lavinal712/togawa_sakiko_wan2.1_lora

Lora of Tokawa Sakiko in Wan2.1

Train and inference in DiffSynth-Studio.

Base model: Wan2.1-T2V-1.3B

Dataset: togawa_sakiko_bangdreamitsmygo

Inference

import torch
from diffsynth import ModelManager, WanVideoPipeline, save_video, VideoData


model_manager = ModelManager(torch_dtype=torch.bfloat16, device="cpu")
model_manager.load_models([
    "models/Wan-AI/Wan2.1-T2V-1.3B/diffusion_pytorch_model.safetensors",
    "models/Wan-AI/Wan2.1-T2V-1.3B/models_t5_umt5-xxl-enc-bf16.pth",
    "models/Wan-AI/Wan2.1-T2V-1.3B/Wan2.1_VAE.pth",
])
model_manager.load_lora("models/lightning_logs/version_2/checkpoints/epoch=9-step=1250.ckpt", lora_alpha=1.0)
pipe = WanVideoPipeline.from_model_manager(model_manager, device="cuda")
pipe.enable_vram_management(num_persistent_param_in_dit=None)

video = pipe(
    prompt="1girl,solo,long_hair,blush,smile,bangs,shirt,ribbon,closed_mouth,hair_ribbon,yellow_eyes,grey_hair,sidelocks,outdoors,day,blunt_bangs,sailor_collar,blurry,official_alternate_costume,tree,looking_to_the_side,black_ribbon,depth_of_field,blurry_background,looking_away,portrait,light_blush,bush,brown_shirt,official_alternate_hairstyle",
    negative_prompt="bad_quality,low_quality,low_res,low_resolution,low_definition,low_definition_video,low_definition_image,low_definition_video_image,low_definition_video_image_quality,low_definition_video_image_quality_video,low_definition_video_image_quality_video_image,low_definition_video_image_quality_video_image_video,low_definition_video_image_quality_video_image_video_image",
    num_inference_steps=50,
    seed=0, tiled=True
)
save_video(video, "video.mp4", fps=30, quality=5)