moss-image 话题在 GitHub 上没有填写简介，这里按 Star 数汇总最相关的热门仓库。
On-device, ComfyUI-style node graph for image/video diffusion on Android. Run MiniMax H3 and WAN 2.2 14B on the Qualcomm Hexagon NPU. SD1.5, SDXL, Flux, Z-Image, Anima, Qwen Image 2.1, Krea 2 & MOSS Image. Inpainting, outpainting, ControlNet, LoRA, IP-Adapter & LivePortrait. Fully offline, no server, no account.
ppt-master v6.8.0 fork (ppt-master-comfyui): local ComfyUI image backend — Qwen-Image-2.1 default, MOSS-Image SFT and Z-Image Turbo selectable; grill-me style interview gate; fully editable PPTX. No API key, no per-image cost. Qwen/MOSS weights are non-commercial — see README.
MOSS-Image Desktop Workstation: Generate images from a single prompt · Visual layout canvas · Built-in inference engine
Preset and per-layer Base+SFT merge node for MOSS-Image in ComfyUI.
ComfyUI node that feeds a reference image through the Qwen3.5-9B vision tower and injects its embeddings into the text prompt (MOSS-Image conditioning)
ComfyUI custom node for MOSS-Image: pick a manga panel layout from 196 previews and enter characters, scenes and dialogue / MOSSで見本から漫画のコマ割りを選んで漫画を作るカスタムノード
A free, local AI image generation studio for Apple Silicon Macs. Run FLUX.2, Krea 2, Z-Image-Turbo, Qwen-Image-2.1-Turbo and SDXL offline on your Mac .
MOSS-Image for Stable Diffusion WebUI Forge Neo: text-to-image with sharp English and Chinese text, img2img and layouts by boxes, with the SFT and Base models
A node designed specifically for image editing models—supporting tiled refinement, editing, and upscaling—compatible with FLUX.3/FLUX.2 klein, Qwen-Image 2.1 / Edit 2509 / 2511, Krea 2+lora and Moss +lora, while ensuring cross-tile consistency.
ComfyUI custom nodes: visual layout editor for MOSS-Image — draw boxes on a canvas and compile the official summary/items layout JSON.
ComfyUI nodes for MOSS-Image: storyboard grids, layout editor, crop/paste, face swap, and an LLM prompt node (caption/expand/edit/assemble) with up to 9 reference images and MiniMax-H3 output. Zero deps, MIT. ｜ 中文：MOSS 故事板/布局/裁贴/换脸 + LLM 提示词节点（9 图、H3 格式）；零依赖，MIT。
用更小的 Qwen3.5 替换 MOSS-Image 的 9B 文本编码器
把 ComfyUI 官方 Create Bounding Boxes 与 MOSS-Image Layout Prompt 融合成单节点的中文画布排版工作台
NegPiP / prompt weighting for Forge Neo, with MOSS-Image and Krea 2 support (fork of the archived sd-forge-negpip; SD1 / SDXL / Anima kept)
Run MOSS-Image locally on Apple silicon Macs. Staged Metal/MPS inference, prompt caching, FP16 and Gradio UI. Mac 本地文生图。
MOSS-Image on Apple Silicon with MLX: exact port, 9 GB peak, and a 15-pass --turbo (6.2x faster). Research notes in research/turbo
ComfyUI 插件：MOSS-Image 中文提示词可视化编辑（bbox 画布）、LLM 中→英翻译、官方口径编译。默认支持 MiMo Token Plan 、Minimax Token Plan 和 DeepSeek API；AGENT.md 追加注入 + LLM 配置预设。
Advanced ComfyUI node suite for the MOSS image ecosystem.
Local MOSS-Image text-to-image studio for Windows and NVIDIA RTX GPUs, with CUDA and WeeLLM streaming for low-VRAM systems.
500 curated MOSS-Image examples with images, complete prompts and generation settings. Posters, products, portraits, illustration and more. By BeatAPI.