VidoGrid logoVidoGrid

MiniMax H3

Video model family from MiniMax: specs, list prices and every update we have collected.

Maker
MiniMax
Output
Video
Weights
Open
Updates collected
15

MiniMax H3 is a video generation model family from MiniMax. Its weights are published, so it can be downloaded and run locally or fine-tuned. It is not in OpenRouter’s public catalogue at the moment.

VidoGrid has collected 15 updates that mention MiniMax H3; the newest is from 03 Nov 2026.

Hugging Face

Trending on Hugging Face

RepositoryTaskBase modelLicenseDownloadsLikes
Pika-H3-FlexPika-Labs · LoRAimage to videoMiniMaxAI/MiniMax-H3other863476
P-H3-ImagePrunaAItext to imageMiniMaxAI/MiniMax-H3other444136
chroma-h3lodestones · LoRAtext to imageMiniMaxAI/MiniMax-H3other8650
MiniMax-H3-Turbo-Loralarryvrh · LoRAtext to videoComfy-Org/MiniMax-H3apache-2.0206k1.2k
DMADZhengmingYu · LoRAtext to videoMiniMaxAI/MiniMax-H3other108k162
Minimax-h3_SingularityWarmBloodAbanimage to videoMiniMaxAI/MiniMax-H3apache-2.01.1M961
MiniMax-H3-X2-Detail-VAEspeach1sdef178image to videoMiniMaxAI/MiniMax-H3other43k120
Minimax-H3-Hybrid-DMAD-PDMDOliviaRossitext to videoComfy-Org/MiniMax-H3other75311

Updates about MiniMax H3

15 frames
  1. 303New
    MiniMax H3 in ComfyUI | Character Swap, Talk, Sing & Timeline (Ep41)

    In this episode, we test MiniMax H3 in ComfyUI with 25 free workflows, plus 2 bonus workflows. H3 is a video model that makes video with sound, from your images, videos and audio. We test them all, and see what H3 does well and where it struggles. Part 1, change your video: a…

    pixaroma03 NovVideo
  2. 296New
    Which MiniMax H3 model should you use?

    Three MiniMax H3 models, three prices. Here's when to use H3 Highspeed, H3 Lite, and H3.

    Replicate Blog03 NovGuide · video
  3. 265New
    Running a 20B Video Diffusion Transformer on Consumer Hardware: A Deployment and Measurement Report for MiniMax H3 on Apple Silicon

    We report the end-to-end deployment and measurement of MiniMax H3, a 20.38-billion-parameter video diffusion transformer (DiT) - the count measured from the safetensors headers of the Q8 checkpoint as deployed locally (Section 3.2) - running entirely on consumer Apple Silicon…

    arXiv: video generation31 OctPaper · video
  4. 199New
    How I Generated Live Video with MiniMax H3 on a Single GPU

    Can MiniMax H3 keep up with video playback on one GPU while still producing clips worth watching? ComfyStreamerH3 is my attempt to find out.

    ComfyUI Blog08 OctNews · video
  5. 160New
    Making the MiniMax H3 Video VAE 2x Faster

    The MiniMax H3 video VAE now encodes up to ~2.2x faster and decodes ~1.4-2.7x faster on Nvidia GPU.

    ComfyUI Blog22 SepNews · video
  1. 156New
    LightX2V 0.5.1ModelTC/LightX2V18 SepRelease · videoOpen weights
  2. 155New
    H3 Max: Built with fal Inference and Training

    H3 Max generates a 5-second video in under 3 seconds. In our human preference evaluations against twelve leading video models, it ranks first on quality, prompt understanding, and aesthetics. Independent benchmarks from Artificial Analysis and Design Arena rank it first as well…

    fal Blog17 SepNews · video
  3. 152New
    MiniMax H3 Ultimate Upscaling in ComfyUI

    Running MiniMax H3 on your own computer at home is great, but generating higher resolution videos can take a while. Thankfully we have various upscale methods to help us! Using Ultimate Upscale, Latent Upscale 3D and SeedVR2 you can quickly generate your lower resolution (0.2…

    Nerdy Rodent13 SepVideo
  4. 138New
    MiniMax H3 Extensions, Voice Clones & SLA in ComfyUI

    Another ComfyUI workflow power-up to dive further into the world of extending pre-existing or freshly generated videos using the MiniMax H3 Reference conditioning nodes, testing Sparse Linear Attention (SLA) along with the new Lightx2v SLA LoRA and the PDD Acc LoRAs too…

    Nerdy Rodent29 AugVideo
  5. 134New
    Comfy Is Now an Official Reseller of MiniMax H3 Commercial Licenses

    Thanks for reading ComfyUI Newsletter!

    ComfyUI Blog27 AugNews · video
  1. 132New
    Introducing H3 Max by fal

    Announcing H3 Max, a post-trained version of MiniMax H3 developed by fal Research and optimized for maximum speed by fal's inference team. In our human preference evaluations, H3 Max ranks #1 across overall quality, prompt understanding, and aesthetics against leading video…

    fal Blog27 AugNews · video
  2. 128New
    ComfyUI MiniMax H3 Speed LoRA + VRAM Monitor Nodes (Ep32)

    Speed up MiniMax H3 video generation in ComfyUI with the Speed LoRA, optimized sampler settings, and Pixaroma VRAM monitoring nodes. In this tutorial, I show you how to reduce MiniMax H3 generation from the standard 20 steps to 8 or even 4 steps, while finding a practical…

    pixaroma26 AugVideo
  3. 121New
    Diffusers 0.40.0: New pipelines, tensor-parallel support, improved CLI, and moreDiffusers20 AugRelease · video
  4. 118New
    MiniMax H3 Turbo + Custom Frames + Video Extend in ComfyUI

    MiniMax H3 works great on your own PC at home, and thanks to ComfyUI we get loads of custom nodes so we can make things our way! Turbo LoRAs for the First/Last and Reference models help to speed things up, and there are loads to choose from. If 20 steps is too many - why not try…

    Nerdy Rodent17 AugVideo
  5. 111New
    MiniMax H3 = The BEST AI Video - Runs Locally in ComfyUI

    Forget the rest because MiniMax H3 really is the best AI video generation model you can run at home, on your own PC using ComfyUI. With a whole range of model sizes available, Comfy have done an AMAZING job of getting this behemoth to run even on something as lowly as an Nvidia…

    Nerdy Rodent04 AugVideo