Merge pull request #807 from modelscope/qwen-image-blockwise-controlnet-train

support qwen-image blockwise controlnet training

README.md

@@ -93,8 +93,8 @@ image.save("image.jpg")
 |[DiffSynth-Studio/Qwen-Image-Distill-Full](https://www.modelscope.cn/models/DiffSynth-Studio/Qwen-Image-Distill-Full)|[code](./examples/qwen_image/model_inference/Qwen-Image-Distill-Full.py)|[code](./examples/qwen_image/model_inference_low_vram/Qwen-Image-Distill-Full.py)|[code](./examples/qwen_image/model_training/full/Qwen-Image-Distill-Full.sh)|[code](./examples/qwen_image/model_training/validate_full/Qwen-Image-Distill-Full.py)|[code](./examples/qwen_image/model_training/lora/Qwen-Image-Distill-Full.sh)|[code](./examples/qwen_image/model_training/validate_lora/Qwen-Image-Distill-Full.py)|
 |[DiffSynth-Studio/Qwen-Image-Distill-LoRA](https://www.modelscope.cn/models/DiffSynth-Studio/Qwen-Image-Distill-LoRA)|[code](./examples/qwen_image/model_inference/Qwen-Image-Distill-LoRA.py)|[code](./examples/qwen_image/model_inference_low_vram/Qwen-Image-Distill-LoRA.py)|-|-|-|-|
 |[DiffSynth-Studio/Qwen-Image-EliGen](https://www.modelscope.cn/models/DiffSynth-Studio/Qwen-Image-EliGen)|[code](./examples/qwen_image/model_inference/Qwen-Image-EliGen.py)|[code](./examples/qwen_image/model_inference_low_vram/Qwen-Image-EliGen.py)|-|-|[code](./examples/qwen_image/model_training/lora/Qwen-Image-EliGen.sh)|[code](./examples/qwen_image/model_training/validate_lora/Qwen-Image-EliGen.py)|
-|[DiffSynth-Studio/Qwen-Image-Blockwise-ControlNet-Canny](https://modelscope.cn/models/DiffSynth-Studio/Qwen-Image-Blockwise-ControlNet-Canny)|[code](./examples/qwen_image/model_inference/Qwen-Image-Blockwise-ControlNet-Canny.py)|[code](./examples/qwen_image/model_inference_low_vram/Qwen-Image-Blockwise-ControlNet-Canny.py)|-|-|-|-|
+|[DiffSynth-Studio/Qwen-Image-Blockwise-ControlNet-Canny](https://modelscope.cn/models/DiffSynth-Studio/Qwen-Image-Blockwise-ControlNet-Canny)|[code](./examples/qwen_image/model_inference/Qwen-Image-Blockwise-ControlNet-Canny.py)|[code](./examples/qwen_image/model_inference_low_vram/Qwen-Image-Blockwise-ControlNet-Canny.py)|[code](./examples/qwen_image/model_training/full/Qwen-Image-Blockwise-ControlNet-Canny.sh)|[code](./examples/qwen_image/model_training/validate_full/Qwen-Image-Blockwise-ControlNet-Canny.py)|[code](./examples/qwen_image/model_training/lora/Qwen-Image-Blockwise-ControlNet-Canny.sh)|[code](./examples/qwen_image/model_training/validate_lora/Qwen-Image-Blockwise-ControlNet-Canny.py)|
-|[DiffSynth-Studio/Qwen-Image-Blockwise-ControlNet-Depth](https://modelscope.cn/models/DiffSynth-Studio/Qwen-Image-Blockwise-ControlNet-Depth)|[code](./examples/qwen_image/model_inference/Qwen-Image-Blockwise-ControlNet-Depth.py)|[code](./examples/qwen_image/model_inference_low_vram/Qwen-Image-Blockwise-ControlNet-Depth.py)|-|-|-|-|
+|[DiffSynth-Studio/Qwen-Image-Blockwise-ControlNet-Depth](https://modelscope.cn/models/DiffSynth-Studio/Qwen-Image-Blockwise-ControlNet-Depth)|[code](./examples/qwen_image/model_inference/Qwen-Image-Blockwise-ControlNet-Depth.py)|[code](./examples/qwen_image/model_inference_low_vram/Qwen-Image-Blockwise-ControlNet-Depth.py)|[code](./examples/qwen_image/model_training/full/Qwen-Image-Blockwise-ControlNet-Depth.sh)|[code](./examples/qwen_image/model_training/validate_full/Qwen-Image-Blockwise-ControlNet-Depth.py)|[code](./examples/qwen_image/model_training/lora/Qwen-Image-Blockwise-ControlNet-Depth.sh)|[code](./examples/qwen_image/model_training/validate_lora/Qwen-Image-Blockwise-ControlNet-Depth.py)|
 
