Yuewen Review // Unlimited Free AI Video Generations?

Today we are going to take a peek at a new open-source video AI known as Step-Video-T2V which is a state-of-the-art (SoTA) text-to-video pre-trained model with 30 billion parameters and the capability to generate videos up to 204 frames.

► Github - https://github.com/stepfun-ai/Step-Video-T2V
► Yuewen Online Version - https://yuewen.cn/videos
► OnlineSim Service (Phone Numbers) - https://onlinesim.io/?aref=3523657

In Step-Video-T2V, videos are represented by a high-compression Video-VAE, achieving 16x16 spatial and 8x temporal compression ratios. User prompts are encoded using two bilingual pre-trained text encoders to handle both English and Chinese. #AI #AiVideo #Yuewen #StepFun #AiTools

A DiT with 3D full attention is trained using Flow Matching and is employed to denoise input noise into latent frames, with text embeddings and timesteps serving as conditioning factors. To further enhance the visual quality of the generated videos, a video-based DPO approach is applied, which effectively reduces artifacts and ensures smoother, more realistic video outputs.

___________________________________________________________________
For Business inquiries do drop an email to [email protected]