theluyuan/DiffSynth-Studio
1
0
Fork 0
mirror of https://github.com/modelscope/DiffSynth-Studio.git synced 2026-03-23 09:28:12 +00:00
Code Issues Packages Projects Releases Wiki Activity

support eligenv2 and context_control

Browse Source
This commit is contained in:
mi804
2025-08-20 22:48:34 +08:00
parent 9ec0652339
commit 5e6f9f89f1
12 changed files with 371 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

35
examples/qwen_image/model_inference/Qwen-Image-Context-Control.py Normal file
View File

@@ -0,0 +1,35 @@
from PIL import Image
import torch
from modelscope import dataset_snapshot_download, snapshot_download
from diffsynth.pipelines.qwen_image import QwenImagePipeline, ModelConfig
from diffsynth.controlnets.processors import Annotator
from diffsynth import download_models
download_models(["Annotators:Depth"])
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"),
],
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")
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))
annotator_ids = ['openpose', 'canny', 'depth', 'lineart', 'softedge', 'normal']
for annotator_id in annotator_ids:
annotator = Annotator(processor_id=annotator_id, device="cuda")
control_image = annotator(origin_image)
control_image.save(f"{annotator.processor_id}.png")
control_prompt = "Context_Control. "
prompt = f"{control_prompt}一个穿着淡蓝色的漂亮女孩正在翩翩起舞，背景是梦幻的星空，光影交错，细节精致。"
negative_prompt = "网格化，规则的网格，模糊, 低分辨率, 低质量, 变形, 畸形, 错误的解剖学, 变形的手, 变形的身体, 变形的脸, 变形的头发, 变形的眼睛, 变形的嘴巴"
image = pipe(prompt, seed=1, negative_prompt=negative_prompt, context_image=control_image, height=1024, width=1024)
image.save(f"image_{annotator.processor_id}.png")