English
Hao AI Lab
Report

Hao AI Lab✓

@haoailab

Hao AI Lab at UCSD. Our mission is to democratize large machine learning models, algorithms, and their underlying systems.

379 Following9K Followers735 Posts
  1. Hao AI Lab✓@haoailab
    As promised, FastVideo open-sources @MiniMax_AI FastH3 Omni, training code included! 🚀 - Real-time gen @ 12x faster on NVIDIA Blackwell - NVFP4/FP8 for Spark + RTX! - ComfyUI day-0 Collab with @NVIDIAAI , Nuva Lab @nuvalab and Reactor @reactorworld Open source must win! ♥️
    Download
    3694841146K
  3. Hao AI Lab✓@haoailab
    (1/7) FastVideo FastH3 Omni goes local on DGX Spark, RTX GPUs, and Apple MLX 🚀 - FastH3 Omni, a 5 s 480p clip from a photo and a prompt takes ~3 min. On two Sparks, ~2 min - FastH3 T2AV is 52.6 s on one Spark, 30.7 s on two Sparks Blog: Cookbook: HF 🤗 @NVIDIARTXSpark @NVIDIAAI @MiniMax_AI Every clip in this video was generated on NVIDIA DGX Spark. 8-step NVFP4 checkpoint.
    Download
    7208710.5K
  4. Hao AI Lab✓@haoailab
    Posts @haoailab
    (7/7) Get started in the FastVideo cookbook, with recipes for DGX Spark, 2× Spark, RTX 5090, 24 GB RTX and Apple Silicon. Blog: Cookbook: Models:
    104526
  5. Hao AI Lab✓@haoailab
    Posts @haoailab
    We thank - @posi_posi8 for the M5 Max runs ♥️ - @nuvalab For the amazing work on data curation, training eval and inference optimizations - @reactorworld For providing the compute and early feedback for production API serving of FastH3 Omni! - NVIDIA FastGen (Julius Berner @julberner, Chao Liu @cxlclb, Arash Vahdat @ArashVahdat) - NVIDIA Enterprise Products (Pengcheng Li @landy0220, Cliff Woolley) for the collaboration on FastH3! 🚀 Special thank to @NVIDIAAI, @mbzuai, and @vllm_project for the continued support of FastVideo!
    0081K
  6. Hao AI Lab✓@haoailab
    Hao AI Lab
    RT @yisun0618: UniServe supports FastH3 Omni on Day 0! FastH3 Omni produces high-quality output with fast generation, and it reaches realtime speed in some settings. Our team had a lot of fun building with it internally.
    Hao AI Lab @haoailab
    As promised, FastVideo open-sources @MiniMax_AI FastH3 Omni, training code included! 🚀 - Real-time gen @ 12x faster on NVIDIA Blackwell - NVFP4/FP8 for Spark + RTX! - ComfyUI day-0 Collab with @NVIDIAAI , Nuva Lab @nuvalab and Reactor @reactorworld Open source must win! ♥️
    06075
  7. Hao AI Lab✓@haoailab
    Check out FastVideo FastH3 Omni on ComfyUI!
    ComfyUI @ComfyUI
    FastH3 OmniRef by @haoailab's is now supported in ComfyUI. This distilled version of Minimax H3 allows multi-modal reference generation of videos. It runs locally on your hardware and provide great balance between quality and speed. Click the links below for open weights and cloud ⬇️
    2081.8K
  8. ComfyUI✓@ComfyUI
    FastH3 OmniRef by @haoailab's is now supported in ComfyUI. This distilled version of Minimax H3 allows multi-modal reference generation of videos. It runs locally on your hardware and provide great balance between quality and speed. Click the links below for open weights and cloud ⬇️
    Download
    222539630.4K
  9. Hao AI Lab✓@haoailab
    Hao AI Lab
    RT @wlsaidhi: We keep our promises :)
    Hao AI Lab @haoailab
    As promised, FastVideo open-sources @MiniMax_AI FastH3 Omni, training code included! 🚀 - Real-time gen @ 12x faster on NVIDIA Blackwell - NVFP4/FP8 for Spark + RTX! - ComfyUI day-0 Collab with @NVIDIAAI , Nuva Lab @nuvalab and Reactor @reactorworld Open source must win! ♥️
    06081
  11. Hao AI Lab✓@haoailab
    Posts @haoailab
    6/7 Serve it: one image + one voice on 4x— GB200, then 8 GPUs across two hosts for bigger reference mixes. Pinned checkpoints and configs. Star the repo, try it in ComfyUI, and tell us what you make. Blog: Model: Uniserve: FastVideo Repo:
    12344.9K
  12. Hao AI Lab✓@haoailab
    Posts @haoailab
    7/7 We thank -@nuvalab For the amazing work on data curation, training eval and inference optimizations - @reactorworld For providing the compute and early feedback for production API serving of FastH3 Omni! - NVIDIA FastGen (Julius Berner @julberner, Chao Liu @cxlclb, Arash Vahdat @ArashVahdat ) - NVIDIA Enterprise Products (Pengcheng Li @landy0220, Cliff Woolley) for the collaboration on FastH3! 🚀 Special thank to @NVIDIAAI, @mbzuai, and @vllm_project for the continued support of FastVideo!
    00173.9K
  13. Show more posts