 </details>
 

README_zh.md

@@ -95,8 +95,8 @@ image.save("image.jpg")
 |[DiffSynth-Studio/Qwen-Image-Distill-Full](https://www.modelscope.cn/models/DiffSynth-Studio/Qwen-Image-Distill-Full)|[code](./examples/qwen_image/model_inference/Qwen-Image-Distill-Full.py)|[code](./examples/qwen_image/model_inference_low_vram/Qwen-Image-Distill-Full.py)|[code](./examples/qwen_image/model_training/full/Qwen-Image-Distill-Full.sh)|[code](./examples/qwen_image/model_training/validate_full/Qwen-Image-Distill-Full.py)|[code](./examples/qwen_image/model_training/lora/Qwen-Image-Distill-Full.sh)|[code](./examples/qwen_image/model_training/validate_lora/Qwen-Image-Distill-Full.py)|
 |[DiffSynth-Studio/Qwen-Image-Distill-LoRA](https://www.modelscope.cn/models/DiffSynth-Studio/Qwen-Image-Distill-LoRA)|[code](./examples/qwen_image/model_inference/Qwen-Image-Distill-LoRA.py)|[code](./examples/qwen_image/model_inference_low_vram/Qwen-Image-Distill-LoRA.py)|-|-|-|-|
 |[DiffSynth-Studio/Qwen-Image-EliGen](https://www.modelscope.cn/models/DiffSynth-Studio/Qwen-Image-EliGen)|[code](./examples/qwen_image/model_inference/Qwen-Image-EliGen.py)|[code](./examples/qwen_image/model_inference_low_vram/Qwen-Image-EliGen.py)|-|-|[code](./examples/qwen_image/model_training/lora/Qwen-Image-EliGen.sh)|[code](./examples/qwen_image/model_training/validate_lora/Qwen-Image-EliGen.py)|
-|[DiffSynth-Studio/Qwen-Image-Blockwise-ControlNet-Canny](https://modelscope.cn/models/DiffSynth-Studio/Qwen-Image-Blockwise-ControlNet-Canny)|[code](./examples/qwen_image/model_inference/Qwen-Image-Blockwise-ControlNet-Canny.py)|[code](./examples/qwen_image/model_inference_low_vram/Qwen-Image-Blockwise-ControlNet-Canny.py)|-|-|-|-|
+|[DiffSynth-Studio/Qwen-Image-Blockwise-ControlNet-Canny](https://modelscope.cn/models/DiffSynth-Studio/Qwen-Image-Blockwise-ControlNet-Canny)|[code](./examples/qwen_image/model_inference/Qwen-Image-Blockwise-ControlNet-Canny.py)|[code](./examples/qwen_image/model_inference_low_vram/Qwen-Image-Blockwise-ControlNet-Canny.py)|[code](./examples/qwen_image/model_training/full/Qwen-Image-Blockwise-ControlNet-Canny.sh)|[code](./examples/qwen_image/model_training/validate_full/Qwen-Image-Blockwise-ControlNet-Canny.py)|[code](./examples/qwen_image/model_training/lora/Qwen-Image-Blockwise-ControlNet-Canny.sh)|[code](./examples/qwen_image/model_training/validate_lora/Qwen-Image-Blockwise-ControlNet-Canny.py)|
-|[DiffSynth-Studio/Qwen-Image-Blockwise-ControlNet-Depth](https://modelscope.cn/models/DiffSynth-Studio/Qwen-Image-Blockwise-ControlNet-Depth)|[code](./examples/qwen_image/model_inference/Qwen-Image-Blockwise-ControlNet-Depth.py)|[code](./examples/qwen_image/model_inference_low_vram/Qwen-Image-Blockwise-ControlNet-Depth.py)|-|-|-|-|
+|[DiffSynth-Studio/Qwen-Image-Blockwise-ControlNet-Depth](https://modelscope.cn/models/DiffSynth-Studio/Qwen-Image-Blockwise-ControlNet-Depth)|[code](./examples/qwen_image/model_inference/Qwen-Image-Blockwise-ControlNet-Depth.py)|[code](./examples/qwen_image/model_inference_low_vram/Qwen-Image-Blockwise-ControlNet-Depth.py)|[code](./examples/qwen_image/model_training/full/Qwen-Image-Blockwise-ControlNet-Depth.sh)|[code](./examples/qwen_image/model_training/validate_full/Qwen-Image-Blockwise-ControlNet-Depth.py)|[code](./examples/qwen_image/model_training/lora/Qwen-Image-Blockwise-ControlNet-Depth.sh)|[code](./examples/qwen_image/model_training/validate_lora/Qwen-Image-Blockwise-ControlNet-Depth.py)|
 
