theluyuan/DiffSynth-Studio
1
0
Fork 0
mirror of https://github.com/modelscope/DiffSynth-Studio.git synced 2026-03-18 22:08:13 +00:00
Code Issues Packages Projects Releases Wiki Activity

rename model

Browse Source
This commit is contained in:
Artiprocher
2025-08-21 13:35:47 +08:00
parent d0467a7e8d
commit 613dafbd09
9 changed files with 14 additions and 15 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
examples/qwen_image/README.md
View File

@@ -51,7 +51,7 @@ image.save("image.jpg")
|[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)|[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)|
|[DiffSynth-Studio/Qwen-Image-Blockwise-ControlNet-Inpaint](https://modelscope.cn/models/DiffSynth-Studio/Qwen-Image-Blockwise-ControlNet-Inpaint)|[code](./model_inference/Qwen-Image-Blockwise-ControlNet-Inpaint.py)|[code](./model_inference_low_vram/Qwen-Image-Blockwise-ControlNet-Inpaint.py)|[code](./model_training/full/Qwen-Image-Blockwise-ControlNet-Inpaint.sh)|[code](./model_training/validate_full/Qwen-Image-Blockwise-ControlNet-Inpaint.py)|[code](./model_training/lora/Qwen-Image-Blockwise-ControlNet-Inpaint.sh)|[code](./model_training/validate_lora/Qwen-Image-Blockwise-ControlNet-Inpaint.py)|
|[DiffSynth-Studio/Qwen-Image-Context-Control](https://www.modelscope.cn/models/DiffSynth-Studio/Qwen-Image-Context-Control)|[code](./model_inference/Qwen-Image-Context-Control.py)|[code](./model_inference_low_vram/Qwen-Image-Context-Control.py)|-|-|[code](./model_training/lora/Qwen-Image-Context-Control.sh)|[code](./model_training/validate_lora/Qwen-Image-Context-Control.py)|
|[DiffSynth-Studio/Qwen-Image-In-Context-Control-Union](https://www.modelscope.cn/models/DiffSynth-Studio/Qwen-Image-In-Context-Control-Union)|[code](./model_inference/Qwen-Image-In-Context-Control-Union.py)|[code](./model_inference_low_vram/Qwen-Image-In-Context-Control-Union.py)|-|-|[code](./model_training/lora/Qwen-Image-In-Context-Control-Union.sh)|[code](./model_training/validate_lora/Qwen-Image-In-Context-Control-Union.py)|
|[DiffSynth-Studio/Qwen-Image-Edit-Lowres-Fix](https://www.modelscope.cn/models/DiffSynth-Studio/Qwen-Image-Edit-Lowres-Fix)|[code](./model_inference/Qwen-Image-Edit-Lowres-Fix.py)|[code](./model_inference_low_vram/Qwen-Image-Edit-Lowres-Fix.py)|-|-|-|-|
## Model Inference

2
examples/qwen_image/README_zh.md
View File

@@ -51,7 +51,7 @@ image.save("image.jpg")
|[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)|[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)|
|[DiffSynth-Studio/Qwen-Image-Blockwise-ControlNet-Inpaint](https://modelscope.cn/models/DiffSynth-Studio/Qwen-Image-Blockwise-ControlNet-Inpaint)|[code](./model_inference/Qwen-Image-Blockwise-ControlNet-Inpaint.py)|[code](./model_inference_low_vram/Qwen-Image-Blockwise-ControlNet-Inpaint.py)|[code](./model_training/full/Qwen-Image-Blockwise-ControlNet-Inpaint.sh)|[code](./model_training/validate_full/Qwen-Image-Blockwise-ControlNet-Inpaint.py)|[code](./model_training/lora/Qwen-Image-Blockwise-ControlNet-Inpaint.sh)|[code](./model_training/validate_lora/Qwen-Image-Blockwise-ControlNet-Inpaint.py)|
|[DiffSynth-Studio/Qwen-Image-Context-Control](https://www.modelscope.cn/models/DiffSynth-Studio/Qwen-Image-Context-Control)|[code](./model_inference/Qwen-Image-Context-Control.py)|[code](./model_inference_low_vram/Qwen-Image-Context-Control.py)|-|-|[code](./model_training/lora/Qwen-Image-Context-Control.sh)|[code](./model_training/validate_lora/Qwen-Image-Context-Control.py)|
|[DiffSynth-Studio/Qwen-Image-In-Context-Control-Union](https://www.modelscope.cn/models/DiffSynth-Studio/Qwen-Image-In-Context-Control-Union)|[code](./model_inference/Qwen-Image-In-Context-Control-Union.py)|[code](./model_inference_low_vram/Qwen-Image-In-Context-Control-Union.py)|-|-|[code](./model_training/lora/Qwen-Image-In-Context-Control-Union.sh)|[code](./model_training/validate_lora/Qwen-Image-In-Context-Control-Union.py)|
|[DiffSynth-Studio/Qwen-Image-Edit-Lowres-Fix](https://www.modelscope.cn/models/DiffSynth-Studio/Qwen-Image-Edit-Lowres-Fix)|[code](./model_inference/Qwen-Image-Edit-Lowres-Fix.py)|[code](./model_inference_low_vram/Qwen-Image-Edit-Lowres-Fix.py)|-|-|-|-|
## 模型推理

