id="black-forest-labs/FLUX.1-Krea-dev", origin_file_pattern="flux1-krea-dev.safetensors"),
+        ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="text_encoder/model.safetensors"),
+        ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="text_encoder_2/*.safetensors"),
+        ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="ae.safetensors"),
+    ],
+)
+state_dict = load_state_dict("models/train/FLUX.1-Krea-dev_full/epoch-0.safetensors")
+pipe.dit.load_state_dict(state_dict)
+
+image = pipe(prompt="a dog", seed=0)
+image.save("image_FLUX.1-Krea-dev_full.jpg")

examples/flux/model_training/validate_full/FLUX.1-dev-AttriCtrl.py

@@ -0,0 +1,21 @@
+import torch
+from diffsynth.pipelines.flux_image import FluxImagePipeline, ModelConfig
+from diffsynth import load_state_dict
+
+
+pipe = FluxImagePipeline.from_pretrained(
+    torch_dtype=torch.bfloat16,
+    device="cuda",
+    model_configs=[
+        ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="flux1-dev.safetensors"),
+        ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="text_encoder/model.safetensors"),
+        ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="text_encoder_2/*.safetensors"),
+        ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="ae.safetensors"),
+        ModelConfig(model_id="DiffSynth-Studio/AttriCtrl-FLUX.1-Dev", origin_file_pattern="models/brightness.safetensors")
+    ],
+)
+state_dict = load_state_dict("models/train/FLUX.1-dev-AttriCtrl_full/epoch-0.safetensors")
+pipe.value_controller.encoders[0].load_state_dict(state_dict)
+
+image = pipe(prompt="a cat", seed=0, value_controller_inputs=0.1, rand_device="cuda")
+image.save("image_FLUX.1-dev-AttriCtrl_full.jpg")

examples/flux/model_training/validate_full/FLUX.1-dev-Controlnet-Inpainting-Beta.py

@@ -0,0 +1,31 @@
+import torch
+from diffsynth.pipelines.flux_image import FluxImagePipeline, ModelConfig, ControlNetInput
+from diffsynth import load_state_dict
+from PIL import Image
+
+
+pipe = FluxImagePipeline.from_pretrained(
+    torch_dtype=torch.bfloat16,
+    device="cuda",
+    model_configs=[
+        ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="flux1-dev.safetensors"),
+        ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="text_encoder/model.safetensors"),
+        ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="text_encoder_2/*.safetensors"),
+        ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="ae.safetensors"),
+        ModelConfig(model_id="alimama-creative/FLUX.1-dev-Controlnet-Inpainting-Beta", origin_file_pattern="diffusion_pytorch_model.safetensors"),
+    ],
+)
+state_dict = load_state_dict("models/train/FLUX.1-dev-Controlnet-Inpainting-Beta_full/epoch-0.safetensors")
+pipe.controlnet.models[0].load_state_dict(state_dict)
+
+image = pipe(
+    prompt="a cat sitting on a chair, wearing sunglasses",
+    controlnet_inputs=[ControlNetInput(
+        image=Image.open("data/example_image_dataset/inpaint/image_1.jpg"),
+        inpaint_mask=Image.open("data/example_image_dataset/inpaint/mask.jpg"),
+        scale=0.9
+    )],
+    height=1024, width=1024,
+    seed=0, rand_device="cuda",
+)
+image.save("image_FLUX.1-dev-Controlnet-Inpainting-Beta_full.jpg")

