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

support qwen-image inpaint controlnet

Browse Source
This commit is contained in:
mi804
2025-08-16 17:12:29 +08:00
parent 7dc49bd036
commit 2d09318236
14 changed files with 241 additions and 7 deletions
Download Patch File Download Diff File Expand all files Collapse all files

34
examples/qwen_image/model_inference_low_vram/Qwen-Image-Blockwise-ControlNet-Inpaint.py Normal file
View File

@@ -0,0 +1,34 @@
import torch
from PIL import Image
from modelscope import dataset_snapshot_download
from diffsynth.pipelines.qwen_image import QwenImagePipeline, ModelConfig, ControlNetInput
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="DiffSynth-Studio/Qwen-Image-Blockwise-ControlNet-Inpaint", origin_file_pattern="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()
dataset_snapshot_download(
dataset_id="DiffSynth-Studio/example_image_dataset",
local_dir="./data/example_image_dataset",
allow_file_pattern="inpaint/*.jpg"
)
prompt = "a cat with sunglasses"
controlnet_image = Image.open("./data/example_image_dataset/inpaint/image_1.jpg").convert("RGB").resize((1024, 1024))
inpaint_mask = Image.open("./data/example_image_dataset/inpaint/mask.jpg").convert("RGB").resize((1024, 1024))
image = pipe(
prompt, seed=0,
blockwise_controlnet_inputs=[ControlNetInput(image=controlnet_image, inpaint_mask=inpaint_mask)],
height=1024, width=1024,
num_inference_steps=40,
)
image.save("image.jpg")