#AI 绘图
200
2026-08-27
wide-trace/open-higgsfield
S
A studio for image and video generation — one prompt bar, each model’s own settings, and every finished run in one gallery.
2026-09-08
EverettFish/holo-card-studio
S
Turn the user's description or uploaded reference into a finished, editable Blender card and an interactive Three.js page. Preserve the requested subject, style, typography and destination. This skill contains code and text only; generated artwork belongs in the user's output project.
2026-09-08
achimala/dream-loop
A
Agent skill for impressive 3D visuals using Blender + image gen + subagent critic
2026-10-16
OpenMOSS/MOSS-Image
A
Official repository for MOSS-Image, a 5B-parameter base DiT model with high-quality text rendering, layout generation, and efficient fine-tuning.
2026-09-16
Show HN: An e-ink frame that hears birds and draws them as 1800s illustrations
A
See also: Avian Visitors - https://news.ycombinator.com/item?id=48343424 - May 2026 (20 comments)
2026-11-09
jtydhr88/ComfyUI-InstantHMR
A
InstantHMR for ComfyUI: fast 3D human bodies from photos, video and a live camera, on the native SAM 3D Body / MHR nodes
2026-09-03
LunarXuan/image-prompt-reverse
A
High-fidelity AI image prompt reverse-engineering skill for Codex
2026-10-01
blendi-remade/dioramas
B
A free, open-source framework for cinematic, interactive 3D websites with AI-generated assets (Nano Banana 2 + Meshy 7.1 on fal). 20 example sites.
2026-10-13
tritant/ComfyUI_NVIDIA_RTX_VSR_Long_Video
A
NVIDIA RTX Video Super Resolution for ComfyUI, optimized for long videos with disk-backed processing and low RAM usage. Supports AI upscaling, denoising, deblurring, H.264/HEVC NVENC encoding, audio preservation, and an integrated video preview.
2026-09-27
czg86389-hub/muse2api
B
把 Muse(muse.ai) 逆向封装为 OpenAI 兼容接口，支持对话、文生图、文生视频/图生视频、多账号池轮转与 48h 自动续期。OpenAI-compatible API for Muse.ai with Chat, Image & Video generation.
2026-10-17
BreezeSolicitorMap/undress.ai
B
Virtual clothing try-on from a single photo — mobile web app. Upload a person and a garment, get a photorealistic result.
2026-09-14
zorrobyte/asset-studio
B
Fully local, agent-callable text-to-3D game asset pipeline: Qwen-Image-2512 -> Pixal3D (TRELLIS.2) -> Blender/meshoptimizer, FastAPI + CLI + MCP, Docker Desktop, RTX 5090
2026-09-10
Devesh-Shirsath/spotkit
B
Spotkit — a Claude Code skill that turns a feature description into minimal, abstract SVG product illustrations that all belong to one design system.
2026-08-23
whyubel1eve/web-image-skill
A
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
2026-10-27
Patch-gg/trompe
A
Texture a whole game level from a gray blockout with image models: plan cameras, paint, project, bake. Real shadows, glTF out.
2026-10-09
silvermoong/stocking-texture-tool
A
给插画里的丝袜加上真实、没有摩尔纹的织物纹理。Adds a realistic, moire-free knit texture to the stockings in an illustration.
2026-10-06
fatihaydost/brand-identity-skill
A
A Claude Code skill that designs a brand identity as one system: logo, typography and colour palette built together from one brief, measured, compared as identity cards, and delivered as a brand guidelines kit.
2026-08-28
kobingogo/motion-sticker-pack
A
Agent Skill: turn a character image into a looping transparent sticker pack (WebP/GIF/PNG + ZIP).
2026-08-23
Cripacx/mediagen
B
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 EU AI Act content marking.
2026-10-21
JGRFW/ComfyUI-CharacterCardStudio
A
ComfyUI custom node: one-click character reference sheet (character card) generation, auto slice & recomposition for Qwen-Image 2.1
2026-10-10
yuichi-suzuki-highdrama/relight-anime
A
Relight Anime: After Effects plugin that adds light and shadow to AI anime footage using estimated depth (TypeGPU lighting model ported to C++/CUDA)
2026-09-29
zju3dv/geometry-as-address
A
[ARXIV 2026] Geometry as Address: Routing Attention to Visual Memory for Long-Horizon Camera-Controlled Video Generation
2026-11-04
KadoBOT/ComfyUI-H3-Continuity-Studio
B
ComfyUI Timeline Studio for MiniMax H3: multi-shot video, visual memory across scenes and angles, and local or cloud Story writing.
