DiffSynth-Studio 2.0 major update

2026-03-18 22:08:13 +00:00 · 2025-12-04 16:33:07 +08:00
parent afd101f345
commit 72af7122b3
758 changed files with 26462 additions and 2221398 deletions
--- a/examples/flux/model_training/full/FLEX.2-preview.sh
+++ b/examples/flux/model_training/full/FLEX.2-preview.sh
@@ -3,7 +3,7 @@ accelerate launch --config_file examples/flux/model_training/full/accelerate_con
  --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/,black-forest-labs/FLUX.1-dev:ae.safetensors" \
+  --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." \
--- a/examples/flux/model_training/full/FLUX.1-Kontext-dev.sh
+++ b/examples/flux/model_training/full/FLUX.1-Kontext-dev.sh
@@ -4,7 +4,7 @@ accelerate launch --config_file examples/flux/model_training/full/accelerate_con
  --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/,black-forest-labs/FLUX.1-dev:ae.safetensors" \
+  --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." \
--- a/examples/flux/model_training/full/FLUX.1-Krea-dev.sh
+++ b/examples/flux/model_training/full/FLUX.1-Krea-dev.sh
@@ -3,7 +3,7 @@ accelerate launch --config_file examples/flux/model_training/full/accelerate_con
  --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/,black-forest-labs/FLUX.1-dev:ae.safetensors" \
+  --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." \
--- a/examples/flux/model_training/full/FLUX.1-dev-AttriCtrl.sh
+++ b/examples/flux/model_training/full/FLUX.1-dev-AttriCtrl.sh
@@ -4,7 +4,7 @@ accelerate launch examples/flux/model_training/train.py \
  --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/,black-forest-labs/FLUX.1-dev:ae.safetensors,DiffSynth-Studio/AttriCtrl-FLUX.1-Dev:models/brightness.safetensors" \
+  --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." \
--- a/examples/flux/model_training/full/FLUX.1-dev-Controlnet-Inpainting-Beta.sh
+++ b/examples/flux/model_training/full/FLUX.1-dev-Controlnet-Inpainting-Beta.sh
@@ -4,7 +4,7 @@ accelerate launch --config_file examples/flux/model_training/full/accelerate_con
  --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/,black-forest-labs/FLUX.1-dev:ae.safetensors,alimama-creative/FLUX.1-dev-Controlnet-Inpainting-Beta:diffusion_pytorch_model.safetensors" \
+  --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." \
--- a/examples/flux/model_training/full/FLUX.1-dev-Controlnet-Union-alpha.sh
+++ b/examples/flux/model_training/full/FLUX.1-dev-Controlnet-Union-alpha.sh
@@ -4,7 +4,7 @@ accelerate launch --config_file examples/flux/model_training/full/accelerate_con
  --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/,black-forest-labs/FLUX.1-dev:ae.safetensors,InstantX/FLUX.1-dev-Controlnet-Union-alpha:diffusion_pytorch_model.safetensors" \
+  --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." \
--- a/examples/flux/model_training/full/FLUX.1-dev-Controlnet-Upscaler.sh
+++ b/examples/flux/model_training/full/FLUX.1-dev-Controlnet-Upscaler.sh
@@ -4,7 +4,7 @@ accelerate launch --config_file examples/flux/model_training/full/accelerate_con
  --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/,black-forest-labs/FLUX.1-dev:ae.safetensors,jasperai/Flux.1-dev-Controlnet-Upscaler:diffusion_pytorch_model.safetensors" \
+  --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." \
--- a/examples/flux/model_training/full/FLUX.1-dev-IP-Adapter.sh
+++ b/examples/flux/model_training/full/FLUX.1-dev-IP-Adapter.sh
@@ -4,7 +4,7 @@ accelerate launch examples/flux/model_training/train.py \
  --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/,black-forest-labs/FLUX.1-dev:ae.safetensors,InstantX/FLUX.1-dev-IP-Adapter:ip-adapter.bin,google/siglip-so400m-patch14-384:" \
+  --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:model.safetensors" \
  --learning_rate 1e-5 \
  --num_epochs 1 \
  --remove_prefix_in_ckpt "pipe.ipadapter." \
--- a/examples/flux/model_training/full/FLUX.1-dev-InfiniteYou.sh
+++ b/examples/flux/model_training/full/FLUX.1-dev-InfiniteYou.sh
@@ -4,7 +4,7 @@ accelerate launch --config_file examples/flux/model_training/full/accelerate_con
  --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/,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" \
+  --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." \
--- a/examples/flux/model_training/full/FLUX.1-dev-LoRA-Encoder.sh
+++ b/examples/flux/model_training/full/FLUX.1-dev-LoRA-Encoder.sh
@@ -4,7 +4,7 @@ accelerate launch examples/flux/model_training/train.py \
  --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/,black-forest-labs/FLUX.1-dev:ae.safetensors,DiffSynth-Studio/LoRA-Encoder-FLUX.1-Dev:model.safetensors" \
+  --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." \
--- a/examples/flux/model_training/full/FLUX.1-dev.sh
+++ b/examples/flux/model_training/full/FLUX.1-dev.sh
@@ -3,7 +3,7 @@ accelerate launch --config_file examples/flux/model_training/full/accelerate_con
  --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/,black-forest-labs/FLUX.1-dev:ae.safetensors" \
+  --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." \
--- a/examples/flux/model_training/full/Nexus-Gen.sh
+++ b/examples/flux/model_training/full/Nexus-Gen.sh
@@ -4,7 +4,7 @@ accelerate launch --config_file examples/flux/model_training/full/accelerate_con
  --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/,black-forest-labs/FLUX.1-dev:ae.safetensors" \
+  --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." \
--- a/examples/flux/model_training/full/Step1X-Edit.sh
+++ b/examples/flux/model_training/full/Step1X-Edit.sh
@@ -4,7 +4,7 @@ accelerate launch --config_file examples/flux/model_training/full/accelerate_con
  --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" \
+  --model_id_with_origin_paths "Qwen/Qwen2.5-VL-7B-Instruct:model-*.safetensors,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." \