Havuz

ingeniería inversa Nano Banana Pro Ext API: 1K $0.03; 4K $0.04. model ID `gemini-3-pro-image-preview`, OpenAI-compatible, async task + cost

小黄（有温度）统一 Skill：品牌 IP 延展、中文轻手绘 PPT、文章封面与正文配图；先规划，再生成可交付 PNG。

리버스 FLUX Kontext Max API: 1K $0.064. model ID `flux-kontext-max`, OpenAI-compatible, async task + cost in every response, $1 minimum top-up.

DSH ComfyUI workbench: asset library + arbitrary workflow runner

Open-source AI workspace for creators: video downloading, translation, dubbing, video/image/voice generation and editing with agents. Powere

一个可以帮你快速反推出网页上图片的提示词，并快速生图测试提示词效果的插件。A Chrome extension to reverse-engineer prompts from web images and instantly validate them via live gen

制作统一漫画墨线风格的解释图与透明角色插图，用于概念、流程、比较和文章配图。

Turn photographs into quiet source-colour isometric paper miniatures with four combinable output modes.

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

A front-end UI for ComfyUI made for beginner level users.

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

Turn a GitHub repository or Hugging Face model into a finished vertical reel: video, cover art and per-platform copy.

Connect Claude to image generation with Agent Skills. Three levels: a zero-cost code-based design engine, a Three.js 3D renderer, and a real

A collection of Agent Skills by Cali Castle.

面向 AI Agent 的 AIGC 漫剧视频创作全流程工具集。

Open-source AI video production editor for filmmakers and AI artists. React + Electron app with node pipelines, image/video generation, stor

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

나노바나나 / 나노 바나나 — Nano Banana 2 API (`gemini-3.1-flash-image-preview`): model id, pricing, parameters and copy-paste examples for the OpenAI-

VEFX-Bench: A Holistic Benchmark for Generic Video Editing and Visual Effects

Multi-modal Generative Media Skills for AI Agents (Claude Code, Cursor, Gemini CLI). High-quality image, video, and audio generation powered

[arXiv 2026] This is the official PyTorch implementation of "MeanFlowNFT: Bringing Forward-Process RL to Average-Velocity Generators".

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

Grok Imagine 1.5 API (`grok-imagine-1.5-apimart`): model id, pricing, parameters and copy-paste examples for the OpenAI-compatible APIMart e

Qwen-Image 3.0 Pro API (`qwen-image-3.0-pro`): model id, pricing, parameters and copy-paste examples for the OpenAI-compatible APIMart endpo

A muted, poetic paper-poster Agent Skill for low-saturation zine-style image generation.

Dreamina — Seedance 2.0 prompts: tested image prompt recipes with example renders, aspect ratios, the model id (`seedance-2.0`) and the cost

为 Hark 提供统一的OpenAI 兼容 API，支持文本对话、图片生成、图片编辑、异步任务和本地控制台。Q交流群1124104343

即梦图片 — Seedream 4.0 API (`seedream-4-0`): model id, pricing, parameters and copy-paste examples for the OpenAI-compatible APIMart endpoint.

Wan 2.7 Video Edit API (`wan2.7-videoedit`): model id, pricing, parameters and copy-paste examples for the OpenAI-compatible APIMart endpoin

电商主图与详情页视觉策划、参考反推和生产级生图提示词 Skill

19 套可直接生图的视觉风格 Skills，为 gpt-image-2 编写。把文章、主题、产品或已有视觉资产编译成完整提示词。/ 19 visual-style prompt skills for gpt-image-2.

Official implementation of “Harness Optimization for Agentic Multi-Reference Image Generation”

Agentic loop image generation without diffusion or autoregressive image models. Coding agents draw in p5.js, using iterative refinement and

Local-first image prompt library for generating images, saving prompts, tags, and collections.

Self-hosted MiniMax H3 video with native audio and Qwen Image. Adaptive ComfyUI workflows, character references, storyboards and saved scene

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

Turn pets, selfies, characters, or anything into a full set of AI chat stickers.

Wan 2.7 prompts: tested image prompt recipes with example renders, aspect ratios, the model id (`wan2.7`) and the cost per image.

Qwen-Image 2.0 prompts: tested image prompt recipes with example renders, aspect ratios, the model id (`qwen-image-2.0`) and the cost per im

Wan 2.7 prompts: tested image prompt recipes with example renders, aspect ratios, the model id (`wan2.7`) and the cost per image.

완 — Wan 2.7 prompts: tested image prompt recipes with example renders, aspect ratios, the model id (`wan2.7`) and the cost per image.

Wan 2.7 Video Edit prompts: tested image prompt recipes with example renders, aspect ratios, the model id (`wan2.7-videoedit`) and the cost

A self-hosted studio for pictures, videos and timelines, in front of your own ComfyUI.

A self-hosted studio for generating images, video, and audio with diffusion models.

Codex skill for turning classical Chinese poetry into cinematic, narrated, scroll-driven webpages · zlbigger.com

Split FLUX.2 and LTX 2.3 across two GPUs (LAN or same-machine) — NVENC compresses activations live on the wire. Icarus (ComfyUI node) + Daed

FLUX Kontext API (`flux-kontext-pro`): model id, pricing, parameters and copy-paste examples for the OpenAI-compatible APIMart endpoint.

Seedance 2.0 Fast API (`doubao-seedance-2.0-fast`): model id, pricing, parameters and copy-paste examples for the OpenAI-compatible APIMart

香蕉 — Nano Banana Pro API (`gemini-3-pro-image-preview`): model id, pricing, parameters and copy-paste examples for the OpenAI-compatible API

FLUX 2 Pro prompts: tested image prompt recipes with example renders, aspect ratios, the model id (`flux-2-pro`) and the cost per image.