 </details>
 

examples/qwen_image/README.md

@@ -46,8 +46,8 @@ image.save("image.jpg")
 |[DiffSynth-Studio/Qwen-Image-Distill-Full](https://www.modelscope.cn/models/DiffSynth-Studio/Qwen-Image-Distill-Full)|[code](./model_inference/Qwen-Image-Distill-Full.py)|[code](./model_inference_low_vram/Qwen-Image-Distill-Full.py)|[code](./model_training/full/Qwen-Image-Distill-Full.sh)|[code](./model_training/validate_full/Qwen-Image-Distill-Full.py)|[code](./model_training/lora/Qwen-Image-Distill-Full.sh)|[code](./model_training/validate_lora/Qwen-Image-Distill-Full.py)|
 |[DiffSynth-Studio/Qwen-Image-Distill-LoRA](https://www.modelscope.cn/models/DiffSynth-Studio/Qwen-Image-Distill-LoRA)|[code](./model_inference/Qwen-Image-Distill-LoRA.py)|[code](./model_inference_low_vram/Qwen-Image-Distill-LoRA.py)|-|-|-|-|
 |[DiffSynth-Studio/Qwen-Image-EliGen](https://www.modelscope.cn/models/DiffSynth-Studio/Qwen-Image-EliGen)|[code](./model_inference/Qwen-Image-EliGen.py)|[code](./model_inference_low_vram/Qwen-Image-EliGen.py)|-|-|[code](./model_training/lora/Qwen-Image-EliGen.sh)|[code](./model_training/validate_lora/Qwen-Image-EliGen.py)|
-|[DiffSynth-Studio/Qwen-Image-Blockwise-ControlNet-Canny](https://modelscope.cn/models/DiffSynth-Studio/Qwen-Image-Blockwise-ControlNet-Canny)|[code](./model_inference/Qwen-Image-Blockwise-ControlNet-Canny.py)|[code](./model_inference_low_vram/Qwen-Image-Blockwise-ControlNet-Canny.py)|-|-|-|-|
+|[DiffSynth-Studio/Qwen-Image-Blockwise-ControlNet-Canny](https://modelscope.cn/models/DiffSynth-Studio/Qwen-Image-Blockwise-ControlNet-Canny)|[code](./model_inference/Qwen-Image-Blockwise-ControlNet-Canny.py)|[code](./model_inference_low_vram/Qwen-Image-Blockwise-ControlNet-Canny.py)|[code](./model_training/full/Qwen-Image-Blockwise-ControlNet-Canny.sh)|[code](./model_training/validate_full/Qwen-Image-Blockwise-ControlNet-Canny.py)|[code](./model_training/lora/Qwen-Image-Blockwise-ControlNet-Canny.sh)|[code](./model_training/validate_lora/Qwen-Image-Blockwise-ControlNet-Canny.py)|
-|[DiffSynth-Studio/Qwen-Image-Blockwise-ControlNet-Depth](https://modelscope.cn/models/DiffSynth-Studio/Qwen-Image-Blockwise-ControlNet-Depth)|[code](./model_inference/Qwen-Image-Blockwise-ControlNet-Depth.py)|[code](./model_inference_low_vram/Qwen-Image-Blockwise-ControlNet-Depth.py)|-|-|-|-|
+|[DiffSynth-Studio/Qwen-Image-Blockwise-ControlNet-Depth](https://modelscope.cn/models/DiffSynth-Studio/Qwen-Image-Blockwise-ControlNet-Depth)|[code](./model_inference/Qwen-Image-Blockwise-ControlNet-Depth.py)|[code](./model_inference_low_vram/Qwen-Image-Blockwise-ControlNet-Depth.py)|[code](./model_training/full/Qwen-Image-Blockwise-ControlNet-Depth.sh)|[code](./model_training/validate_full/Qwen-Image-Blockwise-ControlNet-Depth.py)|[code](./model_training/lora/Qwen-Image-Blockwise-ControlNet-Depth.sh)|[code](./model_training/validate_lora/Qwen-Image-Blockwise-ControlNet-Depth.py)|
 