2026-10-05
joeseesun/qiaomu-codex-imagegen
B
让任何 Agent 调用 Codex 内置生图（MCP + CLI + Skill），内置小红书、视频封面、Mondo 海报技巧 · Codex image generation for any agent
2026-10-01
aek15/listing-to-3d
B
Codex skill for reconstructing real-estate listings as plan-based, walkable 3D scenes.
2026-09-22
baoerger/editable-ppt-rebuilder
B
Auditable workflow for rebuilding raster slides into editable PowerPoint decks with OCR, semantic assets, ImageGen, and strict QA
2026-10-28
ElectronGirl/ComfyUI-Anima-Ref-Adapter
B
Reference-image character and style transfer for Anima in ComfyUI (offset-RoPE reference frame + LoRA)
2026-09-27
lemomo-ai/lemo-opuscar
B
39 film styles, each a reusable style prompt plus a short film made entirely in code by Claude Opus 5.5. Pick a style, bring your own story, and let your agent direct. | Opus5.5 x 39 种影片风格：风格提示词 + 纯代码样片 + 导演与技术指南
2026-09-02
TwoAbove/ComfyUI-H3VideoOutpaint
B
Prompt-free sequential sliding-window MiniMax H3 video outpainting for ComfyUI
2026-08-31
Tomat0223/AbyssBeacon
B
A local model discovery and download manager for Hugging Face, CivitAI, CivitAI Red, ModelScope, TensorHub Art, and SeaArt.
2026-10-22
guscanales/rigup
B
Turn a gaming PC or a MacBook/Mac Mini into a local AI server with one install. A web dashboard installs and switches the models: chat and coding on both, image and video on NVIDIA. Tuned for 12 to 24 GB NVIDIA cards and 16 to 128 GB Apple Silicon Macs.
2026-10-14
obraia/gausify-orbit
B
Turn orbit videos (including AI-generated ones) into Gaussian Splats, 100% locally: desktop app (Tauri) and a WebGPU version that runs in the browser.
2026-09-22
tonyd2wild/2Wild-Image-Video-Gen-Studio
B
Plain-language web remote control for a fleet of ComfyUI instances (Qwen-Image-2.1 stills, MiniMax-H3 video). Stdlib Python, no dependencies.
2026-10-27
chenisan/13soul-storyboard-studio
B
Local browser-based storyboard tool for AI video: X/Y/Z camera coordinates, camera gear, 3D director stage, first-frame generation via Codex CLI (UI in Traditional Chinese)
2026-09-28
sajb0t/comfyui_ensemble_upscale
B
ComfyUI node that upscales an image with one to three ESRGAN models without averaging the detail away.
2026-09-26
Work-Fisher/ComfyUI-Fisher-Pose
B
ComfyUI 姿势与机位编辑器 for Qwen Image 2.1：VNCCS 真人人偶 + OpenPose 一键摆姿（内置 209 骨架）+ 自由视角多人机位 | Pose & camera studio with VNCCS PoseStudio LoRA
2026-09-24
janishar/qwen-image-2.1-studio
B
Local Qwen-Image-2.1 studio for Apple Silicon: text-to-image, multi-image editing and prompt enhancing, with a CLI and a helmstudio web UI.
2026-10-03
ph1lb4/imagegen-mac
B
Local AI image generation for Mac. Run Qwen-Image 2.1 on Apple Silicon, offline and private, with a built-in MCP server for Claude Code and AI agents.
2026-09-20
Saganaki22/ComfyUI-Hyperflow
B
ComfyUI node pack for HyperFlow [Video Rebirth's] 8-step LoRA for MiniMax-H3 (video + audio), ported onto ComfyUI's native MiniMax-H3 model. No ComfyUI core files are modified; no custom sampler is needed.
2026-10-22
ThetaCursed/ComfyUI-MOSSImageTextEncoder
B
ComfyUI node that feeds a reference image through the Qwen3.5-9B vision tower and injects its embeddings into the text prompt (MOSS-Image conditioning)
2026-10-14
Arekejoker/qwen21-nsfw-pose-skill
C
Qwen-Image 2.1 NSFW/姿势出图 skill：作者级提示词配方 + NSFW LoRA + 136 姿势 VNCCS 人偶控制；适用 Claude Code / Codex / Cursor / OpenClaw
2026-10-14
Yuanyu0/DASA
B
The official implementation of "Dynamics-Aware Sparse Attention for Efficient Autoregressive Video Diffusion"
2026-10-13
jonwheatley/pixel-path
B
Turn any two places into a pixel-art fly-through of the real road. A Claude Code skill.
