InfinityStar: amazing 720p, 10x faster than diffusion-based
https://x.com/wildmindai/status/1986502031532826776
https://redd.it/1oqfcdc
@rStableDiffusion
https://x.com/wildmindai/status/1986502031532826776
https://redd.it/1oqfcdc
@rStableDiffusion
X (formerly Twitter)
Wildminder (@wildmindai) on X
InfinityStar by Bytedance: A unified 8B spacetime autoregressive model for high-res image & video gen;
- 5s 720p video ~10x faster than DiT;
- scores 83.74 on VBench, topping other AR models and HunyuanVideo;
- Flan-T5-XL as text encoder.
- 480/720p,…
- 5s 720p video ~10x faster than DiT;
- scores 83.74 on VBench, topping other AR models and HunyuanVideo;
- Flan-T5-XL as text encoder.
- 480/720p,…