Post
1356
Step-Video-TI2V 🔥 text driven Image-to-Video Model released by StepFun_ai
Paper:
Step-Video-TI2V Technical Report: A State-of-the-Art Text-Driven Image-to-Video Generation Model (2503.11251)
Model:
stepfun-ai/stepvideo-ti2v
✨ 30B with MIT license
✨ Up to 102 frames from text + image inputs
✨ Supports motion control and anime-style
Paper:
Step-Video-TI2V Technical Report: A State-of-the-Art Text-Driven Image-to-Video Generation Model (2503.11251)
Model:
stepfun-ai/stepvideo-ti2v
✨ 30B with MIT license
✨ Up to 102 frames from text + image inputs
✨ Supports motion control and anime-style