2026-10-09
LINs-lab/UltraText_Bench
B
UltraText Bench: A Comprehensive Bilingual Benchmark for Evaluating Visual Text Rendering in Image Generation
2026-10-02
shiaho777/float-android
B
一部装在 Android 里的 AI 虚拟手机：拟真桌面、聊天、朋友圈、查手机、地图定位、语音/视频通话、日记日历。AI 角色有作息、日程、位置和长期记忆，会主动发消息、发帖互动。数据全在设备本地，联网只调你自己配置的 LLM/生图/语音 API。
2026-09-23
kinfolk0117/ComfyUI-QwenImage21-LatentUpscale
B
Learned 2x latent upscaling for Qwen Image 2.1 in ComfyUI.
2026-10-17
chegom/ig-cardnews
B
인스타그램 카드뉴스 캐러셀 자동 생성 — gpt-image-2/FLUX로 배경을 만들고 Pillow로 한글을 정확히 얹는 8장 파이프라인
2026-10-16
alienflm/MacTok
B
[CVPR 2026 Highlight] Official PyTorch implementation of MacTok, a masked 1D continuous image tokenizer that compresses images into just 64 or 128 tokens.
2026-09-04
op7418/guizang-yingzao-skill
C
🏯 Claude Code / Codex skill — transform Chinese architecture, cultural places & travel photos into art-directed editorial posters with GPT Image. 中国古建筑与在地文化照片 → 艺术指导海报
2026-08-31
SmBai1998/sci-ps-skill
B
科研绘图不再只是 AI 生一张图。这个 Skill 会自动分析参考图、拆解组件、生成素材，再进入 Photoshop 按图层逐步重建，并对位置、大小、形状、透视、色调、阴影、光效和遮挡关系进行逐层校准。最终不是一张扁平图片，而是一份可以继续修改的完整 PSD。Science 封面、Nature 风格机制图、3D 科研示意图都可以按这套流程处理。
2026-11-05
Pyramidriseize/ai-fursuit-pattern-generator
B
Free studio for fursuit patterns and furry art. Local, portable, no account.
2026-10-14
dughogan/nuke-alphagen-ofx
B
DUGco AlphaGenSAM (beta): Nuke OFX plug-in that brings LTX-2.5 Alpha-Gen + SAM 3.1 into Nuke through a Comfy backend (Comfy Cloud or local ComfyUI)
2026-09-08
LerSent001/holo-card
C
A Codex skill for layered holographic cards with parallax, contour glow, and an optional API workflow
2026-09-07
wanshuiyin/ALIGN-Agentic-Loop-Image-GeneratioN
B
Agentic loop image generation without diffusion or autoregressive image models. Coding agents draw in p5.js, using iterative refinement and adversarial visual review for high-fidelity art and method figures. Skills for Claude Code and Codex.
2026-08-25
wonderfulearth/primitive-operation-painter
C
Autoregressive primitive-operation painter with GPU image-to-sequence converter
2026-11-03
apekshik/anyshot
B
AnyShot: an AI cinematographer for 3D scenes on fal. Scene in, directed shots out.
2026-10-30
wexloops/openfield
B
Open-source studio for video, stills and 3D on your own GPU through ComfyUI
2026-10-29
lovisdotio/video-to-texture
B
Turn an AI video into a real UV texture on your 3D mesh: Blender orbit, Seedance 2.5, nvdiffrast fit, Seedream 5 Pro atlas completion.
2026-10-28
deepopen-com/deepopen-3d-webs
B
Image-driven 3D scene generation system. Users provide a reference image and prompt words, and the system generates previewable, replayable, and traceable scene results according to the camera trajectory; official 3D demonstration assets allow direct viewing of color/depth animations and Gaussian point clouds in the browser 图像驱动的三维场景生成系统
2026-09-04
Saganaki22/ComfyUI-VDN-H3
C
Video Delta Net hybrid attention for MiniMax-H3 as a native ComfyUI node.