examples/flux/model_training/validate_full/FLUX.1-dev-Controlnet-Union-alpha.py

@@ -0,0 +1,31 @@
+import torch
+from diffsynth.pipelines.flux_image import FluxImagePipeline, ModelConfig, ControlNetInput
+from diffsynth import load_state_dict
+from PIL import Image
+
+
+pipe = FluxImagePipeline.from_pretrained(
+    torch_dtype=torch.bfloat16,
+    device="cuda",
+    model_configs=[
+        ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="flux1-dev.safetensors"),
+        ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="text_encoder/model.safetensors"),
+        ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="text_encoder_2/*.safetensors"),
+        ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="ae.safetensors"),
+        ModelConfig(model_id="InstantX/FLUX.1-dev-Controlnet-Union-alpha", origin_file_pattern="diffusion_pytorch_model.safetensors"),
+    ],
+)
+state_dict = load_state_dict("models/train/FLUX.1-dev-Controlnet-Union-alpha_full/epoch-0.safetensors")
+pipe.controlnet.models[0].load_state_dict(state_dict)
+
+image = pipe(
+    prompt="a dog",
+    controlnet_inputs=[ControlNetInput(
+        image=Image.open("data/example_image_dataset/canny/image_1.jpg"),
+        scale=0.9,
+        processor_id="canny",
+    )],
+    height=768, width=768,
+    seed=0, rand_device="cuda",
+)
+image.save("image_FLUX.1-dev-Controlnet-Union-alpha_full.jpg")

examples/flux/model_training/validate_full/FLUX.1-dev-Controlnet-Upscaler.py

@@ -0,0 +1,30 @@
+import torch
+from diffsynth.pipelines.flux_image import FluxImagePipeline, ModelConfig, ControlNetInput
+from diffsynth import load_state_dict
+from PIL import Image
+
+
+pipe = FluxImagePipeline.from_pretrained(
+    torch_dtype=torch.bfloat16,
+    device="cuda",
+    model_configs=[
+        ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="flux1-dev.safetensors"),
+        ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="text_encoder/model.safetensors"),
+        ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="text_encoder_2/*.safetensors"),
+        ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="ae.safetensors"),
+        ModelConfig(model_id="jasperai/Flux.1-dev-Controlnet-Upscaler", origin_file_pattern="diffusion_pytorch_model.safetensors"),
+    ],
+)
+state_dict = load_state_dict("models/train/FLUX.1-dev-Controlnet-Upscaler_full/epoch-0.safetensors")
+pipe.controlnet.models[0].load_state_dict(state_dict)
+
+image = pipe(
+    prompt="a dog",
+    controlnet_inputs=[ControlNetInput(
+        image=Image.open("data/example_image_dataset/upscale/image_1.jpg"),
+        scale=0.9
+    )],
+    height=768, width=768,
+    seed=0, rand_device="cuda",
+)
+image.save("image_FLUX.1-dev-Controlnet-Upscaler_full.jpg")

examples/flux/model_training/validate_full/FLUX.1-dev-IP-Adapter.py

@@ -0,0 +1,28 @@
+import torch
+from diffsynth.pipelines.flux_image import FluxImagePipeline, ModelConfig
+from diffsynth import load_state_dict
+from PIL import Image
+
+
+pipe = FluxImagePipeline.from_pretrained(
+    torch_dtype=torch.bfloat16,
+    device="cuda",
+    model_configs=[
+        ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="flux1-dev.safetensors"),
+        ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="text_encoder/model.safetensors"),
+        ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="text_encoder_2/*.safetensors"),
+        ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="ae.safetensors"),
+        ModelConfig(model_id="InstantX/FLUX.1-dev-IP-Adapter", origin_file_pattern="ip-adapter.bin"),
+        ModelConfig(model_id="google/siglip-so400m-patch14-384"),
+    ],
+)
+state_dict = load_state_dict("models/train/FLUX.1-dev-IP-Adapter_full/epoch-0.safetensors")
+pipe.ipadapter.load_state_dict(state_dict)
+
+image = pipe(
+    prompt="a dog",
+    ipadapter_images=Image.open("data/example_image_dataset/1.jpg"),
+    height=768, width=768,
+    seed=0
+)
+image.save("image_FLUX.1-dev-IP-Adapter_full.jpg")

