NEWVectors or files. Pick a path.Start →
    Models/Text To Video/Efficient-Large-Model/SANA-Video_2B_480p
    Text To Videosana, sana-videoother

    SANA-Video_2B_480p

    by Efficient-Large-Model

    472dl/month
    15likes
    Identifier
    Model ID
    Efficient-Large-Model/SANA-Video_2B_480p

    Tags

    sana, sana-videotext-to-videoSANA-Video480p_5s_pretrained_modelBF16diffusionenzharxiv:2509.24695arxiv:2509.25182base_model:Efficient-Large-Model/SANA-Video_2B_480pbase_model:finetune:Efficient-Large-Model/SANA-Video_2B_480plicense:otherregion:us

    Use SANA-Video_2B_480p on Mixpeek

    Build multimodal processing pipelines with this model and others. Extract features, run inference, and set up retrieval in Mixpeek Studio.

    Open Studio

    How It Runs on Mixpeek

    On Mixpeek, SANA-Video_2B_480p runs as a managed extractor inside a processing pipeline. Point a bucket of text to video data at it, and Mixpeek handles GPU provisioning, batching, retries, and writing the outputs into a vector store you can query.

    Extractor outputs land in the Mixpeek Vector Store (MVS), where you can combine them with retrieval, reranking, and filter stages to build end-to-end search and agent-perception pipelines, no model-serving infrastructure to maintain.