 ## Model Inference
 

examples/qwen_image/README_zh.md

@@ -46,8 +46,8 @@ image.save("image.jpg")
 |[DiffSynth-Studio/Qwen-Image-Distill-Full](https://www.modelscope.cn/models/DiffSynth-Studio/Qwen-Image-Distill-Full)|[code](./model_inference/Qwen-Image-Distill-Full.py)|[code](./model_inference_low_vram/Qwen-Image-Distill-Full.py)|[code](./model_training/full/Qwen-Image-Distill-Full.sh)|[code](./model_training/validate_full/Qwen-Image-Distill-Full.py)|[code](./model_training/lora/Qwen-Image-Distill-Full.sh)|[code](./model_training/validate_lora/Qwen-Image-Distill-Full.py)|
 |[DiffSynth-Studio/Qwen-Image-Distill-LoRA](https://www.modelscope.cn/models/DiffSynth-Studio/Qwen-Image-Distill-LoRA)|[code](./model_inference/Qwen-Image-Distill-LoRA.py)|[code](./model_inference_low_vram/Qwen-Image-Distill-LoRA.py)|-|-|-|-|
 |[DiffSynth-Studio/Qwen-Image-EliGen](https://www.modelscope.cn/models/DiffSynth-Studio/Qwen-Image-EliGen)|[code](./model_inference/Qwen-Image-EliGen.py)|[code](./model_inference_low_vram/Qwen-Image-EliGen.py)|-|-|[code](./model_training/lora/Qwen-Image-EliGen.sh)|[code](./model_training/validate_lora/Qwen-Image-EliGen.py)|
-|[DiffSynth-Studio/Qwen-Image-Blockwise-ControlNet-Canny](https://modelscope.cn/models/DiffSynth-Studio/Qwen-Image-Blockwise-ControlNet-Canny)|[code](./model_inference/Qwen-Image-Blockwise-ControlNet-Canny.py)|[code](./model_inference_low_vram/Qwen-Image-Blockwise-ControlNet-Canny.py)|-|-|-|-|
+|[DiffSynth-Studio/Qwen-Image-Blockwise-ControlNet-Canny](https://modelscope.cn/models/DiffSynth-Studio/Qwen-Image-Blockwise-ControlNet-Canny)|[code](./model_inference/Qwen-Image-Blockwise-ControlNet-Canny.py)|[code](./model_inference_low_vram/Qwen-Image-Blockwise-ControlNet-Canny.py)|[code](./model_training/full/Qwen-Image-Blockwise-ControlNet-Canny.sh)|[code](./model_training/validate_full/Qwen-Image-Blockwise-ControlNet-Canny.py)|[code](./model_training/lora/Qwen-Image-Blockwise-ControlNet-Canny.sh)|[code](./model_training/validate_lora/Qwen-Image-Blockwise-ControlNet-Canny.py)|
-|[DiffSynth-Studio/Qwen-Image-Blockwise-ControlNet-Depth](https://modelscope.cn/models/DiffSynth-Studio/Qwen-Image-Blockwise-ControlNet-Depth)|[code](./model_inference/Qwen-Image-Blockwise-ControlNet-Depth.py)|[code](./model_inference_low_vram/Qwen-Image-Blockwise-ControlNet-Depth.py)|-|-|-|-|
+|[DiffSynth-Studio/Qwen-Image-Blockwise-ControlNet-Depth](https://modelscope.cn/models/DiffSynth-Studio/Qwen-Image-Blockwise-ControlNet-Depth)|[code](./model_inference/Qwen-Image-Blockwise-ControlNet-Depth.py)|[code](./model_inference_low_vram/Qwen-Image-Blockwise-ControlNet-Depth.py)|[code](./model_training/full/Qwen-Image-Blockwise-ControlNet-Depth.sh)|[code](./model_training/validate_full/Qwen-Image-Blockwise-ControlNet-Depth.py)|[code](./model_training/lora/Qwen-Image-Blockwise-ControlNet-Depth.sh)|[code](./model_training/validate_lora/Qwen-Image-Blockwise-ControlNet-Depth.py)|
 