examples/flux/model_training/validate_full/FLUX.1-dev-InfiniteYou.py

@@ -0,0 +1,33 @@
+import torch
+from diffsynth.pipelines.flux_image import FluxImagePipeline, ModelConfig, ControlNetInput
+from diffsynth import load_state_dict
+from PIL import Image
+
+
+pipe = FluxImagePipeline.from_pretrained(
+    torch_dtype=torch.bfloat16,
+    device="cuda",
+    model_configs=[
+        ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="flux1-dev.safetensors"),
+        ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="text_encoder/model.safetensors"),
+        ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="text_encoder_2/*.safetensors"),
+        ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="ae.safetensors"),
+        ModelConfig(model_id="ByteDance/InfiniteYou", origin_file_pattern="infu_flux_v1.0/aes_stage2/image_proj_model.bin"),
+        ModelConfig(model_id="ByteDance/InfiniteYou", origin_file_pattern="infu_flux_v1.0/aes_stage2/InfuseNetModel/*.safetensors"),
+    ],
+)
+state_dict = load_state_dict("models/train/FLUX.1-dev-InfiniteYou_full/epoch-0.safetensors")
+state_dict_projector = {i.replace("image_proj_model.", ""): state_dict[i] for i in state_dict if i.startswith("image_proj_model.")}
+pipe.image_proj_model.load_state_dict(state_dict_projector)
+state_dict_controlnet = {i.replace("controlnet.models.0.", ""): state_dict[i] for i in state_dict if i.startswith("controlnet.models.0.")}
+pipe.controlnet.models[0].load_state_dict(state_dict_controlnet)
+
+image = pipe(
+    prompt="a man with a red hat",
+    controlnet_inputs=[ControlNetInput(
+        image=Image.open("data/example_image_dataset/infiniteyou/image_1.jpg"),
+    )],
+    height=1024, width=1024,
+    seed=0, rand_device="cuda",
+)
+image.save("image_FLUX.1-dev-InfiniteYou_full.jpg")

examples/flux/model_training/validate_full/FLUX.1-dev-LoRA-Encoder.py

@@ -0,0 +1,25 @@
+import torch
+from diffsynth.pipelines.flux_image import FluxImagePipeline, ModelConfig
+from diffsynth import load_state_dict
+
+
+pipe = FluxImagePipeline.from_pretrained(
+    torch_dtype=torch.bfloat16,
+    device="cuda",
+    model_configs=[
+        ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="flux1-dev.safetensors"),
+        ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="text_encoder/model.safetensors"),
+        ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="text_encoder_2/*.safetensors"),
+        ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="ae.safetensors"),
+        ModelConfig(model_id="DiffSynth-Studio/LoRA-Encoder-FLUX.1-Dev", origin_file_pattern="model.safetensors"),
+    ],
+)
+pipe.enable_lora_magic()
+state_dict = load_state_dict("models/train/FLUX.1-dev-LoRA-Encoder_full/epoch-0.safetensors")
+pipe.lora_encoder.load_state_dict(state_dict)
+
+lora = ModelConfig(model_id="VoidOc/flux_animal_forest1", origin_file_pattern="20.safetensors")
+pipe.load_lora(pipe.dit, lora, hotload=True) # Use `pipe.clear_lora()` to drop the loaded LoRA.
+
+image = pipe(prompt="", seed=0, lora_encoder_inputs=lora)
+image.save("image_FLUX.1-dev-LoRA-Encoder_full.jpg")

examples/flux/model_training/validate_full/FLUX.1-dev.py

@@ -0,0 +1,20 @@
+import torch
+from diffsynth.pipelines.flux_image import FluxImagePipeline, ModelConfig
+from diffsynth import load_state_dict
+
+
+pipe = FluxImagePipeline.from_pretrained(
+    torch_dtype=torch.bfloat16,
+    device="cuda",
+    model_configs=[
+        ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="flux1-dev.safetensors"),
+        ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="text_encoder/model.safetensors"),
+        ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="text_encoder_2/*.safetensors"),
+        ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="ae.safetensors"),
+    ],
+)
+state_dict = load_state_dict("models/train/FLUX.1-dev_full/epoch-0.safetensors")
+pipe.dit.load_state_dict(state_dict)
+
+image = pipe(prompt="a dog", seed=0)
+image.save("image_FLUX.1-dev_full.jpg")

