Category

Image, video & design

2,665 agents

Every agent in Image, video & design, page 18 of 27

three-ws-assistant★ 5

A 3D avatar assistant for any website in one script tag, with a chatbot mode and a speak mode.

qwen2.5-coder-7b-cadquery-gguf★ 5

mlx gguf cad cadquery text-to-cad code-generation

glb-tools★ 5

Inspect, re-theme, and bake GLB models from the shell or CI. The client SDK behind the three.ws 3D asset pipeline — structural inspection, token-themed mesh synthesis, and appearance baking over live three.ws endpoints.

three-ws-retarget★ 5

Retarget animations onto any humanoid GLB. Canonicalizes bone names from Mixamo, Avaturn, VRM/VRoid, Daz/Genesis, MakeHuman, Unreal, and Blender rigs onto one canonical skeleton, retargets clips with rest-pose and hip-axis correction, and drives them with a crossfading runtime, so no rig ever freezes in a T-pose.

whiteboard-video★ 5

手绘白板风格技术讲解视频生成器——从演讲稿到成品视频的一站式 AI 工作流 skill。

three-ws-forge★ 5

Text/image/sketch to a textured, rig-ready 3D GLB in one call. The three.ws Forge generation SDK: free TRELLIS lane, pay-per-call USDC tiers over x402, and auto-rigging.

remotion-marketing-video-skill★ 5

Agent skill for creating premium Remotion marketing videos product demos, SaaS promos, motion graphics, UI walkthroughs, social ads, and explainers using React and code-first animation.

viewer-presets★ 5

Tuned visual presets for three.ws avatar viewers — light rigs, floor reflection, bloom, and PBR material presets (chrome/gold/glass/…) with seeded variants.

AI-Product-Design-Team-for-Claude★ 5

AI product design workflow for Claude - UX research, MVP scoping, UX/UI design, prototyping, validation, design systems and developer handoff.

blender-copilot★ 5

A Copilot-style AI chat panel that lives inside Blender. The agent loop runs in Blender's own Python process, executes the model's code against your live scene, and wraps every turn in one Ctrl+Z.

krea2-anime-prompt-director★ 5

Agent skill: turn a short idea into a complete Krea 2 anime prompt with faithful Chinese translation.

keyline★ 5

Design engine for AI agents: images and video at every size, no Chrome, 2× fewer tokens. One native binary, driven over MCP.

chwezi-design-engine★ 5

Cross-cutting design & typography skill engine with an anti-AI-slop doctrine — deliberate, human-crafted type, colour, layout & UI. Referenced by every Chwezi engine.

skill-canvas-video★ 5

Agent skill for creating animated videos using HTML5 Canvas and JavaScript, exportable to MP4.

dsh-image-gen★ 5

GPT Image 2.5 generation through Codex subscriptions or API keys, with progressive previews for DeepSeek Harness

ai-desktop-pet-generator★ 5

🐾 一句话(或参考图)生成常驻桌面的高质感宠物。AI 生图 → 本地绿幕抠图 → 8×9 精灵表 → PySide6 桌宠 App,还能在你用 Claude Code / Codex / Antigravity 写代码时实时做出反应。

ClipCaptionAI★ 5

AI video editing toolkit for YouTube shorts, TikTok captions, viral clip finding, masked captions, automatic B-roll, and Remotion workflows

jBahrs-Clip-Generator★ 5

An AI-powered clip/highlight extraction tool built for content creators. Uses local Whisper transcription, Audio Peak Detection, and one of several AI engines to automatically hunt down, crop, and export the best viral moments from multi-hour stream VODs.

awesome-gpt-image-2-prompts★ 5

Awesome bilingual GPT Image 2 prompt gallery — 118 real image examples with OpenAI-compatible HiAPI requests. Built for AI Agents.

ai-commerce-video★ 5

Open-source Codex Skill for planning and producing guarded AI e-commerce product videos

game-asset-style-agent★ 5

AI agent web app: generate style-consistent game assets from reference images (Claude + gpt-image / Gemini)

Roshera-CAD★ 5

Agent-native geometry kernel: a Rust B-Rep engine where every operation returns a validity certificate — nine structural invariants, computed under the write lock, failing closed. Outside its verified envelope it refuses with a typed error rather than approximating. The kernel cannot lie.

motion★ 5

Text and Motion Score to full-body humanoid three.js AnimationClip using IK and balance, with zero dependencies.

brand-artisan★ 5

Turn JSX into brand images (Open Graph, social posts, banners). No browser, no Figma, no server.

forge★ 5

Text/image/sketch to a textured, rig-ready 3D GLB in one call. The three.ws Forge generation SDK: free TRELLIS lane, pay-per-call USDC tiers over x402, and auto-rigging.

lineage-logo★ 5

A local SVG logo editor for fine-tuning designs by hand or with Codex and Claude Code.

