Self Forcing First and Last Frames ( 3 Photos)
詳細
ファイルをダウンロード
モデル説明
Self Forcing trains autoregressive video diffusion models by simulating the inference process during training, performing autoregressive rollout with KV caching. It resolves the train-test distribution mismatch and enables real-time, streaming video generation on a single RTX 4090 while matching the quality of state-of-the-art diffusion models.
All the links in the description of the video
このモデルで生成された画像
画像が見つかりません。