mirror of
https://github.com/modelscope/DiffSynth-Studio.git
synced 2026-03-18 13:58:15 +00:00
55 lines
1.9 KiB
Python
55 lines
1.9 KiB
Python
from diffsynth.pipelines.qwen_image import QwenImagePipeline, ModelConfig
|
|
from modelscope import dataset_snapshot_download
|
|
from PIL import Image
|
|
import torch
|
|
|
|
vram_config = {
|
|
"offload_dtype": "disk",
|
|
"offload_device": "disk",
|
|
"onload_dtype": torch.float8_e4m3fn,
|
|
"onload_device": "cpu",
|
|
"preparing_dtype": torch.float8_e4m3fn,
|
|
"preparing_device": "cuda",
|
|
"computation_dtype": torch.bfloat16,
|
|
"computation_device": "cuda",
|
|
}
|
|
pipe = QwenImagePipeline.from_pretrained(
|
|
torch_dtype=torch.bfloat16,
|
|
device="cuda",
|
|
model_configs=[
|
|
ModelConfig(model_id="FireRedTeam/FireRed-Image-Edit-1.0", origin_file_pattern="transformer/diffusion_pytorch_model*.safetensors", **vram_config),
|
|
ModelConfig(model_id="Qwen/Qwen-Image", origin_file_pattern="text_encoder/model*.safetensors", **vram_config),
|
|
ModelConfig(model_id="Qwen/Qwen-Image", origin_file_pattern="vae/diffusion_pytorch_model.safetensors", **vram_config),
|
|
],
|
|
processor_config=ModelConfig(model_id="Qwen/Qwen-Image-Edit", origin_file_pattern="processor/"),
|
|
vram_limit=torch.cuda.mem_get_info("cuda")[1] / (1024 ** 3) - 0.5,
|
|
)
|
|
|
|
dataset_snapshot_download(
|
|
"DiffSynth-Studio/example_image_dataset",
|
|
allow_file_pattern="qwen_image_edit/*",
|
|
local_dir="data/example_image_dataset",
|
|
)
|
|
|
|
prompt = "生成这两个人的合影"
|
|
edit_image = [
|
|
Image.open("data/example_image_dataset/qwen_image_edit/image1.jpg"),
|
|
Image.open("data/example_image_dataset/qwen_image_edit/image2.jpg"),
|
|
]
|
|
image = pipe(
|
|
prompt,
|
|
edit_image=edit_image,
|
|
seed=1,
|
|
num_inference_steps=40,
|
|
height=1152,
|
|
width=896,
|
|
edit_image_auto_resize=True,
|
|
)
|
|
image.save("image.jpg")
|
|
|
|
# FireRedTeam/FireRed-Image-Edit-1.0 is a multi-image editing model.
|
|
# Please use a list to input `edit_image`, even if the input contains only one image.
|
|
# edit_image = [Image.open("image.jpg")]
|
|
# Please do not input the image directly.
|
|
# edit_image = Image.open("image.jpg")
|