phyx3d★ 5

Pre-print simulator for Bambu Lab 3D printers: printability, stability, strength (FEA), physics and robot/mechanism simulation — web app + MCP server for AI agents

humanstandards★ 5

Human factors research translated into design standards, code examples, and an MCP server for AI-assisted validation.

mangaharness★ 5

Kumanga — an open-source, local-first AI manga harness. Reusable characters, a non-destructive editor and a natural-language Manga Agent. BYOK, no account.

ambient★ 5

A video understanding and research agent that can reason over long-form videos

Prism★ 5

Turn a conversation into a movie — free, open-source desktop AI filmmaking studio (Gemini, GPT, Claude, Grok).

demo-studio★ 5

Agent skills that turn any web app into a polished, narrated demo video — Playwright capture, smart zooms, ElevenLabs voiceover, Whisper sync and burned captions.

genesis★ 5

Open source World Model engine. Create infinite experiences, in minutes.

AnimeLoom★ 5

Generate consistent anime videos from a text script using AI — no animators needed

modern-design.md★ 5

Open-source library of design.md specs for 36 modern websites — colors, typography, components, motion, JavaScript libraries, and assets. Each spec is detailed enough that an AI agent can reproduce the design without ever seeing the original site. Live showcase on GitHub Pages.

geometry-dsl★ 5

Deterministic geometry diagram DSL for AI agents — text in, precise math figures out (SVG/PNG). Zero-dependency compiler + Claude/Codex/agent skill.

polyxd★ 5

Every ask gets a screen. An open spec, renderers and a verifier for screens drawn on demand in your own design system.

scrim-ui★ 5

The UI layer your AI product is missing — free in-browser tools and copy-ready components for AI interfaces.

vscode-3d★ 5

Preview GLB and glTF models inside VS Code, try 2,800 library animations or a text-described motion on any rig and bake the result, generate and refine models from a prompt on the free three.ws lane, optimize for the web, diff a model against git, AI quality-check a render, and get diagnostics and completions for <agent-3d> embeds. Powered by three

pfp-byte★ 5

Create geometric SVG profile images optimized for the 4 KiB transaction ceiling.

PetGen★ 5

🐾 一句话或参考图,生成你的桌面伙伴。内置桌宠、休息提醒、番茄钟与 AI 任务反馈。

ip-studio★ 5

一个角色,长出整个内容世界:个人 IP 插画一键生成工作室

nanobanana-app★ 5

CLI for generating images with Google's Nano Banana models (2.1, Pro, Lite): batches, references, real per-image cost. Built for humans and AI agents.

agent-skills★ 5

Agent Skill collection: photo-press-v1 turns a photo into a printed-poster via 12 real printmaking crafts (woodcut, ukiyo-e, watercolor, letterpress, risograph, silkscreen, cyanotype...). 照片印坊:照片→工艺海报,风格是工艺不是滤镜。

Image-Generator★ 5

https://image-generator-psi-one.vercel.app/

vehicle-model-recognition-K230D-Agent★ 5

1000-class Chinese vehicle recognition with ResNet-50, deployed to K230D edge board (28 FPS offline) + ReAct agent

MeshVault★ 5

3D objects management and visualization

ManimFlow★ 5

Generate and publish Manim animations from natural-language prompts with autonomous AI coding agents.

creative-skills★ 5

给 AI 助手的 8 个创作技能:立体头像、Q 版角色卡、个人 IP、文章配图与宣传视频。支持按需安装、连续改图和角色素材复用。

not-a-blogger★ 5

Toolkit for AI agents that make short videos: recipes, prompts, templates and QA tools. Includes 18 agent skills, a text mini-course for people, two runnable starters and 12 real video breakdowns. 143 recipes: 73 measured, 70 hypotheses.

three-ws-pose★ 5

Deterministic, named pose seeds for rigged 3D avatars. Map a natural-language prompt to a stable seed + full Euler joint-rotation map from the three.ws pose-studio preset library.

code2video★ 5

AI-powered math video generator — Automatically transform math problems and concepts into animated tutorial videos using Claude + Manim.

tech-route-maker★ 5

Evidence-grounded editable technical route diagrams for research and engineering projects.

three-ws-viewer-presets★ 5

Tuned visual presets for three.ws avatar viewers — light rigs, floor reflection, bloom, and PBR material presets (chrome/gold/glass/…) with seeded variants.

voila★ 5

Demos that record themselves — permission-free, on-device, agent-native product demo videos. The recipe travels inside the MP4.