2026-09-02
lihaoyun6/ComfyUI-H3VAE_TRT
C
Running ONNX/TRT version of the MiniMax-H3 VAE in ComfyUI, which increase speed by up to 1.7x
2026-10-13
VAST-AI-Research/EdenLive
B
Real-time generative rendering for interactive worlds, from any reference.
2026-09-25
virtualrepublic/Gaussian-Render-Capture
B
Blender add-on: renders a model into a ready-to-train COLMAP capture for Gaussian Splatting (Postshot, LichtFeld Studio)
2026-08-25
dughogan/comfy_workflow_audit
B
A tool to evaluate whether a ComfyUI workflow can be used in production.
2026-11-05
andrew-babo/muse4ai
B
Muse4AI — let your AI agent make the pictures and the videos. Local Windows bridge for Muse via REST, MCP, and OAuth.
2026-10-21
qianshuixia/shrimpreel
C
Open-source template for "one photo → AI video that follows a viral template" SaaS sites, one site per trending keyword. Cloudflare Workers + D1/R2/KV/Queues, TanStack Start + Hono, Google sign-in, credit packs (Waffo/Dodo), fal.ai video generation, admin console.
2026-10-01
GStaaaaa/ComfyUI-Gaoshang-Pose
B
高尚姿势编辑器：ComfyUI 1–9 人独立摆姿、9 图输入、彩色编号、站位与转身控制，适配 Qwen Image 2.1。
2026-09-18
cth9191/higgsfield-api-skill
B
On-demand Higgsfield API image and video generation for coding agents, with model-specific docs and resumable jobs.
2026-09-12
koppkvn/image-gen-open-source
B
A local image workspace for generating, editing, and comparing AI images with Codex, OpenAI, and Google. Bring your own accounts and API keys.
2026-08-27
okooo5km/rembrandt-portrait-lighting
C
Turn everyday people or pet photos into clean, cinematic Rembrandt-lit studio portraits.
2026-10-23
Chenkin-x/ComfyUI-Moss-Image-Edit
B
Edit images in ComfyUI with text instructions and up to four reference images.
2026-10-07
dashuaibi12339-blip/discord-ai-metadata-detector
B
Chrome/Edge extension: detect AI-drawing metadata (prompt/params/source) in Discord image attachments
2026-09-24
revfactory/qwen-image-studio
B
Apple Silicon 에서 Qwen-Image-2.1 을 로컬로 돌리는 이미지 생성 스튜디오 (Next.js + shadcn/ui, ComfyUI GGUF, mflux)
2026-08-29
wyzborrero/ComfyUI-H3-FunControl
B
MiniMax-H3 Fun ControlNet for ComfyUI. Depth, canny, pose, HED or MLSD video driving H3 frame by frame, built on ComfyUI's own H3 blocks.
2026-08-28
HK416-TYPED/LAX-Prompt-Lens
B
Chrome extension for extracting Danbooru tags and generating professional illustration art-direction prompts.
2026-11-05
afj176/open-cinema-studio
B
A local, open-weights film studio built on ComfyUI: story, shot direction, reference frames, LTX video with audio, and final cuts.
2026-10-30
10291124jcjc-dotcom/ai-anime-series
B
AI 动画单元剧：固定原创角色，一句话出一集。角色设定图 + 宫格故事板 + 即梦 Seedance 一次生成。Claude Skill.
2026-10-09
threerocks/sweety-image-art-direction
B
图像美术指导：保留画风与主体，明确参考图用途，组织提示词并逐轮检查成图。Standalone, explicit-only AI art direction skill.
2026-09-27
shootthesound/ComfyUI-Fizgig-H3-Still
B
True single-frame stills from MiniMax H3 in ComfyUI: a one-frame latent and a clean decode, at any size. No extra models.
2026-09-16
slmonker/selflift-Avatar
B
Experimental ComfyUI SelfLift variant for MiniMax H3 video/audio masks and audio preservation.
2026-09-15
topmass/topnodes
B
ComfyUI nodes and H3 workflows for single and dual character replacement, SAM mask repair, and full-clip timing
2026-08-24
hsuliang/generate-ai-presentations-skill
B
Codex Skill for creating 16:9 presentation images, PPTX decks, image prompts, and slide planning tables.
