SanSteve
Text-to-Video
huggingface/sansteve-text-to-video-bb59cb670d6a4737
Hugging Face model repository SanSteve/Text-to-Video. This listing describes a public repository, not an inference endpoint.
RuntimeWire coverage
- Nunchux speeds video diffusion with value smoothing and FP8 softmax casting
- Pruna AI promises five-second video clips in two seconds
- MiniMax joins Nebius builder program without disclosing a cloud deal
- MiniMax H3 generates a 10.125-second audiovisual file in under nine seconds
- fal ships H3 Max, generating five-second videos in roughly three seconds
- Vercel halves MiniMax H3 and H3 Max prices without code changes
- MiniMax pitches H3 as a video model for consistent game-sprite motion
- MiniMax will present H3 at ModCon in San Francisco on August 18th
- MiniMax and fal announce livestream on building with H3 video model
- MiniMax plans to release H3 2K model and sparse-attention code
- MiniMax schedules H3 consumer-hardware demo as performance remains unverified
- Head to head: Flux 3 Text To Video Draft vs Heygen Video Agent
View on Hugging Face. Model discovered on Hugging Face; repository presence does not establish a release date or inference availability.