MiniMax H3 Day-0 Support in ComfyUI: Open Weights, Native Audio, and 2K Video

4 hours ago

MiniMax H3 is an open-weights omni-modal video model that can generate video up to 2K resolution and 15 seconds with native stereo audio.
It supports text-to-video, image-to-video, first-and-last-frame control, and reference-to-video using images, video, or audio.
The model integrates multimodal context understanding, collapsing multiple tasks into one by processing images, audio, and video together.
Native stereo audio is generated in the same pass as the video, not as a post-process.
Editing and motion transfer capabilities allow using a reference video for movement while applying different subject and style.
The model is optimized for local inference in ComfyUI with a 66% memory reduction (from 123.6 GB to 42.5 GB), enabling it to run on consumer GPUs like the RTX 3060.
Optimizations include pruning modulation weights, int8 convrot quantization, and custom kernels with dynamic VRAM offloading.
Example outputs demonstrate various creative uses: comic-book style, product commercial, high-fashion editorial, and vibrant product ad.

Seedance 2.5 is a next-generation audio-video joint generation model designed for 30-second storytelling with precise reference control and editing capabilities.
It allows creation of videos up to 30 seconds in a single generation, extendable twice for richer storytelling, with smoother motion and more realistic visuals.
The model understands reference videos more precisely, capturing intention, framing, and cinematic language for creative interpretation beyond motion transfer.

Seedance 2.5 generates up to 30 seconds of high-quality audio-video in a single pass, supports multi-round extensions, and improves shot transitions and scene changes for coherent long-form storytelling.
Multimodal referencing is fully upgraded, allowing up to 30 images, 10 videos, and 10 audio clips as inputs, with enhanced capabilities for clay render, motion, and creative references.
Editing is more precise with timestamp-level control, green screen, camera perspective, and reference-based editing, supporting professional film and advertising workflows.

Nano Banana 2 Lite is a high-speed, cost-efficient Gemini Image model designed for fast image generation and editing.
It enables rapid prototyping and iteration, allowing creators to generate thousands of images at a low cost compared to heavier models.
The model maintains control and accuracy, supporting character consistency, precise visual editing, and real-world knowledge integration.

Inkling-Small is a general-purpose multimodal model that accepts text, image, and audio inputs and generates text outputs.
It can be used with libraries like Transformers, vLLM, SGLang, and Docker, as well as through APIs and third-party providers.
The model uses a 42-layer decoder-only transformer with a sparse Mixture-of-Experts (MoE) architecture, totaling 276B parameters but activating only 12B per token.

Blick enables instant editing with no import or project setup dialogs, opening directly to a blank project with autosave.
Users can start exports and continue editing without interruptions; even fix mistakes mid-render without restarting.
Keyframing is done directly in the timeline, allowing live animation recording during playback.

Seedance 2.5 is a next-generation audio-video joint generation model designed for 30-second storytelling with precise reference control and editing capabilities.
It allows creation of videos up to 30 seconds in a single generation, extendable twice for richer storytelling, with smoother motion and more realistic visuals.
The model understands reference videos more precisely, capturing intention, framing, and cinematic language for creative interpretation beyond motion transfer.

Seedance 2.5 generates up to 30 seconds of high-quality audio-video in a single pass, supports multi-round extensions, and improves shot transitions and scene changes for coherent long-form storytelling.
Multimodal referencing is fully upgraded, allowing up to 30 images, 10 videos, and 10 audio clips as inputs, with enhanced capabilities for clay render, motion, and creative references.
Editing is more precise with timestamp-level control, green screen, camera perspective, and reference-based editing, supporting professional film and advertising workflows.

Nano Banana 2 Lite is a high-speed, cost-efficient Gemini Image model designed for fast image generation and editing.
It enables rapid prototyping and iteration, allowing creators to generate thousands of images at a low cost compared to heavier models.
The model maintains control and accuracy, supporting character consistency, precise visual editing, and real-world knowledge integration.

Inkling-Small is a general-purpose multimodal model that accepts text, image, and audio inputs and generates text outputs.
It can be used with libraries like Transformers, vLLM, SGLang, and Docker, as well as through APIs and third-party providers.
The model uses a 42-layer decoder-only transformer with a sparse Mixture-of-Experts (MoE) architecture, totaling 276B parameters but activating only 12B per token.

Blick enables instant editing with no import or project setup dialogs, opening directly to a blank project with autosave.
Users can start exports and continue editing without interruptions; even fix mistakes mid-render without restarting.
Keyframing is done directly in the timeline, allowing live animation recording during playback.

Hasty Briefsbeta