examples/flux/model_training/validate_full/Nexus-Gen.py

@@ -0,0 +1,28 @@
+import torch
+from PIL import Image
+from diffsynth.pipelines.flux_image import FluxImagePipeline, ModelConfig
+from diffsynth import load_state_dict
+
+pipe = FluxImagePipeline.from_pretrained(
+    torch_dtype=torch.bfloat16,
+    device="cuda",
+    model_configs=[
+        ModelConfig(model_id="DiffSynth-Studio/Nexus-GenV2", origin_file_pattern="model*.safetensors"),
+        ModelConfig(model_id="DiffSynth-Studio/Nexus-GenV2", origin_file_pattern="edit_decoder.bin"),
+        ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="text_encoder/model.safetensors"),
+        ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="text_encoder_2/*.safetensors"),
+        ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="ae.safetensors"),
+    ],
+)
+state_dict = load_state_dict("models/train/FLUX.1-NexusGen-Edit_full/epoch-0.safetensors")
+pipe.dit.load_state_dict(state_dict)
+
+ref_image = Image.open("data/example_image_dataset/nexus_gen/image_1.png").convert("RGB")
+prompt = "Add a pair of sunglasses."
+image = pipe(
+    prompt=prompt, negative_prompt="",
+    seed=42, cfg_scale=2.0, num_inference_steps=50,
+    nexus_gen_reference_image=ref_image,
+    height=512, width=512,
+)
+image.save("NexusGen-Edit_full.jpg")

examples/flux/model_training/validate_full/Step1X-Edit.py

@@ -0,0 +1,25 @@
+import torch
+from diffsynth.pipelines.flux_image import FluxImagePipeline, ModelConfig
+from diffsynth import load_state_dict
+from PIL import Image
+
+
+pipe = FluxImagePipeline.from_pretrained(
+    torch_dtype=torch.bfloat16,
+    device="cuda",
+    model_configs=[
+        ModelConfig(model_id="Qwen/Qwen2.5-VL-7B-Instruct"),
+        ModelConfig(model_id="stepfun-ai/Step1X-Edit", origin_file_pattern="step1x-edit-i1258.safetensors"),
+        ModelConfig(model_id="stepfun-ai/Step1X-Edit", origin_file_pattern="vae.safetensors"),
+    ],
+)
+state_dict = load_state_dict("models/train/Step1X-Edit_full/epoch-0.safetensors")
+pipe.dit.load_state_dict(state_dict)
+
+image = pipe(
+    prompt="Make the dog turn its head around.",
+    step1x_reference_image=Image.open("data/example_image_dataset/2.jpg").resize((768, 768)),
+    height=768, width=768, cfg_scale=6,
+    seed=0
+)
+image.save("image_Step1X-Edit_full.jpg")

examples/flux/model_training/validate_lora/FLEX.2-preview.py

@@ -0,0 +1,18 @@
+import torch
+from diffsynth.pipelines.flux_image import FluxImagePipeline, ModelConfig
+
+
+pipe = FluxImagePipeline.from_pretrained(
+    torch_dtype=torch.bfloat16,
+    device="cuda",
+    model_configs=[
+        ModelConfig(model_id="ostris/Flex.2-preview", origin_file_pattern="Flex.2-preview.safetensors"),
+        ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="text_encoder/model.safetensors"),
+        ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="text_encoder_2/*.safetensors"),
+        ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="ae.safetensors"),
+    ],
+)
+pipe.load_lora(pipe.dit, "models/train/FLEX.2-preview_lora/epoch-4.safetensors", alpha=1)
+
+image = pipe(prompt="dog,white and brown dog, sitting on wall, under pink flowers", seed=0)
+image.save("image_FLEX.2-preview_lora.jpg")

