support wan2.2 5B T2V

This commit is contained in:
mi804
2025-07-20 18:13:50 +08:00
parent d19fcc8c04
commit 55951590f5
5 changed files with 628 additions and 3 deletions

View File

@@ -0,0 +1,34 @@
import torch
from PIL import Image
from diffsynth import save_video, VideoData
from diffsynth.pipelines.wan_video_new import WanVideoPipeline, ModelConfig
from modelscope import snapshot_download
from diffsynth.models.utils import load_state_dict, hash_state_dict_keys
from modelscope import dataset_snapshot_download
dataset_snapshot_download(
dataset_id="DiffSynth-Studio/examples_in_diffsynth",
local_dir="./",
allow_file_pattern=["data/examples/wan/depth_video.mp4", "data/examples/wan/cat_fightning.jpg"]
)
pipe = WanVideoPipeline.from_pretrained(
torch_dtype=torch.bfloat16,
device="cuda",
model_configs=[
ModelConfig(model_id="Wan-AI/Wan2.1-T2V-14B", origin_file_pattern="models_t5_umt5-xxl-enc-bf16.pth", offload_device="cpu"),
ModelConfig(model_id="Wan-AI/Wan2.2-TI2V-5B", origin_file_pattern="model_shards/model-*.safetensors", offload_device="cpu"),
ModelConfig(model_id="Wan-AI/Wan2.2-TI2V-5B", origin_file_pattern="Wan2.2_VAE.safetensors", offload_device="cpu"),
],
)
pipe.enable_vram_management()
# Text-to-video
video = pipe(
prompt="一名宇航员身穿太空服,面朝镜头骑着一匹机械马在火星表面驰骋。红色的荒凉地表延伸至远方,点缀着巨大的陨石坑和奇特的岩石结构。机械马的步伐稳健,扬起微弱的尘埃,展现出未来科技与原始探索的完美结合。宇航员手持操控装置,目光坚定,仿佛正在开辟人类的新疆域。背景是深邃的宇宙和蔚蓝的地球,画面既科幻又充满希望,让人不禁畅想未来的星际生活。",
negative_prompt="色调艳丽过曝静态细节模糊不清字幕风格作品画作画面静止整体发灰最差质量低质量JPEG压缩残留丑陋的残缺的多余的手指画得不好的手部画得不好的脸部畸形的毁容的形态畸形的肢体手指融合静止不动的画面杂乱的背景三条腿背景人很多倒着走",
seed=0, tiled=True,
height=704, width=1280,
)
save_video(video, "video1.mp4", fps=15, quality=5)