2026-10-31
wquguru/shisei
B
💃 Free CC0 mannequin pose reference library for AI image tools (Nano Banana, ChatGPT, ComfyUI, Midjourney) — 250+ poses × 5 angles in line art, names in ja/zh/en/ko
2026-10-30
wangweihong/comfyui-pose-gallery
B
ComfyUI 中文人体姿势图库节点，支持多视角浏览与 Depth Anything → MOSS SFT 深度控制工作流
2026-10-08
dntpi/ComfyUI-H3-Video-Upsampler
B
Upscale a finished MiniMax H3 clip in ComfyUI: H3 latent upscaler + one guided re-draw in tiles, with the h3upscale x2 LoRA (on Hugging Face).
2026-10-08
pixelsncodes/GesturePortal
B
A local gesture-controlled AI webcam portal built with MediaPipe and ComfyUI. Full-scene styling with Portrait v2, FLUX and Qwen.
2026-10-03
fth1905-bot/ComfyUI-Civitai-Browser
B
Browse Civitai workflows & models inside ComfyUI and get any workflow ready in one click: load it, find missing models and download them into the right folders.
2026-11-02
mankidev/codixel
C
Pixel art skill for Claude Code: how to make good pixel, animated game sprite out, effects etc.
2026-10-27
slmonker/ComfyUI-MOSS-Merge-Presets
C
Preset and per-layer Base+SFT merge node for MOSS-Image in ComfyUI.
2026-10-07
overflowofedge/ComfyUI-Qwen-Watermark
C
Local ComfyUI workflow for watermark, mosaic and irregular overlay removal with Qwen Image 2.1 and SAM
2026-09-20
Azure12355/weilanx-cover-skill
C
weilanx Cover Skill: generate Chinese social covers with multi-ratio layouts and consistent characters.
2026-09-13
maosika-ai/reshot
C
ReShot — copy the shot, not the actors. Video → depth map (monocular video depth estimation) for Seedance 2.0/2.5 reference video, MiniMax H3 Fun ControlNet and Wan VACE. Apache-2.0. Open-sourced by Maosika 猫斯卡 (www.maosika.com), the AI short-drama production system.
2026-08-28
newbmechanix-ship-it/ALPHA-T1
C
Single-pass MiniMax H3 image-to-video for ComfyUI (~166s/7s at 704x384 on one RTX 4060 Ti 16GB).
2026-10-08
T8mars/Comfyui-Prism-T8
C
Native Tencent Prism video/audio nodes for ComfyUI, with standalone INT8 ConvRot models and complete canvas workflows.
2026-10-01
TR-MZ/flux2-klein-alpha
C
RGBA VAE + extract/remove LoRAs for FLUX.2 Klein: Gradio demo and ai-toolkit patch
2026-09-27
shootthesound/ComfyUI-Fizgig-H3-Tweaks
C
Training-free tweaks for MiniMax H3 in ComfyUI: crisper or smoother skin, a sub-seed style scene re-roll, and a prompt-strength dial for CFG-free Turbo renders. One node, no extra models.
2026-09-17
liangdabiao/product-motion-gif
C
谁说AI不能生成GIF? 本skill利用GPT-Image 2.5 一次性生成多格帧图 - 合成为动画gif - 一次调用就生成动态图。产品动图生成器 > 你给我产品照片，我还你一段会自动循环播放的产品动图。 这个技能是给"不会用设计软件、但需要动图素材"的人用的。 你不需要懂任何技术，只要会发图片、会说话就够了。
2026-09-15
Work-Fisher/AIFISHER
C
AIFISHER 画布 · 2.0 起源：连接 AI 模型、ComfyUI 与 RunningHub 的本地创作画布。源码公开，仅限非商业用途，禁止接单与倒卖。
2026-09-08
huangbai-AI/ai-apple-video
C
Seedance 2.5 苹果发布会风格产品视频生成技能 — 把任意普通产品包装成高端消费电子产品，生成30秒苹果发布会风格AI视频。作者：靓仔 AI 进化论
2026-09-07
matsuo-koya/minimax-h3-notes
C
Measured speed-ups for MiniMax H3 on one RTX 5090 (ComfyUI): INT8 attention, FastH3 LoRA conversion, distributed segments, and what didn't work
2026-10-24
ATH-MaaS/PixText
C
Efficient Scene-Text Refinement via Pixel-Space Grouped Image Generation
2026-10-16
orylite/lindyson-ai
C
AI video & image generation workspace for e-commerce teams, built on Volcengine Seedance / Seedream, with MCP for ChatGPT & Codex · 面向电商团队的 AI 视频与图片生成工作台
2026-09-29
dr1610/imagechat-local
C
Qwen-Image 2.1対応のローカル画像生成・編集チャット。試用・評価用ベータ版。動作報告・不具合・改善案を歓迎し、可能な範囲で修正・更新します。モデル本体は含みません。
2026-09-21
joeynyc/spark-image-lab
C
Local image generation and editing for NVIDIA DGX Spark, powered by Qwen-Image-2.1 and Gradio.
