ComfyUI Day-0 support for MiniMax H3: a 2K omni-modal video model that fits on an RTX 3060

Hook: On the same day a 2K-resolution, stereo-audio, open-weights omni-modal video model ships, ComfyUI lands a working local-inference path on a 12 GB RTX 3060. That is the first real desktop route for "production-grade" AI video.

Background: from Hailuo to H3, the open-weights moment

On 3 August 2026, Shanghai-based MiniMax (MiniMax Group Inc.) officially released the third-generation omni-modal generation model MiniMax H3 (a.k.a. Hailuo 3.0) as an open-weights release. MiniMax's blog describes H3 as "a general-purpose omni-modal generation model that can jointly understand multimodal contexts spanning text, images, video, and audio" and generate video with "native stereo audio at up to 2K resolution and 15 seconds in length" (MiniMax blog). H3 is the third video model in the Hailuo lineage (after Hailuo 01 and Hailuo 02) and the first that MiniMax has released with open weights. The model card is live on Hugging Face (Hugging Face: MiniMaxAI/MiniMax-H3).

The third-party evaluation house Artificial Analysis posted a leaderboard on X showing H3 ranking #1 in Video Editing, #2 in Text-to-Video, and #3 in Image-to-Video (Artificial Analysis on X). The Decoder wrote on 3 August 2026 that MiniMax H3 was "the first open model to top an AI video ranking" (The Decoder).

The same day, Comfy Org published "MiniMax H3 Day-0 Support in ComfyUI" on its Substack newsletter, detailing the engineering work that brought H3 into ComfyUI 0.30.0 and the optimizations that made local inference feasible on consumer hardware (Comfy Org blog). Two numbers from the post matter most: by pruning roughly 40% of the model parameters (the "modulation weights") into a functionally equivalent lookup table, layering an int8 convrot quantization on top, and shipping custom inference kernels, the Comfy team pushed the total memory footprint of the smallest H3 variants from 123.6 GB in full precision down to 42.5 GB — a 66% reduction. Combined with dynamic VRAM offloading, the result is a 2K-class omni-modal video model that runs locally on an RTX 3060.

What ComfyUI actually did

The ComfyUI integration can be broken into three engineering moves, each of which directly affects "can I run this at home":

  • Multimodal context understanding is the headline capability. H3 takes images, audio, and video in one prompt and resolves them against a description of how the inputs relate, collapsing what would otherwise be five separate tasks (script + image references + audio + reference video + edit pass) into a single model call. The implication: H3 is not a T2V model that happens to accept an image, it is a different architectural choice about where the cross-modal work happens.
  • Native stereo audio is a model property, not a post-process. Every audio output is generated in stereo from the same forward pass that produces the video — there is no separate TTS or audio model bolted on afterwards. The Decoder notes that a single H3 prompt can include up to 9 reference images, 3 reference video clips, and 3 reference audio clips (Hugging Face model card).
  • Editing and motion transfer support a reference-video-supplies-motion, style-comes-from-elsewhere workflow, and combined with in-place editing that means a single shot can be iterated without regenerating the whole clip. For a graph-style pipeline (ComfyUI's natural habitat), this is the capability that changes how workflows are built.

ComfyUI ships three official workflow templates: text-to-video (T2V), image-to-video (I2V), and reference-to-video (R2V) (Comfy-Org workflow_templates). Weights are hosted at Comfy-Org/MiniMax-H3; running locally requires ComfyUI 0.30.0 or later plus the model files in the standard ComfyUI directories.

A practical limit to be aware of: ComfyUI's local H3 workflow caps at 768p. The Decoder reports the same ceiling. The 2K path depends on an H3-Context-IR module that turns prompts and reference material into a structured intermediate representation, and that module is not included in the open-weights release. The community is expected to assemble the context side themselves using MiniMax's published prompting guides.

Opinion: H3's engineering impact outranks "yet another video model"

H3 lands at an interesting moment in the 2026 video-generation landscape, and three things stand out:

1. "Native omni-modal" is moving from concept to working pipeline. Most video models in the past 12 months sold themselves on visual quality and motion stability, with audio and reference understanding handled by separate models. H3 takes four input modalities in one forward pass and emits synchronized stereo video. Whether the underlying mechanism is "truly native" or a tightly-coupled multi-encoder stack is something the open-weights release will let the community verify. What is clear from the ComfyUI Day-0 integration is that the API surface is self-consistent enough to build a real workflow on.

2. Open-weights 2K video has its first real "desktop" path. ComfyUI's 66% memory reduction plus dynamic VRAM offloading is what moves "consumer GPU running a 2K multi-modal video model" from marketing slide to executable. The local ceiling is 768p, so production 2K output still requires either the closed 2K module from MiniMax or an upscale pass — but the bottleneck is no longer "you need eight A100s to try the model." The same day, ByteDance released the closed Seedance 2.5 with 30-second clips and built-in audio, which is a different point on the design space ("long + closed" vs. "open + multi-modal + short").

3. Chinese vendors are bundling "multi-modal weights + infrastructure" together. The pattern repeats: 16 July 2026 saw Moonshot's Kimi K3 launch as a 2.8T-parameter open-weights model ("the world's first open 3T-class model" per Moonshot's own framing on openlm.ai); 19 July 2026 saw Alibaba open-weight the Qwen3.8-Max preview at 2.4T parameters (Alibaba Cloud blog); and on 3 August 2026 MiniMax H3 took the AI video leaderboard with a 33B open-weights release. The "Chinese stack goes fully open" story that started in LLMs is now visibly extending to multi-modal generation.

So what: what practitioners should actually do

For anyone shipping AI video products or building local creative tooling:

  • Update ComfyUI to 0.30.0 and run all three H3 templates today. T2V, I2V, and R2V cover roughly 80% of non-interactive use cases, and side-by-side comparison against Veo / Kling / Runway on the same prompt is the fastest way to locate where H3 still has visible gaps.
  • For 2K commercial deliverables, wait for the missing pieces. The 2K inference module and the H3-Context-IR are still closed. Until MiniMax releases them, the practical path is 768p for offline previews plus a separate upscale pass.
  • Domain fine-tuning is feasible but commercially gated. Fine-tuning H3 on a specific IP, character, or visual style is supported by the open weights, but the commercial-use license restricts it to companies under US$20M in annual revenue. Larger companies need to negotiate separately.

The second half of 2026 is no longer a one-dimensional race about "who is longer, who is sharper." H3's three-part answer is "omni-modal native + open weights + desktop-runnable." The next frontier is the intersection of "open-weights 2K + complete context module" and "consumer-GPU long video."

References