3Dprinting (172) A.I. (664) animation (335) blender (194) colour (225) commercials (46) composition (150) cool (358) design (627) Featured (65) hardware (302) IOS (109) jokes (134) lighting (278) modeling (116) music (183) photogrammetry (171) photography (744) production (1233) python (84) quotes (485) reference (305) software (1319) trailers (295) ves (522) VR (219)
https://huggingface.co/stepfun-ai/stepvideo-t2v
The model generates videos up to 204 frames, using a high-compression Video-VAE (16×16 spatial, 8x temporal). It processes English and Chinese prompts via bilingual text encoders. A 3D full-attention DiT, trained with Flow Matching, denoises latent frames conditioned on text and timesteps. A video-based DPO further reduces artifacts, enhancing realism and smoothness.
COLLECTIONS
| Featured AI
| Design And Composition
| Explore posts
POPULAR SEARCHES
unreal | pipeline | virtual production | free | learn | photoshop | 360 | macro | google | nvidia | resolution | open source | hdri | real-time | photography basics | nuke
FEATURED POSTS
Social Links
DISCLAIMER – Links and images on this website may be protected by the respective owners’ copyright. All data submitted by users through this site shall be treated as freely available to share.