← All creators

artokun

User

Claude Code plugin + MCP server for ComfyUI — 88 tools, 14 AI skills (Flux, WAN, LTX video, Qwen), live graph editing from your Claude session. Generate images & video, manage models and custom nodes.

16 indexed · 0 Featured · 160 stars · avg score 89
Prolific

Categories

Indexed Skills (16)

AI & Automation Solid

comfyui-core

Core ComfyUI knowledge — workflow format, node types, pipeline patterns, and MCP tool usage

160 Updated today
artokun
AI & Automation Solid

director

Full production pipeline — story to scenes, Z-Image start frames, Qwen Edit end frames, WAN FLF video clips, ffmpeg concatenation

160 Updated today
artokun
AI & Automation Solid

flux-txt2img

Build Flux txt2img workflows — Flux.1 Dev (SRPO), Flux 2 Klein 9B, Turbo LoRAs, FluxGuidance, and DualCLIPLoader patterns

160 Updated today
artokun
AI & Automation Solid

ltxv2-video

Build LTX-V2 19B video workflows — text-to-video, image-to-video, distilled model, camera control LoRAs, and two-stage upscaling

160 Updated today
artokun
AI & Automation Solid

model-compatibility

Model family compatibility matrix — loaders, resolutions, samplers, CFG, VAE, ControlNet, and LoRA compatibility for SD 1.5, SDXL, Flux, SD3, and video models

160 Updated today
artokun
AI & Automation Solid

prompt-engineering

ComfyUI prompt engineering knowledge — CLIP text encoding syntax, weight modifiers, model-specific prompting strategies, and best practices

160 Updated today
artokun
AI & Automation Solid

qwen-image-edit

Build Qwen Image Edit workflows — model loading, conditioning, LoRAs, prompt patterns, and XY plot testing

160 Updated today
artokun
AI & Automation Solid

qwen-txt2img

Build Qwen Image 2512 text-to-image workflows — QwenImageIntegratedKSampler, separate component loading, lightning LoRAs, and fine-tuned model variants

160 Updated today
artokun
AI & Automation Solid

troubleshooting

Common ComfyUI errors and fixes — OOM, missing nodes, dtype mismatches, black images, and debugging strategies

160 Updated today
artokun
AI & Automation Solid

wan-flf-video

Build WAN 2.2 First-Last-Frame video workflows — native dual hi-lo (required), and WanVideoWrapper VACE approaches

160 Updated today
artokun
AI & Automation Solid

wan-t2v-video

Build WAN 2.2 Text-to-Video workflows — dual hi-lo models, lightning LoRAs, VACE modules, and KSamplerAdvanced two-pass

160 Updated today
artokun
AI & Automation Solid

z-image-txt2img

Build Z-Image txt2img workflows — RedCraft checkpoint, Z-Image Turbo/Base LoRAs, ControlNet, and sampler presets

160 Updated today
artokun
AI & Automation Solid

civitai

Pair the official Civitai MCP (https://mcp.civitai.com/mcp) with comfyui-mcp to discover models on Civitai and install/generate them locally. Use when the user wants to find a checkpoint/LoRA/embedding on Civitai, browse Civitai images for inspiration, or download a Civitai model into their ComfyUI. comfyui-mcp does NOT proxy Civitai — it hands version ids to the local download/wire/generate loop.

160 Updated today
artokun
Web & Frontend Solid

comfyui-frontend-extensions

Authoring ComfyUI v2 frontend extensions with @comfyorg/extension-api — defineNode/defineExtension/defineWidget, shell UI (sidebar tabs, commands, hotkeys), typed events, and handles. Use when writing or editing ComfyUI web-UI extension code (custom node JS, sidebar panels, widgets).

160 Updated today
artokun
AI & Automation Solid

comfyui-node-registry

Authoring & publishing ComfyUI custom nodes to the Comfy Registry — node structure, pyproject.toml spec, comfy-cli publishing, and CI

160 Updated today
artokun
AI & Automation Solid

model-registry

Curated download URLs and target directories for every model the comfyui-mcp skills reference — checkpoints, VAEs, text encoders, LoRAs — organized by family (Flux, WAN, LTX, Qwen, Z-Image, SD15/SDXL). Use when downloading models with download_model / download_civitai_model, when a workflow fails with a missing-model error, or when setting up a new machine.

160 Updated today
artokun

Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.