Havuz

AI image and video generation skill for Claude Code and other coding agents — Gemini, OpenAI and Kie AI behind one CLI and MCP server, with

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

不依赖模型的多模态能力，用 HTML/CSS 渲染生成图片的 Claude Code skill · 32 套风格 · 20+ 尺寸预设 · 零依赖导出 PNG

Native ComfyUI nodes for SenseNova U1.5 image generation and multi-reference image editing.

Local-first AI canvas and timeline. Any MCP agent. Open-source alternative to Higgsfield.

Open-source AI creation canvas built on ComfyUI. Choose models, connect media, and generate images and videos with your own local or remote

Monocolor Editorial Print, Claude Code için temaya veya fotoğrafa dayalı editorial tarzda görseller üretmeye yönelik bir agent skill’idir.

Neden yükseliyor · Agent skill’lerine yönelik ilgiyle örtüşüyor; README’deki çeşitli ve özenli örnekler kullanım amacını hızlıca gösteriyor. 39 günde 3278 yıldız dikkat çekici bir görünürlük sinyali, ancak tek başına kalite veya kalıcı benimsenme kanıtı değil. Son 28 günde 27 commit olması güncel çalışmaya işaret ederken, commit’lerin tek yazardan gelmesi katkı tabanının dar olduğunu gösteriyor.

本地 ComfyUI 抽卡引擎，解决不会写提示词的问题。

OpenAI-compatible API gateway backed by the ChatGPT.com web UI (patchright + real Chrome): chat completions, thinking modes, image generatio

IP as Logo, uyumlu AI agent'lara basit ve ticari kullanıma uygun mascot logo görselleri üretmeleri için yapılandırılmış yönergeler sağlayan bir Agent Skill'dir.

Neden yükseliyor · 40 günde bildirilen 5.582 yıldız projeye belirgin ilgi olduğunu gösteriyor; ancak son 28 günde commit ve farklı yazar bulunmaması, bu ilginin devam eden geliştirme faaliyetiyle desteklendiğine dair kanıt sunmuyor.

Generate images from local Grok, Antigravity, Cursor, or Codex logins, with official API keys as fallback.

OpenAI-compatible reverse proxy for free multimodal AI APIs (chat / images / videos / audio / 3d)

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

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

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+

Create high-fidelity Codex companions from 2+ photos with local open-weight neural editing and no OpenAI API key.

固定 IP × 3D 编辑型中文文章配图系统｜Codex Skill

Photo Decode / 解图 (PhotoDecode) — AI skill for visual analysis, image decoding, source-adaptive reconstruction, color palettes and key visua

dgx-spark-qwen38 is an open-source installer that turns an NVIDIA DGX Spark, or any GB10 machine (ASUS, Dell, HP, Lenovo, MSI, GIGABYTE, Ace

Free image reading & generation for DeepSeek Harness (rc.7 / rc.8 / v0.1.1-rc.1 / rc.2 / v0.1.2-alpha.3) — paste-image reading with auto vis

踏雪创意风格插画 skill，包含14 家族 丰富的变体风格库，提示词七维优化，元提示词创作，创作偏好本地记忆。

剪影群像风格 Skill v1：正负形互补纸艺双联画，锁定原人物像素｜理智画

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

Use your ChatGPT Plus / Pro (Codex) subscription in DeepSeek Harness (DSH): GPT-6 & Codex models, images, web search and quota via ChatGPT s

Local ChatGPT/Codex session adapter for Claude Code, OpenAI-compatible APIs and GPT Image, with a browser admin console.

Open-source visual ontology and constraint engine for inspectable reference-guided image generation. Try Virtual Try-On and Cosplay in the P

Get production-ready images, video, audio, and 3D from any AI agent: skills that pick the right model, price before spending, and keep chara

VibeGame: Vibe Your Dream Game -- An open-source self-evolving multi-agent framework with an AI-Native game engine that turns your natural l

开源、可自托管的 AI 创作与模型管理平台：多模型对话、模型网关、无限画布、图片/视频/商品视觉、办公输出与运营后台（Vue 3 + NestJS）

Turn photos into 16:9 transparent PNG retro gouache journaling material collections with Codex.

Subject-aware minimal-zine image production for Agent Skills: art direction, generation, series, evidence, and real-bitmap QA.

A Codex plugin and local MCP runtime for context-bounded image generation and inspection.

A tap-to-explore picture book where an AI draws every page in real time — type anything, click anything inside, and it draws a new page abou

把任意故事自动变成完整图片素材、分镜、中文视听提示词与 API 清单的 Codex Skill

Image generation (gpt-image-2) and GPT-5 subagents for Claude Code — through the Codex CLI login you already have. No OpenAI API key.

47 installable visual-design skills for Codex, with reusable Python tooling and versioned packages. Turn photos into artwork. Try online: st

AI visual director for turning personal photos into structured, editable visual narratives.

高级朦胧梦幻动态视觉 Skill：把随手拍照片转化为电影感图生图提示词。Dreamy motion editorial prompts from casual photos.

把照片转成带有纸张质感的 zine 海报，让原始影像在下半张纸面里留下有生命感的余像

NexcoreVision OCR + CNN + VLM evidence architecture, consent-gated local ComfyUI/Qwen deployment, and Agnes media generation in one Agent Sk

从多模态素材到选题、核验、脚本、配图和小红书发布文案的 Codex Skill

Turn themes and travel photos into three original editorial poster directions with Codex and GPT Image.

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

把普通文本变成以假乱真的手写体图片：手写字体 + 信纸背景 + 字距/行距/笔画随机扰动。GUI（PyQt6）与 CLI 双入口，numpy/scipy 高性能渲染引擎。

自然言語で頼むと漫画の原稿が出てくる Claude Code スキル — OMNY(ネームYAML)設計→作画→回収→検品→納品のパイプライン

An open Agent Skill for reconstructing faithful, reusable image-generation prompts from reference images.

A Codex skill for clean upper-photo/lower-abstraction travel artworks with source-readable soft visual distillation

[ECCV 2026] Official implementation of "HRDiT: Training-Free High-Resolution Image Generation with Off-the-Shelf Diffusion Transformer Model

A Codex skill for transforming real photos into Photo Relic artworks: truthful photographs paired with quiet paper-memory prints.

Pluggable controls for reliable AI agents: validated outputs, bounded loops and frozen collective decisions.