Havuz

Official implementation of Prism-MoE, an efficient dense-to-MoE conversion framework for visual autoregressive generation. ICML 2026 Poster.

Give Claude Code or Antigravity an intern: drive Gemini (Antigravity), Codex, Copilot, Cursor and opencode as sub-agents, plus experimental

100个AI电商专家Agent Skills：电商图片、视频、详情页、种草、爆款复刻与多平台内容生产

面向室内设计师与视觉创作者的 Windows 本地 AI 无限画布，支持多模型、ComfyUI 工作流与自定义 API

Visual execution layer for DeepSeek Harness—guided intent, infinite canvas, contextual image tools, and chat-native comments.

A full-stack image & video generation platform powered by Agnes AI. 一站式由AgnesAi实现的图片，视频生成平台。

Layer, animate, glitch, and generate retro visuals and demo scene art.

半调海报 skill：把一句话、一个主题或一张照片做成有印刷质感的艺术封面；12 种风格 + 2 个变体，双色半调、Riso、蓝染、点阵解构，内置元提示词模板。

Use your X Premium or SuperGrok subscription in pi.

HK NPU STUDIO — Local AI for Snapdragon® PCs. NPU-accelerated image generation for Windows 11 ARM64. Featuring Phoenix Boost.

端到端为项目生成风格统一图标集 · 默认4×4网格批量生成+逐个精度兜底+智能抠图，Doubao image_gen 驱动 no API fees

[SIGGRAPH2026] StyleID : Stylization-Agnostic Identity Encoder

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

用固定个人 IP 为中文文章生成 16:9 白底手绘正文配图的 Codex Skill

模块化 NovelAI 全功能 ComfyUI 节点：角色分区、Vibe/精准参考、局部重绘、Director Tools、批量任务与分块精修。

Candy Craft：一个可视化 AI 生图提示词优化工具，支持画板编排、相机布光和双模式 API（后台托管/用户自定义），可直接部署到 Cloudflare Pages。

Turn ComfyUI workflows into stable REST APIs and CLI commands. AI agent friendly.

GPT Image 2.5 Sunburst & Flare toolkit for agents: generation, reference and masked edits, PNG/JPEG/WebP, dry-runs and validated receipts. E

Generates on-brand marketing imagery (ad creatives, logos, slides, carousels) from a brand DESIGN.md via gpt-image-2 — a Codex / Claude Code

Turn complete knowledge into final-only Xiaohongshu educational carousels with consistent characters and deterministic Chinese typesetting.

Codex skill for OpenAI Images API generation and editing in API key mode

Open-source desktop client for the xAI Grok API — chat, image & video generation, voice, and an agentic coding module with local file access

Codex skill that turns paper text into editable draw.io academic figures: drafts a visual reference with image_gen, then rebuilds it as nati

一个工具 = MiniMax 全部多模态能力：DSH 纯文本模型看图/画图/生视频/说话/唱歌/翻唱/搜索/查额度 | One mmx_bridge tool = all MiniMax multimodal (VLM/image/video/speech/music/cover

Turn one topic into a gate-checked Instagram carousel + 9:16 Reels — fully automated, quality-gated, self-hostable.

Local-first AI assistant for Windows: voice (Whisper+Piper), webcam vision, FLUX image gen, image-to-3D, memory, 80+ tools. OpenAI-compatibl

🪄 AI绘画提示词组合器 | 标签浏览/随机组合/ComfyUI集成 | 桌面+手机双端 | AI润色+反推生图+导演预设 |相册管理器

Codex plugin for generating and exporting ChatGPT images through the in-app browser.

Production-grade, agent-portable image prompting skill for Nano Banana Pro and Nano Banana 2 in the Gemini image family

开源微信公众号排版 Skill / AI 视觉主编：让 Agent 将主题、资料或 Markdown 转成 12 套可切换主题的微信兼容文章，支持 AI 配图、手机预览、富文本复制和公众号草稿箱发布。Open-source AI agent skill for Markdown

A unified Model Context Protocol server for MiniMax CLI (mmx)

Local-first AI filmmaking workstation — Flutter Desktop with a node-based canvas wiring multiple AI image/video providers. macOS + Windows.

A Codex Skill that turns one reference image into a safe, one-click Dream Skin theme.

AI Prompt工作流库（自用分享）：详情页制作工作流、电商、TikTok、中泰本地化翻译、AI 生图、视频分镜与自动化

Codex skills for scientific infographics, research cover visuals, and publication-grade paper figures using ChatGPT image generation.

一张照片变成 8 张趣味贴纸：可揭下下载，也可贴上 Mac 桌面 · Turn one photo into 8 playful stickers to download or pin on your Mac desktop.

Qwen Image 2.1 in Frosty Studio: create and edit with 10 references, official prompt enhancement, RGBA and recoverable galleries. Includes F

Local-first novel-to-comic generator — free, no GPU, pluggable providers.

MCP server for Midjourney image generation through Ace Data Cloud.

[ECCV 2026 oral] MIMFlow: Integrating Masked Image Modeling with Normalizing Flows for End-to-End Image Generation

Focused agent skills for thinking and creating · 清晰思考，自由创作。Explore qc-alchemy through 10 visual transformations.

Native macOS image generator for FLUX.2 Klein — fully on-device on Apple Silicon via MLX. No Python, no ComfyUI, no server.

Local-first AI filmmaking workbench on ComfyUI: consistent characters across every still and clip, plan a Day or a Story, talking clips with

AI Claude Code Skill: GPT-Image-2, Foundry, Gemini Game Development Pixel Art, Sprite & Tilemap Image Generation

📸 上传一张照片，生成影棚级职业照/证件照 — 11种风格 + 海马体级美颜，Claude Code / Codex / OpenClaw skill

Rendobar CLI: media processing and AI generation from your terminal. Run FFmpeg, compose video, caption and generate images in the cloud.

Codex使用自定义api如中转站时的图像生成skill

Local AI workstation: chat by voice or text, transcribe, generate images and video (with sound on Apple Silicon), benchmark and serve open-w

700+ visual styles for ComfyUI, every one with a rendered preview you can browse before you commit. Plus 1000+ artists with written descript

Generate, compare, and edit images in Claude Code using your Codex subscription. Background jobs, parallel drafts, and lean context. No imag