MiniMax H3 开放权重上线，并原生支持 ComfyUI

A lone rider crosses a glacial canyon in one continuous move, camera and native audio straight out of H3. A pint-size superhero calls out a towering city monster, character held consistent from a single reference image. One product shot becomes a full scene — the label stays crisp as the can pours out beside a waterfall. ## Choose a plan Access cloud-powered ComfyUI workflows with straightforward, usage-based pricing. Start free. Upgrade when you're ready. 5 free runs on real GPUs — no credit card required. Billed monthly Generates ~380 5s videos\ Billed monthly Generates ~670 5s videos\ Billed monthly Generates ~1,915 5s videos\ Built for teams collaborating on workflows together. Billed monthly Generates ~13,405 5s videos\ Everything in Pro, plus: Coming soon... [...] Alan M., Co-Founder "I use ComfyUI to help me create VFX for my animated show. It's easy to use, especially with importing a Comfy pipeline on the cloud, and I really like the clean UI and how straig

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. [...] H3 launched on July 31 (read the launch story). The open-weights release brings the model to local GPUs with multiple quantization options. H3 example input image from MiniMax's official demo

# MiniMax Access 12 MiniMax modelsthrough theOpenRouter unified API including H3, Speech 2.8 HD, and Speech 2.8 Turbo. Compare pricing, context windows, benchmarks, and capabilities between different MiniMax models. MiniMaxtokens processedon OpenRouter MiniMax: H3H3 1 hour MiniMax H3 is a lightweight, open-weights video generation model from MiniMax. It is designed for precise multimodal editing and controlled content generation, including instruction-guided edits, text and brand rendering, and video-to-video motion transfer. The model is suited for commercial creative workflows across advertising, e-commerce, gaming, and interface design, with native audiovisual output for reference-driven generation. by minimaxJul 29, 2026from $0.13/second [...] MiniMax-M1 is a large-scale, open-weight reasoning model designed for extended context and high-efficiency inference. It leverages a hybrid Mixture-of-Experts (MoE) architecture paired with a custom "lightning attention" mechanis

The local workflow has limits. MiniMax's official model card says H3-Base generates at 768p, while the documented full-2K process combines a locally deployed base model with hosted H3-Context-IR and H3-Regenerate-2K services. ComfyUI's tutorial describes a native canvas with a 768-pixel short edge, capped at 768 by 1,344 pixels. MiniMax describes H3 as open weights, though its terms are more restrictive than an unrestricted open-source license. The MiniMax H3 Community License Agreement imposes geographic restrictions and requires separate written authorization when a commercial product or service using H3 generates more than $20 million in annual revenue. ### ComfyUI's workflow bet [...] The release adds the workflow layer around MiniMax's H3 weights, including editable templates and local-runtime support. RuntimeWire covered MiniMax's checkpoint release, 2K service path and community license separately. Here, the news is how ComfyUI has made the model inspectable and configurable i

Log inSign up ## Post user avatar MiniMax (official) @MiniMax\_AI Thanks for the love @ComfyUI team 🙌 More canvas, more custom nodes, more workflows and soon, open weights so you can build whatever wild graph you want. 🧑‍🎨✨ user avatar ComfyUI @ComfyUI Jul 31 MiniMax H3 is now available in ComfyUI via Partner Nodes. → Multimodal I/O: T2V, First/Last Frame, Omni Reference → Native stereo audio on every clip →Up to 2K, 5-15s at 24 FPS → Edit characters, scenes, dialogue, and voice in place API access is live today. Native 00:00 8:32 PM · Jul 31, 202636.4KViews user avatar Prince does AI @princedoesai Jul 31 yeah open weights is when i pay attention 87 user avatar ComfyUI @ComfyUI Jul 31 [...] 87 user avatar ComfyUI @ComfyUI Jul 31 All love from the Comfy team - can't wait! 🤝 GIF 666 user avatar A.W.E.S.O.M.-O 4000 @Awesome\_O\_AI Jul 31 Open weights and custom nodes could unlock insane

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, 202684.8KViews 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? 238 user avatar 安叫兽|Bird🕊️ 🔶 BNB @ajs6888 Aug 3 这下图又要越连越大了 76