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

qwen-image-distill

Browse Source
This commit is contained in:
Artiprocher
2025-08-05 19:18:43 +08:00
parent 8d2f6ad32e
commit 09360cf4f5
12 changed files with 123 additions and 14 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
examples/qwen_image/README.md
View File

@@ -43,6 +43,7 @@ image.save("image.jpg")
|Model ID|Inference|Full Training|Validation after Full Training|LoRA Training|Validation after LoRA Training|
|-|-|-|-|-|-|
|[Qwen/Qwen-Image](https://www.modelscope.cn/models/Qwen/Qwen-Image )|[code](./model_inference/Qwen-Image.py)|[code](./model_training/full/Qwen-Image.sh)|[code](./model_training/validate_full/Qwen-Image.py)|[code](./model_training/lora/Qwen-Image.sh)|[code](./model_training/validate_lora/Qwen-Image.py)|
|[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_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)|
## Model Inference

1
examples/qwen_image/README_zh.md
View File

@@ -43,6 +43,7 @@ image.save("image.jpg")
|模型 ID|推理|全量训练|全量训练后验证|LoRA 训练|LoRA 训练后验证|
|-|-|-|-|-|-|
|[Qwen/Qwen-Image](https://www.modelscope.cn/models/Qwen/Qwen-Image)|[code](./model_inference/Qwen-Image.py)|[code](./model_training/full/Qwen-Image.sh)|[code](./model_training/validate_full/Qwen-Image.py)|[code](./model_training/lora/Qwen-Image.sh)|[code](./model_training/validate_lora/Qwen-Image.py)|
|[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_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)|
## 模型推理

17
examples/qwen_image/model_inference/Qwen-Image-Distill-Full.py Normal file
View File

@@ -0,0 +1,17 @@
from diffsynth.pipelines.qwen_image import QwenImagePipeline, ModelConfig
import torch
pipe = QwenImagePipeline.from_pretrained(
torch_dtype=torch.bfloat16,
device="cuda",
model_configs=[
ModelConfig(model_id="DiffSynth-Studio/Qwen-Image-Distill-Full", origin_file_pattern="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"),
],
tokenizer_config=ModelConfig(model_id="Qwen/Qwen-Image", origin_file_pattern="tokenizer/"),
)
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, num_inference_steps=15, cfg_scale=1)
image.save("image.jpg")

18
examples/qwen_image/model_inference_lor_vram/Qwen-Image-Distill-Full.py Normal file
View File

@@ -0,0 +1,18 @@
from diffsynth.pipelines.qwen_image import QwenImagePipeline, ModelConfig
import torch
pipe = QwenImagePipeline.from_pretrained(
torch_dtype=torch.bfloat16,
device="cuda",
model_configs=[
ModelConfig(model_id="DiffSynth-Studio/Qwen-Image-Distill-Full", origin_file_pattern="diffusion_pytorch_model*.safetensors", offload_device="cpu", offload_dtype=torch.float8_e4m3fn),
ModelConfig(model_id="Qwen/Qwen-Image", origin_file_pattern="text_encoder/model*.safetensors", offload_device="cpu", offload_dtype=torch.float8_e4m3fn),
ModelConfig(model_id="Qwen/Qwen-Image", origin_file_pattern="vae/diffusion_pytorch_model.safetensors", offload_device="cpu", offload_dtype=torch.float8_e4m3fn),
],
tokenizer_config=ModelConfig(model_id="Qwen/Qwen-Image", origin_file_pattern="tokenizer/"),
)
pipe.enable_vram_management()
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, num_inference_steps=15, cfg_scale=1)
image.save("image.jpg")

12
examples/qwen_image/model_training/full/Qwen-Image-Distill-Full.sh Normal file
View File

@@ -0,0 +1,12 @@
accelerate launch --config_file examples/qwen_image/model_training/full/accelerate_config_zero2offload.yaml examples/qwen_image/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 "DiffSynth-Studio/Qwen-Image-Distill-Full:diffusion_pytorch_model*.safetensors,Qwen/Qwen-Image:text_encoder/model*.safetensors,Qwen/Qwen-Image:vae/diffusion_pytorch_model.safetensors" \
--learning_rate 1e-5 \
--num_epochs 2 \
--remove_prefix_in_ckpt "pipe.dit." \
--output_path "./models/train/Qwen-Image-Distill-Full_full" \
--trainable_models "dit" \
--use_gradient_checkpointing