 ## 模型推理
 

examples/qwen_image/model_training/full/Qwen-Image-Blockwise-ControlNet-Canny.sh

@@ -0,0 +1,38 @@
+accelerate launch examples/qwen_image/model_training/train.py \
+  --dataset_base_path data/example_image_dataset \
+  --dataset_metadata_path data/example_image_dataset/metadata_blockwise_controlnet_canny.csv \
+  --data_file_keys "image,blockwise_controlnet_image" \
+  --max_pixels 1048576 \
+  --dataset_repeat 50 \
+  --model_id_with_origin_paths "Qwen/Qwen-Image:transformer/diffusion_pytorch_model*.safetensors,Qwen/Qwen-Image:text_encoder/model*.safetensors,Qwen/Qwen-Image:vae/diffusion_pytorch_model.safetensors,DiffSynth-Studio/Qwen-Image-Blockwise-ControlNet-Canny:model.safetensors" \
+  --learning_rate 1e-4 \
+  --num_epochs 2 \
+  --remove_prefix_in_ckpt "pipe.blockwise_controlnet.models.0." \
+  --output_path "./models/train/Qwen-Image-Blockwise-ControlNet-Canny_full" \
+  --trainable_models "blockwise_controlnet" \
+  --extra_inputs "blockwise_controlnet_image" \
+  --use_gradient_checkpointing \
+  --find_unused_parameters
+
+# If you want to pre-train a Blockwise ControlNet from scratch,
+# please run the following script to first generate the initialized model weights file,
+# and then start training with a high learning rate (1e-3).
+
+# python examples/qwen_image/model_training/scripts/Qwen-Image-Blockwise-ControlNet-Initialize.py
+
+# accelerate launch examples/qwen_image/model_training/train.py \
+#   --dataset_base_path data/example_image_dataset \
+#   --dataset_metadata_path data/example_image_dataset/metadata_blockwise_controlnet_canny.csv \
+#   --data_file_keys "image,blockwise_controlnet_image" \
+#   --max_pixels 1048576 \
+#   --dataset_repeat 50 \
+#   --model_id_with_origin_paths "Qwen/Qwen-Image:transformer/diffusion_pytorch_model*.safetensors,Qwen/Qwen-Image:text_encoder/model*.safetensors,Qwen/Qwen-Image:vae/diffusion_pytorch_model.safetensors" \
+#   --model_paths '["models/blockwise_controlnet.safetensors"]' \
+#   --learning_rate 1e-3 \
+#   --num_epochs 2 \
+#   --remove_prefix_in_ckpt "pipe.blockwise_controlnet.models.0." \
+#   --output_path "./models/train/Qwen-Image-Blockwise-ControlNet-Canny_full" \
+#   --trainable_models "blockwise_controlnet" \
+#   --extra_inputs "blockwise_controlnet_image" \
+#   --use_gradient_checkpointing \
+#   --find_unused_parameters

examples/qwen_image/model_training/full/Qwen-Image-Blockwise-ControlNet-Depth.sh

@@ -0,0 +1,38 @@
+accelerate launch examples/qwen_image/model_training/train.py \
+  --dataset_base_path data/example_image_dataset \
+  --dataset_metadata_path data/example_image_dataset/metadata_blockwise_controlnet_depth.csv \
+  --data_file_keys "image,blockwise_controlnet_image" \
+  --max_pixels 1048576 \
+  --dataset_repeat 50 \
+  --model_id_with_origin_paths "Qwen/Qwen-Image:transformer/diffusion_pytorch_model*.safetensors,Qwen/Qwen-Image:text_encoder/model*.safetensors,Qwen/Qwen-Image:vae/diffusion_pytorch_model.safetensors,DiffSynth-Studio/Qwen-Image-Blockwise-ControlNet-Depth:model.safetensors" \
+  --learning_rate 1e-4 \
+  --num_epochs 2 \
+  --remove_prefix_in_ckpt "pipe.blockwise_controlnet.models.0." \
+  --output_path "./models/train/Qwen-Image-Blockwise-ControlNet-Depth_full" \
+  --trainable_models "blockwise_controlnet" \
+  --extra_inputs "blockwise_controlnet_image" \
+  --use_gradient_checkpointing \
+  --find_unused_parameters
+
+# If you want to pre-train a Blockwise ControlNet from scratch,
+# please run the following script to first generate the initialized model weights file,
+# and then start training with a high learning rate (1e-3).
+
+# python examples/qwen_image/model_training/scripts/Qwen-Image-Blockwise-ControlNet-Initialize.py
+
+# accelerate launch examples/qwen_image/model_training/train.py \
+#   --dataset_base_path data/example_image_dataset \
+#   --dataset_metadata_path data/example_image_dataset/metadata_blockwise_controlnet_depth.csv \
+#   --data_file_keys "image,blockwise_controlnet_image" \
+#   --max_pixels 1048576 \
+#   --dataset_repeat 50 \
+#   --model_id_with_origin_paths "Qwen/Qwen-Image:transformer/diffusion_pytorch_model*.safetensors,Qwen/Qwen-Image:text_encoder/model*.safetensors,Qwen/Qwen-Image:vae/diffusion_pytorch_model.safetensors" \
+#   --model_paths '["models/blockwise_controlnet.safetensors"]' \
+#   --learning_rate 1e-3 \
+#   --num_epochs 2 \
+#   --remove_prefix_in_ckpt "pipe.blockwise_controlnet.models.0." \
+#   --output_path "./models/train/Qwen-Image-Blockwise-ControlNet-Depth_full" \
+#   --trainable_models "blockwise_controlnet" \
+#   --extra_inputs "blockwise_controlnet_image" \
+#   --use_gradient_checkpointing \
+#   --find_unused_parameters

examples/qwen_image/model_training/full/Qwen-Image-Distill-Full.sh

@@ -9,4 +9,5 @@ accelerate launch --config_file examples/qwen_image/model_training/full/accelera
   --remove_prefix_in_ckpt "pipe.dit." \
   --output_path "./models/train/Qwen-Image-Distill-Full_full" \
   --trainable_models "dit" \
-  --use_gradient_checkpointing
+  --use_gradient_checkpointing \
+  --find_unused_parameters