2026-09-18
liobububu/agnes-manga-studio
C
Local-first AI manga drama production studio powered by Agnes-compatible APIs.
2026-08-27
GENEXIS-AI/gpt-image-skill
C
Generate GPT images from Codex or Claude Code using a ChatGPT subscription, without the Images API.
2026-08-27
Jalen-Brunson/ComfyUI-MiniMax-H3-PDD-Acc
C
Official MiniMax-H3 8-step PDD Acc LoRAs (alibaba-pai) in ComfyUI: LoRA + parallel-decoding head bank, euler on trained sigmas, audio+video in 8 steps
2026-08-23
pengfeiqiao/kunpeng
C
鲲鹏 Kunpeng — 跑在本地的中文 AIGC 创作工作台（Tauri + React + Rust，内嵌 DeepSeek Harness 引擎）
2026-11-05
silverdugongenhance/PromptReel
C
Free desktop app that turns a text prompt into a short video clip on your own PC. Local AI text-to-video with Wan 2.2: type a scene, pick wide, vertical or square, get an MP4. No credits, no subscription, no queue. Windows 10/11.
2026-10-26
LZ1226-OSS/infinite
C
款**零成本、本地运行**的 AI 短剧创作工具：用一块无限画布，把「剧本 → 分镜 → 图片 → 视频 → 成片」整条流水线做出来。支持接入你自己的大模型 API（DeepSeek / 智谱 / OpenAI 等），无需服务器、无需安装，双击即用。
2026-10-08
openhausfun/photocraft
C
Independent source snapshot of storytold/photocraft. Original MIT/Apache-2.0 licenses and attribution retained.
2026-10-05
pixelchemy-research/TRACE
C
[ACCV 2026] TRACE: Time-Adaptive Residual Attention Control with Content–Style Decomposition for Training-Free Diffusion Style Transfer
2026-10-04
lingdongbudong/Comfyui-Krea2-Portrait-V3
C
ComfyUI 自定义节点：摄影人物提示词随机生成器 · 纯本地 · 不用大模型 · 运行时零联网 · 63 池 949 条中文条目 + 2165 位角色 · 只生成提示词，不生成图片
2026-10-02
SatoDive/ComfyUI-H3-IMG-Gen-SatoDive
C
Simple ComfyUI nodes for MiniMax H3: exact output resolution, multi-reference images, single-pass generation, optional resolution-preserving detail refine.
2026-09-28
HaizhuAI/HaizhuVideo-H3Gateway
C
MiniMax H3 image-to-video gateway — OpenAI-compatible API + web studio
2026-09-21
benjiyaya/ComfyUI-Qwen-Image-2.1-Prompt-Enhancer
C
ComfyUI Custom Node for Qwen-Image-2.1 Prompt Enhancement , support T2I , Image Edit
2026-09-11
sepiablue-ai/ComfyUI-MiniMax-H3-W4A4-VSA
C
MiniMax H3 Ref2VA acceleration with FC1 ConvRot W4A4 and Streaming VSA for ComfyUI
2026-09-10
huangbai-AI/ai-motion-poster-skill
C
高端商业动态海报 Skill：写实三维物体 × 实验性排版，四幕分镜、物体驱动转场、准确文案与可复用提示词。
2026-09-10
lukasersil/gpt-images
C
A Claude skill that turns a plain brief into a production-ready prompt for OpenAI GPT Image models (ChatGPT Images 2.5): six-block prompts, the hard API limits, and edits that don't drift. MIT.
2026-09-14
JGRFW/comfyui-AICG3D
C
把 ComfyUI-MiniMaxH3-Easy 与 Goohai-MiniMax-H3_Integration 合并成一个统一的 MiniMax H3 创作工作台（非官方）
2026-08-29
MajoorWaldi/ComfyUI-Majoor-H3-GuideMaster
C
H3 GuideMaster makes it easy to place images and audio on a MiniMax H3 timeline.
