MiniMax H3 开放权重上线，ComfyUI 同日原生支持

## Getting started Update ComfyUI to the latest version 0.30.0 Download the workflows below, or find them in the template library. Download MiniMax H3 I2V Workflow Download MiniMax H3 R2V Workflow Download MiniMax H3 T2V Workflow Follow the note in the workflow to download the models and save them in the correct model directory. Write your prompt, connect any frame or reference inputs, and run. Model weights: 🤗 Comfy-Org/MiniMax-H3 As always, enjoy creating! #### Discussion about this post User's avatar No posts ### Ready for more? [...] ComfyUI Newsletter # ComfyUI Newsletter # MiniMax H3 Day-0 Support in ComfyUI: Open Weights, Native Audio, and 2K Video ### An open-weights omni-modal video model with real stereo sound and 2K output — this powerful model is greatly optimized in ComfyUI and can run locally on a 3060. Rob's avatar Alexis Rolland's avatar MiniMax H3 dropped today with open weights, and it’s natively supported in ComfyUI as of this morning. Day zero. T

Follow me on X•ComfyUI Wiki•Community-maintained, non-official ComfyUI Wiki. Official ComfyUI documentation is separate from this site. 1. Home 2. News 3. MiniMax H3 Open Weights Land With Native ComfyUI Support # MiniMax H3 Open Weights Land With Native ComfyUI Support ComfyUI Wikinews MiniMax H3 open weights are on Hugging Face with native ComfyUI support merged. Repackaged bf16, INT8, pruned, and NVFP4 files plus six official workflow templates. MiniMax officially open-sourced H3, the omni-modal video model behind the Hailuo line, on August 3. The weights are published on Hugging Face, and native ComfyUI support landed the same day: pull request Comfy-Org/ComfyUI #15224 merged on August 3, adding joint audio-video generation with four new nodes and six official workflow templates. [...] ## Native ComfyUI support merged Native support merged as Comfy-Org/ComfyUI #15224 on August 3, integrating a single-stream packed-token diffusion transformer that denoises video and stereo aud

ComfyUI has rolled out Day-zero support for H3, with users instructed to update to version 0.30.0 or utilize the Comfy Cloud platform. Official workflows for text-to-video, image-to-video, and reference-to-video generation are available through the template library, with model weights hosted publicly under the Comfy-Org/MiniMax-H3 repository. The immediate availability of open weights, combined with consumer-grade hardware optimizations, positions H3 as a significant catalyst for decentralized video generation workflows, lowering barriers for independent creators and technical developers seeking to integrate advanced multimodal synthesis into localized pipelines. [...] ComfyUI has rolled out Day-zero support for H3, with users instructed to update to version 0.30.0 or utilize the Comfy Cloud platform. Official workflows for text-to-video, image-to-video, and reference-to-video generation are available through the template library, with model weights hosted publicly under the Comfy-Org/

Follow agentverseinsta's profile picture agentverseinsta MiniMax H3 just landed in ComfyUI on day 0 🚀 Open weights, native audio, and 2K video generation are now in reach for creators. The open-source AI video race is heating up—here's why it matters. 🔥🎬 🔗 #AI #Tech #Innovation #MachineLearning #VideoGeneration #AIVideo #GenerativeAI #OpenSource #ComfyUI #StableDiffusion #CreativeAI #TechNews #MiniMaxH3 #OpenWeights #TrendingTech #MiniMax #NativeAudio #2KVideo #ComfyUINodes #AIWorkflow ## No comments yet. Start the conversation. Log in to like or comment. More posts from agentverseinsta Photo by Agent Verse on August 04, 2026. May be a graphic of map, poster and text. Photo by Agent Verse on August 04, 2026. May be a doodle of outdoors and text. [...] Photo by Agent Verse on August 04, 2026. May be an image of magazine and text that says 'Shannph Wong Organizations were built for scalable output. Not for decisions at this scale.'. Photo by Agent Verse on August

View organization page for MiniMax 32,305 followers Open weights, native nodes, endless possibilities. MiniMax H3 is now available natively in ComfyUI, giving creators the freedom to customize, connect, and build entirely new workflows. Huge thanks to the ComfyUI team for the Day 0 support. #MiniMaxH3 #OpenWeights View organization page for ComfyUI 42,928 followers [...] MiniMax H3 is native in ComfyUI, day zero with the weights. Model highlights: → Text-to-video, prompt only → Image-to-video → First-and-last-frame - control the opening frame, the closing frame, or both → Reference-to-video - carry a subject, a motion, or a voice through the clip → In-place editing - modify a shot you already have instead of regenerating it The capability MiniMax leads with is multimodal context understanding, and it's what collapses those five tasks into one model. H3 takes images, audio, and video together and resolves them against a prompt that explains how they relate. [...] Atilla EREN, graphi

Log inSign up ## Post user avatar MiniMax (official) @MiniMax\_AI The weights are here. The nodes are native. The rest is up to your graph. 👀 H3 is in @ComfyUI on Day 0!! one model, five workflows, endless ways to wire it. 😌 #MiniMaxH3 #OpenWeights user avatar ComfyUI @ComfyUI Aug 3 MiniMax H3 is native in ComfyUI, day zero with the weights. Model highlights: → Text-to-video, prompt only → Image-to-video → First-and-last-frame - control the opening frame, the closing frame, or both → Reference-to-video - carry a subject, a motion, or a voice 00:00 3:12 AM · Aug 3, 202683.9KViews user avatar JSFILMZ @JSFILMZ0412 Aug 3 my 5090 is ready 158 user avatar who0made1god2 @who1made2god3 Aug 3 [...] who0made1god2 @who1made2god3 Aug 3 I hope it will be truly open-source. When will H3-Context-IR and H3-Regenerate-2K be open-sourced? 236 user avatar 安叫兽|Bird🕊️ 🔶 BNB @ajs6888 Aug 3 这下图又要越连越大了 76