examples/flux/model_training/validate_lora/FLUX.1-Kontext-dev.py

@@ -0,0 +1,24 @@
+import torch
+from diffsynth.pipelines.flux_image import FluxImagePipeline, ModelConfig
+from PIL import Image
+
+
+pipe = FluxImagePipeline.from_pretrained(
+    torch_dtype=torch.bfloat16,
+    device="cuda",
+    model_configs=[
+        ModelConfig(model_id="black-forest-labs/FLUX.1-Kontext-dev", origin_file_pattern="flux1-kontext-dev.safetensors"),
+        ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="text_encoder/model.safetensors"),
+        ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="text_encoder_2/*.safetensors"),
+        ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="ae.safetensors"),
+    ],
+)
+pipe.load_lora(pipe.dit, "models/train/FLUX.1-Kontext-dev_lora/epoch-4.safetensors", alpha=1)
+
+image = pipe(
+    prompt="Make the dog turn its head around.",
+    kontext_images=Image.open("data/example_image_dataset/2.jpg").resize((768, 768)),
+    height=768, width=768,
+    seed=0
+)
+image.save("image_FLUX.1-Kontext-dev_lora.jpg")

examples/flux/model_training/validate_lora/FLUX.1-Krea-dev.py

@@ -0,0 +1,18 @@
+import torch
+from diffsynth.pipelines.flux_image import FluxImagePipeline, ModelConfig
+
+
+pipe = FluxImagePipeline.from_pretrained(
+    torch_dtype=torch.bfloat16,
+    device="cuda",
+    model_configs=[
+        ModelConfig(model_id="black-forest-labs/FLUX.1-Krea-dev", origin_file_pattern="flux1-krea-dev.safetensors"),
+        ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="text_encoder/model.safetensors"),
+        ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="text_encoder_2/*.safetensors"),
+        ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="ae.safetensors"),
+    ],
+)
+pipe.load_lora(pipe.dit, "models/train/FLUX.1-Krea-dev_lora/epoch-4.safetensors", alpha=1)
+
+image = pipe(prompt="a dog", seed=0)
+image.save("image_FLUX.1-Krea-dev_lora.jpg")

examples/flux/model_training/validate_lora/FLUX.1-dev-AttriCtrl.py

@@ -0,0 +1,19 @@
+import torch
+from diffsynth.pipelines.flux_image import FluxImagePipeline, ModelConfig
+
+
+pipe = FluxImagePipeline.from_pretrained(
+    torch_dtype=torch.bfloat16,
+    device="cuda",
+    model_configs=[
+        ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="flux1-dev.safetensors"),
+        ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="text_encoder/model.safetensors"),
+        ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="text_encoder_2/*.safetensors"),
+        ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="ae.safetensors"),
+        ModelConfig(model_id="DiffSynth-Studio/AttriCtrl-FLUX.1-Dev", origin_file_pattern="models/brightness.safetensors")
+    ],
+)
+pipe.load_lora(pipe.dit, "models/train/FLUX.1-dev-AttriCtrl_lora/epoch-3.safetensors", alpha=1)
+
+image = pipe(prompt="a cat", seed=0, value_controller_inputs=0.1, rand_device="cuda")
+image.save("image_FLUX.1-dev-AttriCtrl_lora.jpg")

examples/flux/model_training/validate_lora/FLUX.1-dev-Controlnet-Inpainting-Beta.py