2026-11-02
wangweihong/comfyui-hairstyle-gallery
C
ComfyUI offline hairstyle gallery: 893 mannequin hair references, bilingual UI and Qwen Image 2.1 workflows
2026-10-31
wzc520pyfm/gen-ai-pose-image
C
澜姿：从姿势线稿和衣装集给社区鲸鱼娘大肥鱼模特出图，调整姿势加变装，也可装进 DeepSeek Harness。Lanpose generates images of the community whale-girl Dafeiyu from pose sketches and costumes, and installs into DeepSeek Harness.
2026-10-30
op7418/malfoy-desktop
C
马尔福桌面：住着马尔福小姐的 AI 女友 / AI 陪伴桌面。斯莱特林休息室动态壁纸加互动剧情角色扮演，点她会回应，好感度解锁装扮和相册。用即梦 AI 短剧工作室制作，支持 macOS 和 Wallpaper Engine。Malfoy Desktop: an AI girlfriend and companion living wallpaper. Role-play with Miss Malfoy in the Slytherin common room. Noncommercial fan project.
2026-10-12
rossark0/duolingo-character-style-skill
C
Draw people in Duolingo's flat illustration style, a skill for Claude
2026-10-07
hypersniper05/MCP-Image-Generator-Uncensored
C
Self-hosted MCP server for image generation and editing with the uncensored Qwen-Image-2.1 model
2026-10-05
xianyu110/ecommerce-image-skills
C
12 电商出图 Agent Skills for Claude Code / Codex / Cursor · GPT Image 2.5 (Flare/Sunburst) · Amazon 白底主图, A+, 场景图, 模特图, 小红书封面, 淘宝详情页
2026-09-28
NidAll/comfyui-ming-image-prompt-builder
C
A visual, structured JSON prompt builder for Ming-Image-0.1-Design text-to-image workflows in ComfyUI.
2026-09-20
Technicalflight/image-prompt-reverse
C
把一张图片逆推成生成提示词（Image to Prompt）：中英双语重建提示词 + 风格标签 + 结构化 JSON prompt，零依赖校验脚本 | Forensic image-to-prompt reconstruction. AGPL-3.0 · Commercial use requires license.
2026-09-16
Prophetic-Helgy/gemini-mediagen-automatizator
C
Claude Code skill + reference scripts: generate images (Nano Banana Pro), video and music through your logged-in gemini.google.com browser session via CDP (browser-harness) — no API key
2026-09-02
FanYUJ1U/anime-editorial-poster-skill
C
A Codex skill for refined anime fashion-editorial posters with multi-reference control.
2026-09-02
wu529778790/freeimg.shenzjd.com
C
基于 Gitee AI 的免费 2K 图片生成器，每天可免费生成 100 张，无任何限制。内置 18000+ AI 提示词库与 12 种预设风格（公众号/小红书配图），Next.js 构建
2026-08-25
Straniero44/wenai
D
An intimate AI companion skill for OpenClaw — fall in love with your AI girlfriend, with a Pony V6 XL powered visual workflow.
2026-10-29
lingdongbudong/Comfyui-Anima-Wardrobe-V4
C
ComfyUI 自定义节点：ANIMA3 提示词随机生成器 · 五级 NSFW 档位闸门 · 三层权重 · 角色库 2383 位 + 场景搭配 261 条 · 纯本地零依赖 · 只生成提示词，不生成图片
2026-10-28
beyondtahir/beyondsumi
C
Cinematic Sumi storytelling for YouTube creators. Three art styles, SVG, narration, Python sound and HD video dashboards—without a video-generation API.
2026-10-11
nimblecloud13/ComfyUI-MiniMax-H3-Guide
D
Plain-English ComfyUI guides for MiniMax H3, Wan 2.2, Qwen Image 2.1 and Krea 2: what every part, file name and setting actually does.
2026-10-04
omnichar/ComfyUI-Omnichar
C
ComfyUI custom node for using .char. Exports refmode, lora adapters, guided prompts for your consistent character.
2026-09-30
TreapGoGo/deepseek-whale-girl
D
由社区共同维护的鲸鱼娘二创资源库，整理角色参考图、生成提示词、社区作品与相关项目，为创作者提供方便易用的参考与灵感。本项目为非官方社区项目，不代表 DeepSeek 官方立场。
2026-09-25
pottokao-dotcom/ComfyUI-QwenImage-PhotoStyles
C
ComfyUI node for Qwen-Image-2.1: 17 photographic styles (camera language + mood) via a PE-T2I prompt rewriter. Not a model loader.
