theluyuan/DiffSynth-Studio
1
0
Fork 0
mirror of https://github.com/modelscope/DiffSynth-Studio.git synced 2026-03-24 18:28:10 +00:00
Code Issues Packages Projects Releases Wiki Activity

DiffSynth-Studio 2.0 major update

Browse Source
This commit is contained in:
root
2025-12-04 16:33:07 +08:00
parent afd101f345
commit 72af7122b3
758 changed files with 26462 additions and 2221398 deletions
Download Patch File Download Diff File Expand all files Collapse all files

21
examples/qwen_image/model_inference_low_vram/Qwen-Image-Distill-LoRA.py
View File

@@ -2,20 +2,29 @@ from diffsynth.pipelines.qwen_image import QwenImagePipeline, ModelConfig
from modelscope import snapshot_download
import torch
# Please do not use float8 on this model
snapshot_download("DiffSynth-Studio/Qwen-Image-Distill-LoRA", local_dir="models/DiffSynth-Studio/Qwen-Image-Distill-LoRA")
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="Qwen/Qwen-Image", origin_file_pattern="transformer/diffusion_pytorch_model*.safetensors", offload_device="cpu"),
ModelConfig(model_id="Qwen/Qwen-Image", origin_file_pattern="text_encoder/model*.safetensors", offload_device="cpu"),
ModelConfig(model_id="Qwen/Qwen-Image", origin_file_pattern="vae/diffusion_pytorch_model.safetensors", offload_device="cpu"),
ModelConfig(model_id="Qwen/Qwen-Image", 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),
],
tokenizer_config=ModelConfig(model_id="Qwen/Qwen-Image", origin_file_pattern="tokenizer/"),
vram_limit=torch.cuda.mem_get_info("cuda")[1] / (1024 ** 3) - 0.5,
)
pipe.enable_vram_management()
pipe.load_lora(pipe.dit, "models/DiffSynth-Studio/Qwen-Image-Distill-LoRA/model.safetensors")
pipe.load_lora(pipe.dit, "models/DiffSynth-Studio/Qwen-Image-Distill-LoRA/model.safetensors", hotload=True)
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)