@@ -0,0 +1,29 @@
+import torch
+from diffsynth.pipelines.flux_image import FluxImagePipeline, ModelConfig, ControlNetInput
+from PIL import Image
+
+
+pipe = FluxImagePipeline.from_pretrained(
+    torch_dtype=torch.bfloat16,
+    device="cuda",
+    model_configs=[
+        ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="flux1-dev.safetensors"),
+        ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="text_encoder/model.safetensors"),
+        ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="text_encoder_2/*.safetensors"),
+        ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="ae.safetensors"),
+        ModelConfig(model_id="alimama-creative/FLUX.1-dev-Controlnet-Inpainting-Beta", origin_file_pattern="diffusion_pytorch_model.safetensors"),
+    ],
+)
+pipe.load_lora(pipe.dit, "models/train/FLUX.1-dev-Controlnet-Inpainting-Beta_lora/epoch-4.safetensors", alpha=1)
+
+image = pipe(
+    prompt="a cat sitting on a chair, wearing sunglasses",
+    controlnet_inputs=[ControlNetInput(
+        image=Image.open("data/example_image_dataset/inpaint/image_1.jpg"),
+        inpaint_mask=Image.open("data/example_image_dataset/inpaint/mask.jpg"),
+        scale=0.9
+    )],
+    height=1024, width=1024,
+    seed=0, rand_device="cuda",
+)
+image.save("image_FLUX.1-dev-Controlnet-Inpainting-Beta_lora.jpg")

examples/flux/model_training/validate_lora/FLUX.1-dev-Controlnet-Union-alpha.py

@@ -0,0 +1,29 @@
+import torch
+from diffsynth.pipelines.flux_image import FluxImagePipeline, ModelConfig, ControlNetInput
+from PIL import Image
+
+
+pipe = FluxImagePipeline.from_pretrained(
+    torch_dtype=torch.bfloat16,
+    device="cuda",
+    model_configs=[
+        ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="flux1-dev.safetensors"),
+        ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="text_encoder/model.safetensors"),
+        ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="text_encoder_2/*.safetensors"),
+        ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="ae.safetensors"),
+        ModelConfig(model_id="InstantX/FLUX.1-dev-Controlnet-Union-alpha", origin_file_pattern="diffusion_pytorch_model.safetensors"),
+    ],
+)
+pipe.load_lora(pipe.dit, "models/train/FLUX.1-dev-Controlnet-Union-alpha_lora/epoch-4.safetensors", alpha=1)
+
+image = pipe(
+    prompt="a dog",
+    controlnet_inputs=[ControlNetInput(
+        image=Image.open("data/example_image_dataset/canny/image_1.jpg"),
+        scale=0.9,
+        processor_id="canny",
+    )],
+    height=768, width=768,
+    seed=0, rand_device="cuda",
+)
+image.save("image_FLUX.1-dev-Controlnet-Union-alpha_lora.jpg")

examples/flux/model_training/validate_lora/FLUX.1-dev-Controlnet-Upscaler.py

@@ -0,0 +1,28 @@
+import torch
+from diffsynth.pipelines.flux_image import FluxImagePipeline, ModelConfig, ControlNetInput
+from PIL import Image
+
+
+pipe = FluxImagePipeline.from_pretrained(
+    torch_dtype=torch.bfloat16,
+    device="cuda",
+    model_configs=[
+        ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="flux1-dev.safetensors"),
+        ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="text_encoder/model.safetensors"),
+        ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="text_encoder_2/*.safetensors"),
+        ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="ae.safetensors"),
+        ModelConfig(model_id="jasperai/Flux.1-dev-Controlnet-Upscaler", origin_file_pattern="diffusion_pytorch_model.safetensors"),
+    ],
+)
+pipe.load_lora(pipe.dit, "models/train/FLUX.1-dev-Controlnet-Upscaler_lora/epoch-4.safetensors", alpha=1)
+
+image = pipe(
+    prompt="a dog",
+    controlnet_inputs=[ControlNetInput(
+        image=Image.open("data/example_image_dataset/upscale/image_1.jpg"),
+        scale=0.9
+    )],
+    height=768, width=768,
+    seed=0, rand_device="cuda",
+)
+image.save("image_FLUX.1-dev-Controlnet-Upscaler_lora.jpg")

