moss-image
nightmare-mobile
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.
- 293
- Kotlin
- 13 h ago
ppt-master-zit
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.
- 177
- Python
- MIT
- 10 d ago
ComfyUI-MOSS-Merge-Presets
Preset and per-layer Base+SFT merge node for MOSS-Image in ComfyUI.
- 78
- Python
- MIT
- 13 d ago
ComfyUI-MOSSImageTextEncoder
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)
- 52
- Python
- MIT
- 5 wk ago
ComfyUI-MossPanelDataset
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
- 43
- Python
- MIT
- 2 wk ago
Siliconed
Local image generation and editing on Apple silicon, built on Core AI. Krea 2, Z-Image, Qwen-Image 2.1, Anima and MOSS-Image in native Swift, on the GPU and the Neural Engine, under a fixed memory budget. No Python, no cloud.
- 35
- Swift
- Apache-2.0
- 24 h ago
DiffusionBear
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 .
- 30
- Python
- MIT
- 7 d ago
ComfyUI-Element_TileEdit
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, Moss +lora, MiniMax-H3-Image, while ensuring cross-tile consistency.
- 23
- Python
- Apache-2.0
- 6 d ago
ComfyUI-MOSS-Storyboard
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。
- 20
- Python
- MIT
- 9 d ago
comfyui-moss-prompt-studio
ComfyUI 插件:MOSS-Image 全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。
- 13
- Python
- 11 d ago
RayCodes_MOSS_Image
I Tested MOSS Image AI: The New King of Local Product Ads? - End-to-end commercial product advertising studio powered by OpenMOSS 5B DiT and 8-step DMD.
- 3
- Python
- 5 wk ago
Ekphrasis-Prompt-Bench
Universal Prompt generation tool for Image-to-prompt, photobashing, prompt ideas and rewriting with local vision models (LM Studio), plus a review bench for renders
- 2
- Python
- 11 h ago
comfyui-Ultra-Image-PiD
ComfyUI custom node for AI image generation with Krea 2, Z-Image, Anima, Qwen Image, Qwen Image 2.1 (Turbo) and MOSS-Image. Optional PixelDiT (PiD) 2x/4x upscaling, multi-LoRA and Korean/English UI.
- 1
- Python
- GPL-3.0
- 5 d ago
MOSS Layout Studio + Blind Check
Draw MOSS layouts and blind-check two generated outputs
Runs in the browser on Hugging Face
- 1
- apache-2.0
- 4 wk ago
moss-qwen-faceswap
MOSS body generation + Qwen-Image-2.1 BFS face swap pipeline with Gradio console. Measured similarity 0.783. AI-generated subjects only - no non-consensual use.
- 1
- Python
- 4 wk ago
run-comfyui-image2
Inference Krea-2, Qwen Image 2.x , MOSS-Image, Flux 3 Image Klein, P-H3-Image, Minimax-H3-Image with ComfyUI
- 0
- Shell
- MIT
- 3 d ago
moss-image-base-bf16-m5-ultra
MOSS-Image-Base and -SFT text-to-image on one M5 Ultra: the 5B transformer and prompt encoder on TensorFold's Metal runtime, bf16 as published
- 0
- Python
- MIT
- 3 wk ago
hermes-moss-image
Hermes Agent image plugin for MOSS-Image on TensorFold: exact sizes, steps, seed and guidance from the prompt
- 0
- Python
- MIT
- 3 wk ago












