theluyuan/DiffSynth-Studio
1
0
Fork 0
mirror of https://github.com/modelscope/DiffSynth-Studio.git synced 2026-03-24 10:18:12 +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

46
examples/wanvideo/model_inference_low_vram/LongCat-Video.py Normal file
View File

@@ -0,0 +1,46 @@
import torch
from diffsynth.utils.data import save_video, VideoData
from diffsynth.pipelines.wan_video import WanVideoPipeline, ModelConfig
vram_config = {
"offload_dtype": "disk",
"offload_device": "disk",
"onload_dtype": torch.bfloat16,
"onload_device": "cpu",
"preparing_dtype": torch.bfloat16,
"preparing_device": "cuda",
"computation_dtype": torch.bfloat16,
"computation_device": "cuda",
}
pipe = WanVideoPipeline.from_pretrained(
torch_dtype=torch.bfloat16,
device="cuda",
model_configs=[
ModelConfig(model_id="meituan-longcat/LongCat-Video", origin_file_pattern="dit/diffusion_pytorch_model*.safetensors", **vram_config),
ModelConfig(model_id="Wan-AI/Wan2.1-T2V-14B", origin_file_pattern="models_t5_umt5-xxl-enc-bf16.pth", **vram_config),
ModelConfig(model_id="Wan-AI/Wan2.1-T2V-14B", origin_file_pattern="Wan2.1_VAE.pth", **vram_config),
],
tokenizer_config=ModelConfig(model_id="Wan-AI/Wan2.1-T2V-1.3B", origin_file_pattern="google/umt5-xxl/"),
vram_limit=torch.cuda.mem_get_info("cuda")[1] / (1024 ** 3) - 2,
)
# Text-to-video
video = pipe(
prompt="In a realistic photography style, a white boy around seven or eight years old sits on a park bench, wearing a light blue T-shirt, denim shorts, and white sneakers. He holds an ice cream cone with vanilla and chocolate flavors, and beside him is a medium-sized golden Labrador. Smiling, the boy offers the ice cream to the dog, who eagerly licks it with its tongue. The sun is shining brightly, and the background features a green lawn and several tall trees, creating a warm and loving scene.",
negative_prompt="Bright tones, overexposed, static, blurred details, subtitles, style, works, paintings, images, static, overall gray, worst quality, low quality, JPEG compression residue, ugly, incomplete, extra fingers, poorly drawn hands, poorly drawn faces, deformed, disfigured, misshapen limbs, fused fingers, still picture, messy background, three legs, many people in the background, walking backwards",
seed=0, tiled=True, num_frames=93,
cfg_scale=2, sigma_shift=1,
)
save_video(video, "video_1_LongCat-Video.mp4", fps=15, quality=5)
# Video-continuation (The number of frames in `longcat_video` should be 4n+1.)
longcat_video = video[-17:]
video = pipe(
prompt="In a realistic photography style, a white boy around seven or eight years old sits on a park bench, wearing a light blue T-shirt, denim shorts, and white sneakers. He holds an ice cream cone with vanilla and chocolate flavors, and beside him is a medium-sized golden Labrador. Smiling, the boy offers the ice cream to the dog, who eagerly licks it with its tongue. The sun is shining brightly, and the background features a green lawn and several tall trees, creating a warm and loving scene.",
negative_prompt="Bright tones, overexposed, static, blurred details, subtitles, style, works, paintings, images, static, overall gray, worst quality, low quality, JPEG compression residue, ugly, incomplete, extra fingers, poorly drawn hands, poorly drawn faces, deformed, disfigured, misshapen limbs, fused fingers, still picture, messy background, three legs, many people in the background, walking backwards",
seed=1, tiled=True, num_frames=93,
cfg_scale=2, sigma_shift=1,
longcat_video=longcat_video,
)
save_video(video, "video_2_LongCat-Video.mp4", fps=15, quality=5)