ClipProj-MiniMax-H3
NicoLab28 · Kit
Lets a small Qwen3-VL stand in for the 32B text encoder of MiniMax H3 in ComfyUI, cutting VRAM from 15.7 GB to 4.5 GB. A proof of concept that needs a custom n…
New
AI projects from Hugging Face
Categories and filters
Listings
LightVAE
lightx2v · Kit
Swaps in lighter video autoencoder parts for Wan2.1, Wan2.2 and MiniMax-H3, through a ComfyUI node or a Python script. For video AI users who want compact VAE…
New
MiniMax-H3-TAE
Kijai · Kit
A small, quickly trained decoder that gives live image previews while MiniMax-H3 video generates in ComfyUI. It gives a cleaner preview than the plain latent2r…
New
MiniMax Music 3
Comfy-Org · Kit
Repackaged MiniMax Music 3 model files for ComfyUI, with a Text to Music workflow for making audio from a written prompt. For ComfyUI users who generate music.
New
natural-face-speech-h3-lora
vpakarinen · Kit
A LoRA add-on for the MiniMax H3 video model that aims for natural face movement and clear English speech in text-to-video and image-to-video clips. For people…
New
Licon VBVR for MiniMax-H3
LiconStudio · Kit
An image-to-video LoRA for MiniMax-H3 that reduces duplicated objects, clipping and odd character motion in generated clips. It suits ComfyUI users who animate…
New
Minimax H3 Latent Upscaler
LBH-123-AI · Kit
Upscales Minimax H3 video latents directly, so you can generate at low resolution and refine at the target size without a decode and re-encode. For people runn…
New
Minimax-h3_Singularity
WarmBloodAban · Kit
Generates video from text, images, references or other videos in ComfyUI with a fine-tuned fusion of MiniMax-H3, now in a V2 INT8 release. For video creators w…
New
MiniMax H3 Turbo LoRA Fast
prithivMLmods · Kit
Try LoRAs for the MiniMax-H3 model, including realistic people and close-up face styles, in a Gradio app that runs in your browser or on your own computer.
New
SLM-MiniMax-Continual-Trainer
BRR1154 · Kit
Has a large controller model watch small language model training, name the layers behind a failure and plan weight updates. Aimed at people who train and tune…
New