huggingface.co · Open Weight Models
MiniMax's open weight image model: a 33.1B diffusion transformer for text to image and editing with up to 16 references, about 16 MP output in 6 steps. Community license.
MiniMax H3 Image is one of 30 open weight model tools on Axiomi. See all open weight model tools or how we check facts.
// guides
MiniMax H3 Image ComfyUI setup: which files to download, the fixed 6 step settings, editing with references, hardware needs and a license that excludes the US.
// related
MOSS-Image (OpenMOSS)openmoss.github.ioOpenMOSS's Apache 2.0 open weight text to image model: a 5B diffusion transformer with a Qwen3.5-9B text encoder, strong at long text and JSON layout control.Open Weight ModelsOpen source★ 2.9k
FLUXbfl.aiBlack Forest Labs image models. Open weights include FLUX 3 Image Klein, FLUX.2 dev and klein, and FLUX.1 schnell and dev, under Apache 2.0, FLUX Kommunity and non commercial licenses.Open Weight ModelsFreemium★ 26.1k
Mistral AImistral.aiParis based lab publishing both open weight and commercial models, from small edge models to mixture of experts flagships.Open Weight ModelsFreemium★ 10.8k
ComfyUIcomfy.orgNode based open source app for running image, video and audio generation models locally, with shareable JSON workflows and support for quantized checkpoints.ML FrameworksOpen source★ 146.6k
Bonsai (Prism ML)prismml.comPrism ML's family of 1 bit and ternary open weight models, including Bonsai 2 27B, a Qwen3.8-27B derivative that fits in about 6 to 7 GB and runs on Prism's llama.cpp fork.Open Weight ModelsOpen source★ 3.5k
LFM2 / LFM2.5 (Liquid AI)liquid.aiLiquid AI's LFM2 and LFM2.5 open weight edge models, including LFM2.5-24B-A2B (24B MoE, ~2.45B active, 131K context) with official GGUF, MLX, vLLM and SGLang builds.Open Weight ModelsSee siteHN 16