Text to videoTool
ClipProj: Swap MiniMax H3's 32B Text Encoder for a 4B in ComfyUIA ComfyUI custom node replaces MiniMax H3's 15.7 GB Qwen3-VL-32B text encoder with a Qwen3-VL-4B plus a learned projection, cutting conditioning VRAM to 4.5 GB.
MIT
ComfyUI News & Open-Source AI Releases
ComfyUI ecosystem updates — open-source model releases, custom nodes, workflows, and tools for image, video, and audio generation.
Text to video
InpaintingTool
LanPaint 2.0.0: MiniMax H3 Video and Audio InpaintingLanPaint 2.0.0 adds MiniMax H3 support with a video and audio inpainting pipeline: paint per-frame masks and audio intervals in one editor, then inpaint both in a single pass.
Text to imageFine-tune
Kroma v0.2: Krea 2 Full-Model Fine-Tune for ComfyUILodestones releases Kroma v0.2 as a full Krea 2 fine-tuned checkpoint instead of a LoRA, with base and turbo files plus community INT8 quants for ComfyUI.
MIT
Video editingTool
H3 Motion Context v0.2.0: Seamless MiniMax H3 Clip ChainingH3 Motion Context v0.2.0 chains MiniMax H3 clips so motion and audio continue across cuts, adds reference mode support, and removes the visible seam at joins.
Text to videoTool
MiniMax H3 2x Latent Upscaler With ComfyUI NodesMamad8 releases a 2x clean-latent upscaler for MiniMax H3 with two ComfyUI nodes, doubling spatial resolution before VAE decode while staying in latent space.
Text to videoLoRA
MiniMax H3 Turbo LoRA v4: 2-Step Audio-Video GenerationThe v4 step-600 Turbo LoRA distills MiniMax H3 audio-video generation to 2-3 sampling steps, with updated ComfyUI nodes supporting pruned checkpoints and a bundled workflow.
Image editingTool
MiniMax H3 Image VAE: Direct Single-Latent Image DecodingMamad8 releases an experimental image-specialized MiniMax H3 VAE that decodes a single T=1 temporal latent directly into an image, no custom node required.
Character animationBase model
Wan-Animate-2: End-to-End Character Animation With ComfyUI SupportAlibaba Tongyi Lab releases Wan-Animate-2, an end-to-end character animation model consuming driving videos directly, with text-driven viewpoint control and native ComfyUI nodes.
Apache-2.0
Image to videoLoRA
MiniMax H3 Turbo LoRA: 4-Step FL2V Distillation for ComfyUILightx2v and ModelTC distill MiniMax H3 into a 4-step FL2V Turbo LoRA, cutting sampling from ~20 steps to 4 with a ComfyUI conversion and demo Spaces.
Text to videoLoRA
MiniMax H3 Turbo LoRA: 4-Step Audio-Video Generation PreviewA community LoRA renders MiniMax H3 video with synchronized stereo audio in 4 sampling steps instead of ~20. ComfyUI conversion and an example workflow are included.
Apache-2.0
Text to videoTool
ComfyUI-H3-SeedScout: Audition H3 Seeds Before Full Rendertsuremen's new ComfyUI node scouts multiple seeds through the first steps of the MiniMax H3 schedule, shows live previews on the node, and finishes only the seed you pick.
Text to videoBase model
MiniMax H3 w4a8: Kijai's Experimental 4-Bit Weights Land in ComfyUIKijai publishes experimental w4a8 quantized MiniMax H3 weights (12.5 GB FL2VA) with an int8 convrot VAE. ComfyUI core support merged in PR #15308.
minimax-h3-community-license-agreement
Text to videoBase model
MAGI-2 Preview: Sand.ai's Open-Source 114B Audio-Video ModelSand.ai open-sources MAGI-2 Preview, a 114B-parameter MoE that turns text or images into 10-second videos with synchronized audio, activating only 6B parameters per token.
Apache-2.0
Video editingBase model
JoyAI-Video-Edit: Real-Time Video Editing From JD Open SourceJD Open Source releases JoyAI-Video-Edit, a 16B autoregressive diffusion model that edits live video streams in real time at 30 FPS 720p.
Apache-2.0
Text to imageLoRA
Krea 2 OpenPose ControlNet LoRA With ComfyUI WorkflowA classic OpenPose ControlNet LoRA for Krea 2 Turbo: feed a DWPose skeleton map and the model follows the pose while the prompt defines appearance.
Apache-2.0
Text to videoTool
MiniMax H3 TAE: Tiny 2D Autoencoder for Fast Previews in ComfyUIKijai ships a quickly trained 2D tiny autoencoder (TAE) for MiniMax H3 in ComfyUI, previewing video latents faster than latent2rgb via ComfyUI-KJNodes.
Text to videoTool
ComfyUI Spectrum Node Cuts MiniMax H3 Generation Time by ~30%xmarre's ComfyUI-Spectrum-MiniMax-H3 node uses spectral feature forecasting to skip expensive transformer evaluations, delivering ~30% faster MiniMax H3 generation in ComfyUI.
Text to videoBase model
MiniMax H3 Community Quants: GGUF, INT4 and NVFP4 DownloadsCommunity quantizations of MiniMax H3 hit Hugging Face the day after open weights: GGUF Q2-Q5, pruned INT4/INT8, and NVFP4 files with bundled ComfyUI workflows.
minimax-h3-community-license-agreement
Text to videoBase model
AI Toolkit Adds MiniMax H3 Text-to-Video and Image-to-Video TrainingOstris AI Toolkit now supports training MiniMax H3 T2V and I2V LoRAs, with NVFP4 quantization and VAE gradient checkpointing for consumer GPUs.
Open-Weights
Text to videoBase model
MiniMax H3 Open Weights Land With Native ComfyUI SupportMiniMax H3 open weights are on Hugging Face with native ComfyUI support merged. Repackaged bf16, INT8, pruned, and NVFP4 files plus six official workflow templates.
Open-Weights