examples/qwen_image/model_training/full/Qwen-Image.sh

@@ -9,4 +9,5 @@ accelerate launch --config_file examples/qwen_image/model_training/full/accelera
   --remove_prefix_in_ckpt "pipe.dit." \
   --output_path "./models/train/Qwen-Image_full" \
   --trainable_models "dit" \
-  --use_gradient_checkpointing
+  --use_gradient_checkpointing \
+  --find_unused_parameters

examples/qwen_image/model_training/lora/Qwen-Image-Blockwise-ControlNet-Canny.sh

@@ -0,0 +1,17 @@
+accelerate launch examples/qwen_image/model_training/train.py \
+  --dataset_base_path data/example_image_dataset \
+  --dataset_metadata_path data/example_image_dataset/metadata_blockwise_controlnet_canny.csv \
+  --data_file_keys "image,blockwise_controlnet_image" \
+  --max_pixels 1048576 \
+  --dataset_repeat 50 \
+  --model_id_with_origin_paths "Qwen/Qwen-Image:transformer/diffusion_pytorch_model*.safetensors,Qwen/Qwen-Image:text_encoder/model*.safetensors,Qwen/Qwen-Image:vae/diffusion_pytorch_model.safetensors,DiffSynth-Studio/Qwen-Image-Blockwise-ControlNet-Canny:model.safetensors" \
+  --learning_rate 1e-4 \
+  --num_epochs 5 \
+  --remove_prefix_in_ckpt "pipe.dit." \
+  --output_path "./models/train/Qwen-Image-Blockwise-ControlNet-Canny_lora" \
+  --lora_base_model "dit" \
+  --lora_target_modules "to_q,to_k,to_v,add_q_proj,add_k_proj,add_v_proj,to_out.0,to_add_out,img_mlp.net.2,img_mod.1,txt_mlp.net.2,txt_mod.1" \
+  --lora_rank 32 \
+  --extra_inputs "blockwise_controlnet_image" \
+  --use_gradient_checkpointing \
+  --find_unused_parameters

examples/qwen_image/model_training/lora/Qwen-Image-Blockwise-ControlNet-Depth.sh

@@ -0,0 +1,17 @@
+accelerate launch examples/qwen_image/model_training/train.py \
+  --dataset_base_path data/example_image_dataset \
+  --dataset_metadata_path data/example_image_dataset/metadata_blockwise_controlnet_depth.csv \
+  --data_file_keys "image,blockwise_controlnet_image" \
+  --max_pixels 1048576 \
+  --dataset_repeat 50 \
+  --model_id_with_origin_paths "Qwen/Qwen-Image:transformer/diffusion_pytorch_model*.safetensors,Qwen/Qwen-Image:text_encoder/model*.safetensors,Qwen/Qwen-Image:vae/diffusion_pytorch_model.safetensors,DiffSynth-Studio/Qwen-Image-Blockwise-ControlNet-Depth:model.safetensors" \
+  --learning_rate 1e-4 \
+  --num_epochs 5 \
+  --remove_prefix_in_ckpt "pipe.dit." \
+  --output_path "./models/train/Qwen-Image-Blockwise-ControlNet-Depth_lora" \
+  --lora_base_model "dit" \
+  --lora_target_modules "to_q,to_k,to_v,add_q_proj,add_k_proj,add_v_proj,to_out.0,to_add_out,img_mlp.net.2,img_mod.1,txt_mlp.net.2,txt_mod.1" \
+  --lora_rank 32 \
+  --extra_inputs "blockwise_controlnet_image" \
+  --use_gradient_checkpointing \
+  --find_unused_parameters

examples/qwen_image/model_training/lora/Qwen-Image-Distill-Full.sh

@@ -11,4 +11,5 @@ accelerate launch examples/qwen_image/model_training/train.py \
   --lora_base_model "dit" \
   --lora_target_modules "to_q,to_k,to_v,add_q_proj,add_k_proj,add_v_proj,to_out.0,to_add_out,img_mlp.net.2,img_mod.1,txt_mlp.net.2,txt_mod.1" \
   --lora_rank 32 \
-  --use_gradient_checkpointing
+  --use_gradient_checkpointing \
+  --find_unused_parameters

examples/qwen_image/model_training/scripts/Qwen-Image-Blockwise-ControlNet-Initialize.py

@@ -0,0 +1,13 @@
+# This script is for initializing a Qwen-Image-Blockwise-ControlNet
+from diffsynth import hash_state_dict_keys
+from diffsynth.models.qwen_image_controlnet import QwenImageBlockWiseControlNet
+import torch
+from safetensors.torch import save_file
+
+
+controlnet = QwenImageBlockWiseControlNet().to(dtype=torch.bfloat16, device="cuda")
+controlnet.init_weight()
+state_dict_controlnet = controlnet.state_dict()
+
+print(hash_state_dict_keys(state_dict_controlnet))
+save_file(state_dict_controlnet, "models/blockwise_controlnet.safetensors")

examples/qwen_image/model_training/train.py

@@ -80,17 +80,18 @@ class QwenImageTrainingModule(DiffusionTrainingModule):
         }
         
