Havuz

One-click character swap for videos: an open-source, local Higgsfield Genjutsu alternative built on ComfyUI and MiniMax H3, with FLUX.3 Klei

Qwen-Image 2.1 NSFW/姿势出图 skill：作者级提示词配方 + NSFW LoRA + 136 姿势 VNCCS 人偶控制；适用 Claude Code / Codex / Cursor / OpenClaw

可在对话内生成、编辑、对比图像；内置 500 + 提示词、图库、多模型工作流，支持 ComfyUI。AI image studio for DeepSeek Harness — generate, edit & compare images in chat, with 500+

Python library ve CLI olarak görsel ve videolardaki bazı AI watermark işaretlerini ve provenance metadata'sını bulup kaldırmaya yönelik araçlar sunuyor.

Neden yükseliyor · 186 günlük bir repoda 5685 yıldız ve son 28 günde 150 commit dikkat çekiyor; bu, ilgi ve geliştirme etkinliği için güçlü bir sinyal. Ancak bu artışın nedenini veya kullanım başarısını verilen verilerden doğrulamak mümkün değil; son dönemdeki 3 farklı yazar katkının dar bir grupta yoğunlaşabileceğini gösteriyor.

短剧工作台 | 无限时长视频的 MiniMax H3 工作流 | ComfyUI 本地短剧与长视频生成插件

AI画布、AI短剧创作工具：免费、轻量的无限画布，支持短剧剧本、角色管理、分镜、图像/视频生成和短剧剪辑，集成 ComfyUI、Agent、MCP。Free AI canvas and short drama maker.

Berth is a lightweight GPU resource manager written in Go. It controls which applications get access to your GPU, when they get it, and how

Fish Audio Drama 3 text to speech, natively in ComfyUI: voice cloning, dialogue and inline cues on cards from 8 GB, plus a native Qwen3-ASR.

DSH 插件：在对话里调用本机 ComfyUI，用千问 Qwen-Image 2.1 出图。纯本地、不出网、不需要 API Key。

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,

Локальная студия генерации кинематографичных видео со звуком на MiniMax H3 — Windows, NVIDIA GPU, полностью offline.

ppt-master v6.7.0 fork (ppt-master-comfyui): local ComfyUI image backend — Qwen-Image-2.1 default, MOSS-Image SFT and Z-Image Turbo selectab

Generative Fill, Remove object, Generative Expand and Text to Image for PhotoCraft and GIMP 3. Free, local, on your own GPU through ComfyUI.

Custom tools to enhance your Open-Webui Experience! 🚀

Self-hosted, booru-style gallery for a personal image collection

ComfyUI nodes I made for my own workflows: click or type to mask a thing, crop, rotate and pad by dragging handles, inpaint and outpaint tha

Preset and per-layer Base+SFT merge node for MOSS-Image in ComfyUI.

Open-source AI video workbench. Bring any model or your local ComfyUI, and let Claude Code / Codex / Cursor direct it over MCP — storyboard,

Local MCP server for ComfyUI — run your local ComfyUI from AI agents

One ComfyUI skill for every AI coding agent (Claude Code, Codex, Gemini CLI, Qwen Code): drives a local ComfyUI end to end. 75 model prompt

Expand ideas into detailed image prompts with a Chinese SKILL and ComfyUI templates.

Steerable, resumable, bounded-memory MiniMax H3 video workflows for ComfyUI

一套功能完整、轻量稳定的 ComfyUI 实用节点集。初衷是为了平替一些断更插件的功能，会持续更新一些新开发的节点插件。有好的创意可以发Issues，我会力所能及想办法做出来。全中文界面，原生控件，不依赖第三方库。

Refine and improve the quality of small faces in MiniMax H3 video. Per-frame face tracking, crop, refine with H3, stitch back.