examples/flux/model_training/validate_lora/FLUX.1-dev-EliGen.py

@@ -0,0 +1,33 @@
+import torch
+from PIL import Image
+from diffsynth.pipelines.flux_image import FluxImagePipeline, ModelConfig
+
+pipe = FluxImagePipeline.from_pretrained(
+    torch_dtype=torch.bfloat16,
+    device="cuda",
+    model_configs=[
+        ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="flux1-dev.safetensors"),
+        ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="text_encoder/model.safetensors"),
+        ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="text_encoder_2/*.safetensors"),
+        ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="ae.safetensors"),
+    ],
+)
+
+pipe.load_lora(pipe.dit, "models/train/FLUX.1-dev-EliGen_lora/epoch-4.safetensors", alpha=1)
+
+entity_prompts = ["A beautiful girl", "sign 'Entity Control'", "shorts", "shirt"]
+global_prompt = "A beautiful girl wearing shirt and shorts in the street,  holding a sign 'Entity Control'"
+masks = [Image.open(f"data/example_image_dataset/eligen/{i}.png").convert('RGB') for i in range(len(entity_prompts))]
+# generate image
+image = pipe(
+    prompt=global_prompt,
+    cfg_scale=1.0,
+    num_inference_steps=50,
+    embedded_guidance=3.5,
+    seed=42,
+    height=1024,
+    width=1024,
+    eligen_entity_prompts=entity_prompts,
+    eligen_entity_masks=masks,
+)
+image.save(f"EliGen_lora.png")

examples/flux/model_training/validate_lora/FLUX.1-dev-IP-Adapter.py

@@ -0,0 +1,26 @@
+import torch
+from diffsynth.pipelines.flux_image import FluxImagePipeline, ModelConfig
+from PIL import Image
+
+
+pipe = FluxImagePipeline.from_pretrained(
+    torch_dtype=torch.bfloat16,
+    device="cuda",
+    model_configs=[
+        ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="flux1-dev.safetensors"),
+        ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="text_encoder/model.safetensors"),
+        ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="text_encoder_2/*.safetensors"),
+        ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="ae.safetensors"),
+        ModelConfig(model_id="InstantX/FLUX.1-dev-IP-Adapter", origin_file_pattern="ip-adapter.bin"),
+        ModelConfig(model_id="google/siglip-so400m-patch14-384"),
+    ],
+)
+pipe.load_lora(pipe.dit, "models/train/FLUX.1-dev-IP-Adapter_lora/epoch-4.safetensors", alpha=1)
+
+image = pipe(
+    prompt="dog,white and brown dog, sitting on wall, under pink flowers",
+    ipadapter_images=Image.open("data/example_image_dataset/1.jpg"),
+    height=768, width=768,
+    seed=0
+)
+image.save("image_FLUX.1-dev-IP-Adapter_lora.jpg")

examples/flux/model_training/validate_lora/FLUX.1-dev-InfiniteYou.py

@@ -0,0 +1,28 @@
+import torch
+from diffsynth.pipelines.flux_image import FluxImagePipeline, ModelConfig, ControlNetInput
+from PIL import Image
+
+
+pipe = FluxImagePipeline.from_pretrained(
+    torch_dtype=torch.bfloat16,
+    device="cuda",
+    model_configs=[
+        ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="flux1-dev.safetensors"),
+        ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="text_encoder/model.safetensors"),
+        ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="text_encoder_2/*.safetensors"),
+        ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="ae.safetensors"),
+        ModelConfig(model_id="ByteDance/InfiniteYou", origin_file_pattern="infu_flux_v1.0/aes_stage2/image_proj_model.bin"),
+        ModelConfig(model_id="ByteDance/InfiniteYou", origin_file_pattern="infu_flux_v1.0/aes_stage2/InfuseNetModel/*.safetensors"),
+    ],
+)
+pipe.load_lora(pipe.dit, "models/train/FLUX.1-dev-InfiniteYou_lora/epoch-4.safetensors", alpha=1)
+
+image = pipe(
+    prompt="a man with a red hat",
+    controlnet_inputs=[ControlNetInput(
+        image=Image.open("data/example_image_dataset/infiniteyou/image_1.jpg"),
+    )],
+    height=1024, width=1024,
+    seed=0, rand_device="cuda",
+)
+image.save("image_FLUX.1-dev-InfiniteYou_lora.jpg")