         # Extra inputs
-        controlnet_input = {}
+        controlnet_input, blockwise_controlnet_input = {}, {}
         for extra_input in self.extra_inputs:
             if extra_input.startswith("blockwise_controlnet_"):
-                controlnet_input[extra_input.replace("blockwise_controlnet_", "")] = data[extra_input]
+                blockwise_controlnet_input[extra_input.replace("blockwise_controlnet_", "")] = data[extra_input]
             elif extra_input.startswith("controlnet_"):
                 controlnet_input[extra_input.replace("controlnet_", "")] = data[extra_input]
             else:
                 inputs_shared[extra_input] = data[extra_input]
         if len(controlnet_input) > 0:
-            controlnet_key = "blockwise_controlnet_inputs" if "blockwise_controlnet_image" in self.extra_inputs else "controlnet_inputs"
+            inputs_shared["controlnet_inputs"] = [ControlNetInput(**controlnet_input)]
-            inputs_shared[controlnet_key] = [ControlNetInput(**controlnet_input)]
+        if len(blockwise_controlnet_input) > 0:
+            inputs_shared["blockwise_controlnet_inputs"] = [ControlNetInput(**blockwise_controlnet_input)]
         
         # Pipeline units will automatically process the input parameters.
         for unit in self.pipe.units:

examples/qwen_image/model_training/validate_full/Qwen-Image-Blockwise-ControlNet-Canny.py

@@ -0,0 +1,31 @@
+from diffsynth.pipelines.qwen_image import QwenImagePipeline, ModelConfig, ControlNetInput
+from PIL import Image
+import torch
+from modelscope import dataset_snapshot_download
+
+
+pipe = QwenImagePipeline.from_pretrained(
+    torch_dtype=torch.bfloat16,
+    device="cuda",
+    model_configs=[
+        ModelConfig(model_id="Qwen/Qwen-Image", origin_file_pattern="transformer/diffusion_pytorch_model*.safetensors"),
+        ModelConfig(model_id="Qwen/Qwen-Image", origin_file_pattern="text_encoder/model*.safetensors"),
+        ModelConfig(model_id="Qwen/Qwen-Image", origin_file_pattern="vae/diffusion_pytorch_model.safetensors"),
+        ModelConfig(path="models/train/Qwen-Image-Blockwise-ControlNet-Canny_full/epoch-1.safetensors"),
+    ],
+    tokenizer_config=ModelConfig(model_id="Qwen/Qwen-Image", origin_file_pattern="tokenizer/"),
+)
+
+dataset_snapshot_download(
+    dataset_id="DiffSynth-Studio/example_image_dataset",
+    local_dir="./data/example_image_dataset",
+    allow_file_pattern="canny/image_1.jpg"
+)
+controlnet_image = Image.open("data/example_image_dataset/canny/image_1.jpg").resize((1328, 1328))
+
+prompt = "一只小狗，毛发光洁柔顺，眼神灵动，背景是樱花纷飞的春日庭院，唯美温馨。"
+image = pipe(
+    prompt, seed=0,
+    blockwise_controlnet_inputs=[ControlNetInput(image=controlnet_image)]
+)
+image.save("image.jpg")

examples/qwen_image/model_training/validate_full/Qwen-Image-Blockwise-ControlNet-Depth.py

@@ -0,0 +1,31 @@
+from diffsynth.pipelines.qwen_image import QwenImagePipeline, ModelConfig, ControlNetInput
+from PIL import Image
+import torch
+from modelscope import dataset_snapshot_download
+
+
+pipe = QwenImagePipeline.from_pretrained(
+    torch_dtype=torch.bfloat16,
+    device="cuda",
+    model_configs=[
+        ModelConfig(model_id="Qwen/Qwen-Image", origin_file_pattern="transformer/diffusion_pytorch_model*.safetensors"),
+        ModelConfig(model_id="Qwen/Qwen-Image", origin_file_pattern="text_encoder/model*.safetensors"),
+        ModelConfig(model_id="Qwen/Qwen-Image", origin_file_pattern="vae/diffusion_pytorch_model.safetensors"),
+        ModelConfig(path="models/train/Qwen-Image-Blockwise-ControlNet-Depth_full/epoch-1.safetensors"),
+    ],
+    tokenizer_config=ModelConfig(model_id="Qwen/Qwen-Image", origin_file_pattern="tokenizer/"),
+)
+
+dataset_snapshot_download(
+    dataset_id="DiffSynth-Studio/example_image_dataset",
+    local_dir="./data/example_image_dataset",
+    allow_file_pattern="depth/image_1.jpg"
+)
+controlnet_image = Image.open("data/example_image_dataset/depth/image_1.jpg").resize((1328, 1328))
+
+prompt = "精致肖像，水下少女，蓝裙飘逸，发丝轻扬，光影透澈，气泡环绕，面容恬静，细节精致，梦幻唯美。"
+image = pipe(
+    prompt, seed=0,
+    blockwise_controlnet_inputs=[ControlNetInput(image=controlnet_image)]
+)
+image.save("image.jpg")