Free open-source AI desktop app for audiobooks, podcasts, documentaries, films and animated videos with local models, cloud APIs and editabl

Self-hosted, one-tab workbench for the whole training lifecycle: build Character/Concept/Style datasets (generate, scrape, or triage a big d

原作から脚本・画像生成・組版・PDF出力まで進める、Codex向け漫画制作ツール

🔒 Your private AI assistant, 100% local on Windows: chat, vision, documents (RAG), web search, images, videos with sound, voice, code projec

Distributed image and video generation in ComfyUI for two NVIDIA DGX Sparks.

ComfyUI 自定义节点：ANIMA3 提示词随机生成器 · 五级 NSFW 档位闸门 · 三层权重 · 角色库 2383 位 + 场景搭配 261 条 · 纯本地零依赖 · 只生成提示词，不生成图片

MATRIX Qwen Image 2.1 Dataset Workflow for ComfyUI: local 32-picture character datasets, with Normal and Turbo workflows.

AI-native video editing built around real creative timelines, generative workflows, and local agent control.

破限本地AI女友后宫，Agent+画图语音向量数据库+live2D+桌宠+酒馆角色卡导入+webchat，QQ+Telegram双通道，8G显存可跑 uncensored Fully offline AI girlfriends harem Openclaw/Claude cod

Self-hosted AI studio on your own GPU: chat with your files (RAG), screen and browser agents, coding swarms, LoRA training, an MCP server fo

The local-first sidebar AI agent for ComfyUI — runs on your own Claude OR ChatGPT subscription (no API keys, no extra LLM costs). Drives you

Complete Production Environment for professional MiniMax Music 3 audio generation, including Prompt Generation, Metadata generation includin

Illustrious & NoobAI Style Explorer - A fast, visual reference library for 16,000+ artist styles, optimized for Illustrious XL and NoobAI-XL

Autonomous AI agent for Instagram — generates reels, carousels, memes, quote cards and posts them on autopilot. Free-tier LLM router, commer

🎬 AI全自动短视频引擎 — 基于 Pixelle-Video，新增 HappyHorse (DashScope) 云端文生视频。无需GPU，输入主题一键生成完整视频。Apache 2.0。

Free, open-source plugin for Photoshop and ComfyUI, now on Adobe Exchange. Generate, inpaint, upscale, and split a flat image back into laye

8 个游戏美术 Agent Skills：像素精灵、Spine 骨骼动画、方块角色（Blockbench）与讲解配音。附可复用代码、资源来源、验证记录和效果示例。

中文 9 段式人像提示词创作体系 · 可直接出图的模板/风格预设/千条级批量生成器 · 覆盖全身照与上半身中景照 · 适配 ComfyUI/Krea2/GPT Image 2 · 无强制约束，创作自由

专为 ComfyUI 打造的开源无限画布 AI 创作工作台：纯前端直连自建与云端算力（首选推荐 LightCC 镜像开箱即用），工作流槽位驱动 UI，涵盖生图/全能参考视频/首尾帧，集成 Canvas Agent 与插件生态。Pure frontend infinite canv

面向 DeepSeek Harness 的本地图像生成插件（优化版）：经本机 ComfyUI 调用 Qwen-Image 2.1 生成图像，全部流量限于 127.0.0.1。本版增强推理性能、NVIDIA/Intel/AMD 显卡适配与 Windows/Linux 兼容。原作者

A ComfyUI diffusers implementation of Krea2 for the highest possible quality and most options

A local AI film studio for one Windows PC with an 8 GB NVIDIA card. Write the story, cast the people and render the shots with LTX-2.5, Mini

Codex skill for Krea 2 prompt creation, reverse prompting, conversion, repair, evaluation, and ComfyUI/RunningHub node prompt workflows.

A visual, structured JSON prompt builder for Ming-Image-0.1-Design text-to-image workflows in ComfyUI.

Image generation & visual processing suite for DeepSeek Harness: pluggable providers (FAL, Replicate, OpenAI, ChatGPT Plus, Grok, ComfyUI, S

Prompt builder for Krea-2 in ComfyUI. Fill structured fields and get flowing prose in the format the model expects, not a keyword list.