examples/flux/model_training/validate_lora/FLUX.1-dev.py

@@ -0,0 +1,18 @@
+import torch
+from diffsynth.pipelines.flux_image import FluxImagePipeline, ModelConfig
+
+
+pipe = FluxImagePipeline.from_pretrained(
+    torch_dtype=torch.bfloat16,
+    device="cuda",
+    model_configs=[
+        ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="flux1-dev.safetensors"),
+        ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="text_encoder/model.safetensors"),
+        ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="text_encoder_2/*.safetensors"),
+        ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="ae.safetensors"),
+    ],
+)
+pipe.load_lora(pipe.dit, "models/train/FLUX.1-dev_lora/epoch-4.safetensors", alpha=1)
+
+image = pipe(prompt="a dog", seed=0)
+image.save("image_FLUX.1-dev_lora.jpg")

examples/flux/model_training/validate_lora/Nexus-Gen.py

@@ -0,0 +1,26 @@
+import torch
+from PIL import Image
+from diffsynth.pipelines.flux_image import FluxImagePipeline, ModelConfig
+
+pipe = FluxImagePipeline.from_pretrained(
+    torch_dtype=torch.bfloat16,
+    device="cuda",
+    model_configs=[
+        ModelConfig(model_id="DiffSynth-Studio/Nexus-GenV2", origin_file_pattern="model*.safetensors"),
+        ModelConfig(model_id="DiffSynth-Studio/Nexus-GenV2", origin_file_pattern="edit_decoder.bin"),
+        ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="text_encoder/model.safetensors"),
+        ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="text_encoder_2/*.safetensors"),
+        ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="ae.safetensors"),
+    ],
+)
+pipe.load_lora(pipe.dit, "models/train/FLUX.1-NexusGen-Edit_lora/epoch-4.safetensors", alpha=1)
+
+ref_image = Image.open("data/example_image_dataset/nexus_gen/image_1.png").convert("RGB")
+prompt = "Add a pair of sunglasses."
+image = pipe(
+    prompt=prompt, negative_prompt="",
+    seed=42, cfg_scale=1.0, num_inference_steps=50,
+    nexus_gen_reference_image=ref_image,
+    height=512, width=512,
+)
+image.save("NexusGen-Edit_lora.jpg")

examples/flux/model_training/validate_lora/Step1X-Edit.py

@@ -0,0 +1,23 @@
+import torch
+from diffsynth.pipelines.flux_image import FluxImagePipeline, ModelConfig
+from PIL import Image
+
+
+pipe = FluxImagePipeline.from_pretrained(
+    torch_dtype=torch.bfloat16,
+    device="cuda",
+    model_configs=[
+        ModelConfig(model_id="Qwen/Qwen2.5-VL-7B-Instruct"),
+        ModelConfig(model_id="stepfun-ai/Step1X-Edit", origin_file_pattern="step1x-edit-i1258.safetensors"),
+        ModelConfig(model_id="stepfun-ai/Step1X-Edit", origin_file_pattern="vae.safetensors"),
+    ],
+)
+pipe.load_lora(pipe.dit, "models/train/Step1X-Edit_lora/epoch-4.safetensors", alpha=1)
+
+image = pipe(
+    prompt="Make the dog turn its head around.",
+    step1x_reference_image=Image.open("data/example_image_dataset/2.jpg").resize((768, 768)),
+    height=768, width=768, cfg_scale=6,
+    seed=0
+)
+image.save("image_Step1X-Edit_lora.jpg")