2026-09-04
coolxxxx/video-prompt-reverse-engineer
C
Reverse-engineer reference videos into executable AI video prompts (Sora, Kling, Runway, Vidu, Pika, Seedance 2.0/2.5 native format)
2026-08-29
camilleroux/genart-skill
D
Generative art skill for Claude Code — deterministic, hash-seeded, onchain-ready
2026-10-22
kangarooking/design-skills
C
设计Skill：面向 AI 生图与视觉设计的开源 Agent Skills | Design Skills: Open-source Agent Skills for AI image creation and visual design.
2026-09-03
AntaresAlice/h3-webui
C
A self-hosted video-generation web UI built on ComfyUI + MiniMax-H3
2026-10-31
wangweihong/comfyui-costume-gallery
C
ComfyUI 中文服装图库节点：内置 1407 套服装原图与缩略图，支持搜索、分类和 Qwen Image 2.1 姿态换装流程
2026-10-20
slmonker/ComfyUI-MOSS-PromptEnhancer
C
Local GGUF prompt generation for MOSS-Image in ComfyUI, with Caption/Layout modes and Chinese text preservation.
2026-10-19
rakshazi/krea2-prompting
C
Krea 2 (Turbo) prompting skill with huge references library, including adult (the most tested section ;)
2026-10-14
nnkiirue99-maker/ai-companion-drawer
C
Drawer｜给 AI 伴侣一个悄悄留下便签和像素小画的抽屉。中文教程、流式隐藏、独立演示，MIT 开源。
2026-08-24
alchaincyf/huashu-gpt-image
C
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。
2026-10-16
q253595422/dsh-imagegen-video
C
DeepSeek Harness plugin: image + video generation studio with an infinite canvas. Fork of dickpy/dsh-imagegen with a complete video pipeline and clip stitching.
2026-10-01
daaihq/da-brand-ip-skill
C
Create reusable brand characters with 124 styles, three design assets, and multilingual documentation.
2026-09-15
inspoai-studio/inspoai-studio
C
Inspo AI Studio — AI UI generation grounded in 200K+ real product screens. Turn a prompt into production-ready React + Tailwind UI, convert HTML and designs to Figma, generate dashboards and landing pages, and search real UI, icon and typeface references.
2026-08-31
fajrisilmi12-cyber/hermes-socmed-function
C
Custom Hermes Agent skills: AI image generation (9Router) + multi-platform social media posting (Zernio + Cloudinary) + IG scheduling workflow
2026-08-27
Miint-Sunny/nai5-prompting
C
教 AI 写 NovelAI Diffusion V5 提示词的方法 skill：构思＋写法两件套，基于 2226 张实测图库 / 962 条真实提示词。Agent Skills 标准封装。
2026-08-24
jkf87/gjc-agy-skill
C
GJC(가재코드) 스킬 — Antigravity CLI(agy) 연동: 비전/OCR, 이미지 생성, print 모드 레시피. 실측 기반 함정 문서 포함
2026-10-30
paipiange/nvzhuang
C
1407 张 AI 女装参考图集与虚拟试穿网站，支持中英检索、OpenAI Images / Gemini / 豆包及自定义 Base URL、API Key、模型。https://github.com/paipiange/nvzhuang
2026-10-12
bardak971/afflatus
C
A self-hosted studio for pictures, videos and timelines, in front of your own ComfyUI.
2026-09-15
Shellishack/infinite-pokemon
C
A Pokémon-style adventure built with Codex, featuring AI-generated maps, NPCs, branching saves, and multiplayer. The adventure never ends.
2026-10-23
Work-Fisher/fisher-moss-prompt-expander
C
Expand ideas into detailed image prompts with a Chinese SKILL and ComfyUI templates.
2026-10-22
DECRUX9812/hermes-plugin-gameforge
C
Game development plugin for Hermes Agent: sound effects, music, NPC voices, pixel art, 3D models, Godot/Unity/Blender/Unreal, a playtester that actually plays the build, and one-click export.
2026-10-10
shianlab/m-type
C
M-TYPE 麦门人格档案：16 个复古透明角色 × 麦当劳 MCP × 可收藏的时光报告。Agent Skill · HTML / PNG · 模拟案例与完整素材。
2026-09-25
wildminder/awesome-qwen-image
C
Qwen-Image 2.1. Checkpoints, quants, prompt engines, LoRAs, and tooling