DiffSynth-Studio 2.0 major update

examples/wanvideo/model_training/special/direct_distill/validate.py

@@ -0,0 +1,23 @@
+import torch
+from PIL import Image
+from diffsynth.utils.data import save_video, VideoData
+from diffsynth.pipelines.wan_video import WanVideoPipeline, ModelConfig
+
+
+pipe = WanVideoPipeline.from_pretrained(
+    torch_dtype=torch.bfloat16,
+    device="cuda",
+    model_configs=[
+        ModelConfig("models/train/Wan2.1-T2V-1.3B_full_distill/epoch-1.safetensors"),
+        ModelConfig(model_id="Wan-AI/Wan2.1-T2V-1.3B", origin_file_pattern="models_t5_umt5-xxl-enc-bf16.pth"),
+        ModelConfig(model_id="Wan-AI/Wan2.1-T2V-1.3B", origin_file_pattern="Wan2.1_VAE.pth"),
+    ],
+    tokenizer_config=ModelConfig(model_id="Wan-AI/Wan2.1-T2V-1.3B", origin_file_pattern="google/umt5-xxl/"),
+)
+
+video = pipe(
+    prompt="纪实摄影风格画面，一只活泼的小狗在绿茵茵的草地上迅速奔跑。小狗毛色棕黄，两只耳朵立起，神情专注而欢快。阳光洒在它身上，使得毛发看上去格外柔软而闪亮。背景是一片开阔的草地，偶尔点缀着几朵野花，远处隐约可见蓝天和几片白云。透视感鲜明，捕捉小狗奔跑时的动感和四周草地的生机。中景侧面移动视角。",
+    cfg_scale=1, num_inference_steps=4,
+    seed=0, tiled=True,
+)
+save_video(video, "video_distill_Wan2.1-T2V-1.3B.mp4", fps=15, quality=5)