The model is published on Hugging Face under the "MiniMax-H3-Image COMMUNITY LICENSE AGREEMENT," and personal use in Japan is available free of charge. The image-generation tool "ComfyUI" has already ...

On November 3, Pruna AI released the image generation model "P-H3-Image." Based on the video generation model MiniMax H3, it is a model specialized for image generation and editing that can generate ...

On November 10, MiniMax released the weights for its image generation and editing model, "MiniMax-H3-Image." It is the official image-based version of the video model MiniMax H3 and is capable of ...

Image, an image generation and editing model that produces roughly 16-megapixel images directly. Its official speed comparisons vary by task and mode. We also cover input preparation and license terms ...

Starting with v2.1, the nodes are optimized for the latest features in ComfyUI, ensuring compatibility with recent updates such as Nodes 2.0, Subgraphs, INT8-ConvRot, and ComfyKitchen-Attention.

MOSS-Image image-generation acceleration node for ComfyUI. It reduces model calls while keeping the native attention path and the native sampler. TE-Speed-MOSS adds output-prediction step caching to ...

Black Forest Labs released FLUX 3 Image Klein on October 15, 2026, a 5.6B-parameter open-weights model for text-to-image generation, image editing, and multi-reference generation with support for up ...

ComfyUI is one of those tools that's genuinely fun to use…once you've managed to get it running. Every step of making an AI graphic gets its own little box, also called a node, on a large canvas, and ...

Alibaba’s Qwen team has released Qwen-Image-2.1, a unified text-to-image generation and image editing model. Its visual generation component has 7B parameters across 32 single-stream DiT layers. One ...