Cadra★ 5

Code-first, agent-first 3D video animation framework and studio, built on Three.js and WebGPU. One scene DSL authored in code, by an agent over MCP, or visually, rendered identically live or headless.

libtv-video-production★ 5

OpenClaw Skill —— AI 短视频全流程自动化,用 AI Agent 操控 LibTV CLI 完成从脚本到视频的生成。含标准化 7 步工作流、角色 锚点方案、8 条踩坑避雷清单。Z-image Turbo 锚点 + Seedance 2.0 Mini 视频生成,单轮 ~1100 积分。

Manga-NAI-GPT★ 5

一个故事变成漫画:粘贴整段故事,AI 自动分镜、出图、嵌字成整章。基于 Manga Editor Desu 的个人 fork,独立维护。

three-ws-mocap★ 5

Motion capture as an API. Turn webcam/video into face, pose, and hand animation clips, then save, share, and replay them on any three.ws avatar.

ai-3d-character-generator★ 4

🎮 AI-Powered 3D Character Generator with ComfyUI, Hugging Face, and AgenticSeek integration. Generate 3D models, characters, and assets from text prompts, images, or 3D files. Perfect for game development, Unity, and Unreal Engine.

motif★ 4

LLM-Orchestrated Agent Pipeline for Music-Driven Video Mashup & AMV Generation

IgnisCAD★ 4

A wrapper for the build123d library, designed for AI agents.

studio-director★ 4

JSON-Native AI Visual Direction Engine

Grounded-SAM-2-Stream★ 4

Track anything in streaming with Grounding DINO, SAM 2, and LLM

ai-solution-architect★ 4

Generate solution architecture diagrams

gptpose★ 4

GPT pose image generator to condition SD models with ControlNet OpenPose

Food-Genie--a-Smart-AI-LLM-Based-Food-Reconizer★ 4

An LLM based food recognizer web app which tell about details about food preset in image, calculates calories, fats etc

vision_assist★ 4

Google glass for the blind

tiktoker★ 4

🤳 Meet the AI that makes your videos unskippable

ClipsExtractor★ 4

Youtube Video Clips Extractor [An idea to extract only the clips corresponding to the topics given in the prompt]

promt-to-animation★ 4

2d animation from promt using manim

GenImageGenerator★ 4

Traning qilinadi va generatsiya qiladigan ajoib Gen Ai! Pytorch ai! Machine Learning

my-groupme-bot-imgflip★ 4

💬 A my-groupme-bot plugin which integrates with Imgflip for meme generation from user input.

Emo_Analysis★ 4

Sentiment Analysis app with React-Native

brAInstormer-cloud★ 4

brAInstormer — all-in-one generative AI creative suite: GPT chat, Stable Diffusion, DALL·E 3, text-to-video and animation on one screen.

3Dera★ 4

3Dera Learn history with VR and AI!

OpenAIImageClient★ 4

Generate and edit images using gpt-image-1 model

DALL-E_AI_CLONE★ 4

Build and Deploy a Full Stack MERN AI Image Generation App MidJourney & DALL E Clone

Art-Vision-AI-DALLE-Midjourney-clone★ 4

This is a clone website of DALL-E that can generate image on the text prompt using OpenAI API.

node-red-contrib-image-generation-ubos★ 4

A Node-RED node that interacts with OpenAI machine learning models to generate image outputs like 'DALL·E 2'.

Portfolio-Case-Study★ 4

A Claude Code skill for crafting portfolio-ready design case studies. Structured template, tone guide, and slide layout for UX, product, and design portfolios.

solkerfi★ 4

3D solar system explorer

heroku-clip★ 4

Deploy an API built with Streamlit on Heroku, in order to classify images.

OpenAI-Photo-Generator★ 4

This is a simple React app that generates a photo based on text input using the OpenAI API.

video-generate★ 4

A cutting-edge project leveraging DALL-E 3 and gpt-4o for AI-driven video generation, with FFmpeg for multimedia manipulation.

openai-smart-vision★ 4

AI apps using OpenAI Vision model.

openai★ 4

Examples of using OpenAI’s Image API

Hokage_Vision_Agent★ 4

Agentic anime detection workbench: mock/Ultralytics backends, CLI/API/GUI, tool-calling agent.

ai-styling-case-studies★ 4

See real examples of my styling work (before/after, AI or Human-generated mood boards, capsule breakdowns)

ComfyUI_Viewer_OpenReel_Extension★ 4

Embed and edit videos directly within ComfyUI workflows using the OpenReel extension with timeline, effects, and server-side rendering.

wave-ui-viz★ 4

gradio region:us

weather-picture-agent★ 4

gradio smolagents agent smolagent tool agent-course region:us

LogosAI★ 4

gradio mcp-server-track mcp-server region:us

gradio_overlay_video★ 4

gradio gradio-custom-component gradio-5 laban-movement-analysis pose-visualisation pose-estimation movement-visualisation visualisation

InstructPix2Pix-Chatbot-ui★ 4

docker region:us

vqa_autonomous_driving_smolvlm2★ 4

gradio region:us

ragesh-stable-diffusion-3.5-large★ 4

gradio region:us

GPTJ_PLUS_DALL_E★ 4

gradio region:us

gpt-talking-portrait★ 4

gradio region:us

clip_gpt2★ 4

streamlit region:us

Other categories