examples/qwen_image/model_training/validate_lora/Qwen-Image-Blockwise-ControlNet-Canny.py

@@ -0,0 +1,32 @@
+from diffsynth.pipelines.qwen_image import QwenImagePipeline, ModelConfig, ControlNetInput
+from PIL import Image
+import torch
+from modelscope import dataset_snapshot_download
+
+
+pipe = QwenImagePipeline.from_pretrained(
+    torch_dtype=torch.bfloat16,
+    device="cuda",
+    model_configs=[
+        ModelConfig(model_id="Qwen/Qwen-Image", origin_file_pattern="transformer/diffusion_pytorch_model*.safetensors"),
+        ModelConfig(model_id="Qwen/Qwen-Image", origin_file_pattern="text_encoder/model*.safetensors"),
+        ModelConfig(model_id="Qwen/Qwen-Image", origin_file_pattern="vae/diffusion_pytorch_model.safetensors"),
+        ModelConfig(model_id="DiffSynth-Studio/Qwen-Image-Blockwise-ControlNet-Canny", origin_file_pattern="model.safetensors"),
+    ],
+    tokenizer_config=ModelConfig(model_id="Qwen/Qwen-Image", origin_file_pattern="tokenizer/"),
+)
+pipe.load_lora(pipe.dit, "models/train/Qwen-Image-Blockwise-ControlNet-Canny_lora/epoch-4.safetensors")
+
+dataset_snapshot_download(
+    dataset_id="DiffSynth-Studio/example_image_dataset",
+    local_dir="./data/example_image_dataset",
+    allow_file_pattern="canny/image_1.jpg"
+)
+controlnet_image = Image.open("data/example_image_dataset/canny/image_1.jpg").resize((1328, 1328))
+
+prompt = "一只小狗，毛发光洁柔顺，眼神灵动，背景是樱花纷飞的春日庭院，唯美温馨。"
+image = pipe(
+    prompt, seed=0,
+    blockwise_controlnet_inputs=[ControlNetInput(image=controlnet_image)]
+)
+image.save("image.jpg")

examples/qwen_image/model_training/validate_lora/Qwen-Image-Blockwise-ControlNet-Depth.py

@@ -0,0 +1,33 @@
+from diffsynth.pipelines.qwen_image import QwenImagePipeline, ModelConfig, ControlNetInput
+from PIL import Image
+import torch
+from modelscope import dataset_snapshot_download
+
+
+pipe = QwenImagePipeline.from_pretrained(
+    torch_dtype=torch.bfloat16,
+    device="cuda",
+    model_configs=[
+        ModelConfig(model_id="Qwen/Qwen-Image", origin_file_pattern="transformer/diffusion_pytorch_model*.safetensors"),
+        ModelConfig(model_id="Qwen/Qwen-Image", origin_file_pattern="text_encoder/model*.safetensors"),
+        ModelConfig(model_id="Qwen/Qwen-Image", origin_file_pattern="vae/diffusion_pytorch_model.safetensors"),
+        ModelConfig(model_id="DiffSynth-Studio/Qwen-Image-Blockwise-ControlNet-Depth", origin_file_pattern="model.safetensors"),
+    ],
+    tokenizer_config=ModelConfig(model_id="Qwen/Qwen-Image", origin_file_pattern="tokenizer/"),
+)
+pipe.load_lora(pipe.dit, "models/train/Qwen-Image-Blockwise-ControlNet-Depth_lora/epoch-4.safetensors")
+
+dataset_snapshot_download(
+    dataset_id="DiffSynth-Studio/example_image_dataset",
+    local_dir="./data/example_image_dataset",
+    allow_file_pattern="depth/image_1.jpg"
+)
+
+controlnet_image = Image.open("data/example_image_dataset/depth/image_1.jpg").resize((1328, 1328))
+
+prompt = "精致肖像，水下少女，蓝裙飘逸，发丝轻扬，光影透澈，气泡环绕，面容恬静，细节精致，梦幻唯美。"
+image = pipe(
+    prompt, seed=0,
+    blockwise_controlnet_inputs=[ControlNetInput(image=controlnet_image)]
+)
+image.save("image.jpg")