15
examples/qwen_image/model_training/lora/Qwen-Image-Distill-Full.sh Normal file
View File

@@ -0,0 +1,15 @@
accelerate launch examples/qwen_image/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 "DiffSynth-Studio/Qwen-Image-Distill-Full:diffusion_pytorch_model*.safetensors,Qwen/Qwen-Image:text_encoder/model*.safetensors,Qwen/Qwen-Image:vae/diffusion_pytorch_model.safetensors" \
--learning_rate 1e-4 \
--num_epochs 5 \
--remove_prefix_in_ckpt "pipe.dit." \
--output_path "./models/train/Qwen-Image-Distill-Full_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 \
--align_to_opensource_format \
--use_gradient_checkpointing

20
examples/qwen_image/model_training/validate_full/Qwen-Image-Distill-Full.py Normal file
View File

@@ -0,0 +1,20 @@
from diffsynth.pipelines.qwen_image import QwenImagePipeline, ModelConfig
from diffsynth import load_state_dict
import torch
pipe = QwenImagePipeline.from_pretrained(
torch_dtype=torch.bfloat16,
device="cuda",
model_configs=[
ModelConfig(model_id="DiffSynth-Studio/Qwen-Image-Distill-Full", origin_file_pattern="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"),
],
tokenizer_config=ModelConfig(model_id="Qwen/Qwen-Image", origin_file_pattern="tokenizer/"),
)
state_dict = load_state_dict("models/train/Qwen-Image-Distill-Full_full/epoch-1.safetensors")
pipe.dit.load_state_dict(state_dict)
prompt = "a dog"
image = pipe(prompt, seed=0, num_inference_steps=15, cfg_scale=1)
image.save("image.jpg")

6
examples/qwen_image/model_training/validate_full/Qwen-Image.py
View File

@@ -7,9 +7,9 @@ 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", offload_device="cpu", offload_dtype=torch.float8_e4m3fn),
ModelConfig(model_id="Qwen/Qwen-Image", origin_file_pattern="text_encoder/model*.safetensors", offload_device="cpu", offload_dtype=torch.float8_e4m3fn),
ModelConfig(model_id="Qwen/Qwen-Image", origin_file_pattern="vae/diffusion_pytorch_model.safetensors", offload_device="cpu", offload_dtype=torch.float8_e4m3fn),
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"),
],
tokenizer_config=ModelConfig(model_id="Qwen/Qwen-Image", origin_file_pattern="tokenizer/"),
)

18
examples/qwen_image/model_training/validate_lora/Qwen-Image-Distill-Full.py Normal file
View File

@@ -0,0 +1,18 @@
from diffsynth.pipelines.qwen_image import QwenImagePipeline, ModelConfig
import torch
pipe = QwenImagePipeline.from_pretrained(
torch_dtype=torch.bfloat16,
device="cuda",
model_configs=[
ModelConfig(model_id="DiffSynth-Studio/Qwen-Image-Distill-Full", origin_file_pattern="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"),
],
tokenizer_config=ModelConfig(model_id="Qwen/Qwen-Image", origin_file_pattern="tokenizer/"),
)
pipe.load_lora(pipe.dit, "models/train/Qwen-Image-Distill-Full_lora/epoch-4.safetensors")
prompt = "a dog"
image = pipe(prompt, seed=0, num_inference_steps=15, cfg_scale=1)
image.save("image.jpg")

6
examples/qwen_image/model_training/validate_lora/Qwen-Image.py
View File

@@ -6,9 +6,9 @@ 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", offload_device="cpu", offload_dtype=torch.float8_e4m3fn),
ModelConfig(model_id="Qwen/Qwen-Image", origin_file_pattern="text_encoder/model*.safetensors", offload_device="cpu", offload_dtype=torch.float8_e4m3fn),
ModelConfig(model_id="Qwen/Qwen-Image", origin_file_pattern="vae/diffusion_pytorch_model.safetensors", offload_device="cpu", offload_dtype=torch.float8_e4m3fn),
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"),
],
tokenizer_config=ModelConfig(model_id="Qwen/Qwen-Image", origin_file_pattern="tokenizer/"),
)