Havuz

Agentic, long-horizon visual generation: a fuzzy story → a cross-model-audited image-based movie. Brings ARIS's research-wiki + multi-agent

Turn travel photos into archival photo-and-rubber-stamp field note posters.

🎬 泡泡猫的影视工具 — AI 影视创作工作站：文生图、图生图、文生视频、图生视频、短剧剧本拆解与提示词专家。支持 Agnes / DeepSeek / Qwen / 豆包 / MiniMax / Ollama 六大厂商，全局浮层不堵对话框。

DSH Tavern 剧情配图插件，支持 ComfyUI 与多种在线生图服务。

Official code release for the paper "One-Step Generative Modeling via Wasserstein Gradient Flows"

Local MCP server for ChatGPT image generation.

PortableLM — Zero-dependency, air-gapped local AI that runs entirely from a USB drive. Chat, generate images, and synthesize speech offline

Official torch code and models for Sphere Encoder 2

把参考照片做成编辑级艺术海报的开源 Codex Skill 合集

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

Scientific paper figure generation Skill for agents: web research-figure conventions, controlled colour, topology planning, and image genera

The ultimate A1111-style sidebar. Bring the classic UX you know and love into ComfyUI.

教 Claude Code/Codex 真正用好 gpt-image-2 的 skill 包 · Drop-in skill teaching agents to actually use GPT Image 2 — intent-first prompting, surgica

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.

Standalone Skill and Codex Plugin for OpenAI-compatible image generation, editing, batch workflows, QA, and focused canvas editing.

A local image workspace for generating, editing, and comparing AI images with Codex, OpenAI, and Google. Bring your own accounts and API key

Scientific figure workbench with independent VLM/image connections, Chinese UI, and unified size controls.

Open-source AI model aggregation platform with web/admin dashboard, agents, image/video/audio generation, OpenAI-compatible API, wallet bill

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

使用Agnes模型免费生成图片和视频/Generate images and videos for free using the Agnes model.

Crow — a local AI agent, not a chat box: 30 tools, MCP, memory, skills, goals, subagents, vision, and image generation and editing with Qwen

OpenClaw/Claude Code SKILL.md for gpt-image-2 via Codex OAuth, no OPENAI_API_KEY required

Teaching image models to think in manga pages, not illustration grids.

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

为中文公众号文章生成真实 3D 毛毡质感的封面、正文配图与精确插入指南的 Codex Skill。

解决 Codex 中转站生图分辨率/比例与提示词记录问题 / Relay image generation with resolution, aspect-ratio, and prompt records

AI academic PPT workflow skill for Codex / ChatGPT: paper-to-editable PowerPoint, planning table, mockup family, and PPTX generation.

GPT-image-2 的 prompt 工程方法论。核心：用真实参考名替代形容词，prompt 默认中文短句。含单图 playbook、批量网格生成、失败模式树。跨 agent 通用。

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

Design, generate, package, repair, and verify polished app icons from briefs, brand assets, references, SVGs, existing icons, and generated

Official implementation of "Unifying Distributional Training for One-Step Visual Generation" (MGFlow).

A frontend tool for the NovelAI API, offering a clean, high-efficiency interface along with a suite of practical client-side features.

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

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

RunAPI MCP server for model discovery, pricing lookup, media task creation, and balance checks.

Official repository for "Persistence Forcing: Exploiting Feature Specialization in Pixel-Space Diffusion"

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

Give any folder a skin. A free, open-source folder icon changer for macOS, Windows and Linux: skins from community packs, your own photos, o

🎬 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。

Self-hosted studio that turns a story into a consistent AI-illustrated comic, webtoon or narrated video. Bring your own provider key, local

NeveAI é uma plataforma de IA local privacy-first, desenvolvida para oferecer uma experiência de alta performance na execução de LLMs, reduz

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

edge-dit.cpp — a native C/C++ inference engine for Diffusion Transformers (DiT), designed for local and resource-constrained devices with au

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

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

固定 IP × 3D 编辑型中文文章配图系统｜Codex Skill

Ecommerce data and creative AI APIs for marketplace research, product imagery, and video generation, with documentation and code examples.

514 Krea 2 Turbo prompts with generated examples and ComfyUI wildcards

AI agent skill for seamless integration with JsonCut, enabling automated creation and editing of videos and images using the jsoncut.com API