4
examples/qwen_image/model_inference/Qwen-Image-Context-Control.py → examples/qwen_image/model_inference/Qwen-Image-In-Context-Control-Union.py
View File

@@ -17,8 +17,8 @@ pipe = QwenImagePipeline.from_pretrained(
],
tokenizer_config=ModelConfig(model_id="Qwen/Qwen-Image", origin_file_pattern="tokenizer/"),
)
snapshot_download("DiffSynth-Studio/Qwen-Image-Context-Control", local_dir="models/DiffSynth-Studio/Qwen-Image-Context-Control", allow_file_pattern="model.safetensors")
pipe.load_lora(pipe.dit, "models/DiffSynth-Studio/Qwen-Image-Context-Control/model.safetensors")
snapshot_download("DiffSynth-Studio/Qwen-Image-In-Context-Control-Union", local_dir="models/DiffSynth-Studio/Qwen-Image-In-Context-Control-Union", allow_file_pattern="model.safetensors")
pipe.load_lora(pipe.dit, "models/DiffSynth-Studio/Qwen-Image-In-Context-Control-Union/model.safetensors")
dataset_snapshot_download(dataset_id="DiffSynth-Studio/examples_in_diffsynth", local_dir="./", allow_file_pattern=f"data/examples/qwen-image-context-control/image.jpg")
origin_image = Image.open("data/examples/qwen-image-context-control/image.jpg").resize((1024, 1024))

4
examples/qwen_image/model_inference_low_vram/Qwen-Image-Context-Control.py → examples/qwen_image/model_inference_low_vram/Qwen-Image-In-Context-Control-Union.py
View File

@@ -18,8 +18,8 @@ pipe = QwenImagePipeline.from_pretrained(
tokenizer_config=ModelConfig(model_id="Qwen/Qwen-Image", origin_file_pattern="tokenizer/"),
)
pipe.enable_vram_management()
snapshot_download("DiffSynth-Studio/Qwen-Image-Context-Control", local_dir="models/DiffSynth-Studio/Qwen-Image-Context-Control", allow_file_pattern="model.safetensors")
pipe.load_lora(pipe.dit, "models/DiffSynth-Studio/Qwen-Image-Context-Control/model.safetensors")
snapshot_download("DiffSynth-Studio/Qwen-Image-In-Context-Control-Union", local_dir="models/DiffSynth-Studio/Qwen-Image-In-Context-Control-Union", allow_file_pattern="model.safetensors")
pipe.load_lora(pipe.dit, "models/DiffSynth-Studio/Qwen-Image-In-Context-Control-Union/model.safetensors")
dataset_snapshot_download(dataset_id="DiffSynth-Studio/examples_in_diffsynth", local_dir="./", allow_file_pattern=f"data/examples/qwen-image-context-control/image.jpg")
origin_image = Image.open("data/examples/qwen-image-context-control/image.jpg").resize((1024, 1024))

4
examples/qwen_image/model_training/lora/Qwen-Image-Context-Control.sh → examples/qwen_image/model_training/lora/Qwen-Image-In-Context-Control-Union.sh
View File

@@ -8,11 +8,11 @@ accelerate launch examples/qwen_image/model_training/train.py \
--learning_rate 1e-4 \
--num_epochs 5 \
--remove_prefix_in_ckpt "pipe.dit." \
--output_path "./models/train/Qwen-Image-Context-Control_lora" \
--output_path "./models/train/Qwen-Image-In-Context-Control-Union_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 64 \
--lora_checkpoint "models/DiffSynth-Studio/Qwen-Image-Context-Control/model.safetensors" \
--lora_checkpoint "models/DiffSynth-Studio/Qwen-Image-In-Context-Control-Union/model.safetensors" \
--extra_inputs "context_image" \
--use_gradient_checkpointing \
--find_unused_parameters

2
examples/qwen_image/model_training/validate_lora/Qwen-Image-Context-Control.py → examples/qwen_image/model_training/validate_lora/Qwen-Image-In-Context-Control-Union.py
View File

@@ -12,7 +12,7 @@ pipe = QwenImagePipeline.from_pretrained(
],
tokenizer_config=ModelConfig(model_id="Qwen/Qwen-Image", origin_file_pattern="tokenizer/"),
)
pipe.load_lora(pipe.dit, "models/train/Qwen-Image-Context-Control_lora/epoch-4.safetensors")
pipe.load_lora(pipe.dit, "models/train/Qwen-Image-In-Context-Control-Union_lora/epoch-4.safetensors")
image = Image.open("data/example_image_dataset/canny/image_1.jpg").resize((1024, 1024))
prompt = "Context_Control. a dog"
image = pipe(prompt=prompt, seed=0, context_image=image, height=1024, width=1024)