support klein edit

examples/flux2/model_training/full/FLUX.2-klein-4B.sh

@@ -11,3 +11,20 @@ accelerate launch examples/flux2/model_training/train.py \
   --output_path "./models/train/FLUX.2-klein-4B_full" \
   --trainable_models "dit" \
   --use_gradient_checkpointing
+
+# Edit
+# accelerate launch examples/flux2/model_training/train.py \
+#   --dataset_base_path data/example_image_dataset \
+#   --dataset_metadata_path data/example_image_dataset/metadata_qwen_imgae_edit_multi.json \
+#   --data_file_keys "image,edit_image" \
+#   --extra_inputs "edit_image" \
+#   --max_pixels 1048576 \
+#   --dataset_repeat 50 \
+#   --model_id_with_origin_paths "black-forest-labs/FLUX.2-klein-4B:text_encoder/*.safetensors,black-forest-labs/FLUX.2-klein-4B:transformer/*.safetensors,black-forest-labs/FLUX.2-klein-4B:vae/diffusion_pytorch_model.safetensors" \
+#   --tokenizer_path "black-forest-labs/FLUX.2-klein-4B:tokenizer/" \
+#   --learning_rate 1e-5 \
+#   --num_epochs 2 \
+#   --remove_prefix_in_ckpt "pipe.dit." \
+#   --output_path "./models/train/FLUX.2-klein-4B_full" \
+#   --trainable_models "dit" \
+#   --use_gradient_checkpointing

examples/flux2/model_training/full/FLUX.2-klein-9B.sh

@@ -1,4 +1,5 @@
-accelerate launch examples/flux2/model_training/train.py \
+# This script is tested on 8*A100
+accelerate launch --config_file examples/flux2/model_training/full/accelerate_config.yaml examples/flux2/model_training/train.py \
   --dataset_base_path data/example_image_dataset \
   --dataset_metadata_path data/example_image_dataset/metadata.csv \
   --max_pixels 1048576 \
@@ -11,3 +12,20 @@ accelerate launch examples/flux2/model_training/train.py \
   --output_path "./models/train/FLUX.2-klein-9B_full" \
   --trainable_models "dit" \
   --use_gradient_checkpointing
+
+# Edit
+# accelerate launch --config_file examples/flux2/model_training/full/accelerate_config.yaml examples/flux2/model_training/train.py \
+#   --dataset_base_path data/example_image_dataset \
+#   --dataset_metadata_path data/example_image_dataset/metadata_qwen_imgae_edit_multi.json \
+#   --data_file_keys "image,edit_image" \
+#   --extra_inputs "edit_image" \
+#   --max_pixels 1048576 \
+#   --dataset_repeat 50 \
+#   --model_id_with_origin_paths "black-forest-labs/FLUX.2-klein-9B:text_encoder/*.safetensors,black-forest-labs/FLUX.2-klein-9B:transformer/*.safetensors,black-forest-labs/FLUX.2-klein-9B:vae/diffusion_pytorch_model.safetensors" \
+#   --tokenizer_path "black-forest-labs/FLUX.2-klein-9B:tokenizer/" \
+#   --learning_rate 1e-5 \
+#   --num_epochs 2 \
+#   --remove_prefix_in_ckpt "pipe.dit." \
+#   --output_path "./models/train/FLUX.2-klein-9B_full" \
+#   --trainable_models "dit" \
+#   --use_gradient_checkpointing

examples/flux2/model_training/full/FLUX.2-klein-base-4B.sh

@@ -11,3 +11,20 @@ accelerate launch examples/flux2/model_training/train.py \
   --output_path "./models/train/FLUX.2-klein-base-4B_full" \
   --trainable_models "dit" \
   --use_gradient_checkpointing
+
+# Edit
+# accelerate launch examples/flux2/model_training/train.py \
+#   --dataset_base_path data/example_image_dataset \
+#   --dataset_metadata_path data/example_image_dataset/metadata_qwen_imgae_edit_multi.json \
+#   --data_file_keys "image,edit_image" \
+#   --extra_inputs "edit_image" \
+#   --max_pixels 1048576 \
+#   --dataset_repeat 50 \
+#   --model_id_with_origin_paths "black-forest-labs/FLUX.2-klein-4B:text_encoder/*.safetensors,black-forest-labs/FLUX.2-klein-base-4B:transformer/*.safetensors,black-forest-labs/FLUX.2-klein-4B:vae/diffusion_pytorch_model.safetensors" \
+#   --tokenizer_path "black-forest-labs/FLUX.2-klein-4B:tokenizer/" \
+#   --learning_rate 1e-5 \
+#   --num_epochs 2 \
+#   --remove_prefix_in_ckpt "pipe.dit." \
+#   --output_path "./models/train/FLUX.2-klein-base-4B_full" \
+#   --trainable_models "dit" \
+#   --use_gradient_checkpointing

examples/flux2/model_training/full/FLUX.2-klein-base-9B.sh

@@ -1,4 +1,5 @@
-accelerate launch examples/flux2/model_training/train.py \
+# This script is tested on 8*A100
+accelerate launch --config_file examples/flux2/model_training/full/accelerate_config.yaml examples/flux2/model_training/train.py \
   --dataset_base_path data/example_image_dataset \
   --dataset_metadata_path data/example_image_dataset/metadata.csv \
   --max_pixels 1048576 \
@@ -11,3 +12,20 @@ accelerate launch examples/flux2/model_training/train.py \
   --output_path "./models/train/FLUX.2-klein-base-9B_full" \
   --trainable_models "dit" \
   --use_gradient_checkpointing
+
+# Edit
+# accelerate launch --config_file examples/flux2/model_training/full/accelerate_config.yaml examples/flux2/model_training/train.py \
+#   --dataset_base_path data/example_image_dataset \
+#   --dataset_metadata_path data/example_image_dataset/metadata_qwen_imgae_edit_multi.json \
+#   --data_file_keys "image,edit_image" \
+#   --extra_inputs "edit_image" \
+#   --max_pixels 1048576 \
+#   --dataset_repeat 50 \
+#   --model_id_with_origin_paths "black-forest-labs/FLUX.2-klein-9B:text_encoder/*.safetensors,black-forest-labs/FLUX.2-klein-base-9B:transformer/*.safetensors,black-forest-labs/FLUX.2-klein-9B:vae/diffusion_pytorch_model.safetensors" \
+#   --tokenizer_path "black-forest-labs/FLUX.2-klein-9B:tokenizer/" \
+#   --learning_rate 1e-5 \
+#   --num_epochs 2 \
+#   --remove_prefix_in_ckpt "pipe.dit." \
+#   --output_path "./models/train/FLUX.2-klein-base-9B_full" \
+#   --trainable_models "dit" \
+#   --use_gradient_checkpointing

examples/flux2/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