artokun/comfyui-mcp

artokun/comfyui-mcp · plugin/skills/ai-toolkit-trainer/SKILL.md · Train custom LoRAs with ostris AI-Toolkit. Covers WAN 2.2/2.1 (people, styles, video motion) and Z-Image (Turbo & Base…

artokun/comfyui-mcp · plugin/skills/anima-base/SKILL.md · Anime/illustration text-to-image (ANIMA 1.0, ~2B Cosmos DiT). Use for anime, manga, illustrated characters; accepts…

artokun/comfyui-mcp · plugin/skills/anima-lora-trainer/SKILL.md · Train a custom anime LoRA on the ANIMA base model with Citron's local Gradio trainer (kohya sd-scripts), <6GB VRAM…

artokun/comfyui-mcp · plugin/skills/civitai/SKILL.md · Discover Civitai models with the BUILT-IN download_model action:"search_civitai" and install/generate them locally…

artokun/comfyui-mcp · plugin/skills/color-correction/SKILL.md · Diagnose and fix video/image color OBJECTIVELY with the get_image (action:"analyze_color") tool (scopes/stats such as…

artokun/comfyui-mcp · plugin/skills/comfyui-core/SKILL.md · Core ComfyUI knowledge covering workflow format, node types, pipeline patterns, and MCP tool usage

artokun/comfyui-mcp · plugin/skills/comfyui-frontend-extensions/SKILL.md · Authoring ComfyUI v2 frontend extensions with @comfyorg/extension-api, covering…

artokun/comfyui-mcp · plugin/skills/comfyui-launch-flags/SKILL.md · Pick the right ComfyUI startup flags for VRAM, attention, caching, and speed. The full decision matrix for OOM…

artokun/comfyui-mcp · plugin/skills/comfyui-node-registry/SKILL.md · Authoring & publishing ComfyUI custom nodes to the Comfy Registry, covering node structure, pyproject.toml spec…

artokun/comfyui-mcp · plugin/skills/debug-render/SKILL.md · Debug a WRONG or imperfect render (not a hard error) by inspecting inputs and intermediate steps with run-to-node…

artokun/comfyui-mcp · plugin/skills/director/SKILL.md · Full production pipeline covering story to scenes, Z-Image start frames, Qwen Edit end frames, WAN FLF video clips…

artokun/comfyui-mcp · plugin/skills/ernie-image/SKILL.md · Build Baidu ERNIE-Image / ERNIE-Image-Turbo workflows, primarily TEXT-TO-IMAGE. Pick ERNIE when you need precise…

artokun/comfyui-mcp · plugin/skills/flux-txt2img/SKILL.md · Build Flux txt2img workflows with Flux.1 Dev (SRPO), Flux 2 Klein 9B, Turbo LoRAs, FluxGuidance, and DualCLIPLoader…

artokun/comfyui-mcp · plugin/skills/ideogram-ultra/SKILL.md · Build Ideogram 4 (Ideogram Ultra) txt2img and img2img workflows with the local open-weights model, dual…

artokun/comfyui-mcp · plugin/skills/installer-packs/SKILL.md · Use when installing a model family from an installer pack, or when building/deriving a new pack from an upstream…

artokun/comfyui-mcp · plugin/skills/krea2-identity-edit/SKILL.md · Swap an OUTFIT or transfer CLOTHING onto a person LOCALLY, keeping their face, pose and background. Use for "put this…

artokun/comfyui-mcp · plugin/skills/krea2-txt2img/SKILL.md · Build Krea 2 Turbo txt2img workflows with the native krea2 CLIPLoader, Qwen3-VL encoder, Qwen image VAE, 8-step turbo…

artokun/comfyui-mcp · plugin/skills/local-llm-free/SKILL.md · Run the ComfyUI agent locally for FREE with no subscription, no API key, and fully offline, using our gemma4 models…

artokun/comfyui-mcp · plugin/skills/lora-manager/SKILL.md · Author ComfyUI-LoRA-Manager nodes from the panel. Use when adding a LoRA Manager loader, stacker, prompt, or text node…

artokun/comfyui-mcp · plugin/skills/ltx-director/SKILL.md · Drive the LTX Director (Timeline) node. Its Add Image/Text/Audio buttons are DOM-only and cannot be clicked by an…

artokun/comfyui-mcp · plugin/skills/ltxv2-video/SKILL.md · Build Lightricks LTX-2 / LTX-2.3 video workflows covering text-to-video, image-to-video, GGUF and bundled checkpoints…

artokun/comfyui-mcp · plugin/skills/minimax-h3-video/SKILL.md · Build MiniMax H3 (Hailuo) local video workflows with native T2V/I2V/R2V nodes, Comfy-Org INT8 weights, turbo LoRAs for…

artokun/comfyui-mcp · plugin/skills/model-compatibility/SKILL.md · Model family compatibility matrix covering loaders, resolutions, samplers, CFG, VAE, ControlNet, and LoRA compatibility…

artokun/comfyui-mcp · plugin/skills/model-registry/SKILL.md · Curated download URLs and target directories, organized by family (Flux, WAN, LTX, Qwen, Z-Image, SD15/SDXL), for every…

artokun/comfyui-mcp · plugin/skills/panel-node-pack-sync/SKILL.md · Keep the ComfyUI sidebar panel node-pack (comfyui-agent-panel) in step with the orchestrator after comfyui-mcp updates…

artokun/comfyui-mcp · plugin/skills/panel-operations/SKILL.md · On-demand procedures for the ComfyUI sidebar panel agent that are too long to sit in the system prompt. Read it when a…

artokun/comfyui-mcp · plugin/skills/prompt-engineering/SKILL.md · ComfyUI prompt engineering knowledge covering CLIP text encoding syntax, weight modifiers, model-specific prompting…

artokun/comfyui-mcp · plugin/skills/qwen-image-edit/SKILL.md · Build Qwen Image Edit workflows covering model loading, conditioning, LoRAs, prompt patterns, and XY plot testing

artokun/comfyui-mcp · plugin/skills/qwen-txt2img/SKILL.md · Build Qwen Image 2512 text-to-image workflows with QwenImageIntegratedKSampler, separate component loading, lightning…

artokun/comfyui-mcp · plugin/skills/report-bug/SKILL.md · Issue reporting is disabled during limited maintenance of comfyui-mcp and the local Agent Panel. When the user hits a…

artokun/comfyui-mcp · plugin/skills/rgthree/SKILL.md · Configure and author rgthree-comfy nodes — Fast Groups Bypasser/Muter (group toggles), Power Lora Loader…

artokun/comfyui-mcp · plugin/skills/train-character-lora/SKILL.md · Train a character/identity LoRA locally on FLUX.1-dev via the comfyui-mcp train_* tools (GPU Docker + ostris…

artokun/comfyui-mcp · plugin/skills/triton-sageattention/SKILL.md · Install Triton + SageAttention to accelerate ComfyUI (the sageattn attention_mode and inductor torch.compile used by…

artokun/comfyui-mcp · plugin/skills/troubleshooting/SKILL.md · Common ComfyUI errors and fixes. OOM, missing nodes, dtype mismatches, black images, and debugging strategies

artokun/comfyui-mcp · plugin/skills/video-extend/SKILL.md · Extend / continue a video temporally with Pusa 2.2 in ComfyUI. Temporal flowmatching (the flowmatch_pusa scheduler +…

artokun/comfyui-mcp · plugin/skills/video-upscale/SKILL.md · Upscale and restore video in ComfyUI. Both the quick local path (per-frame ESRGAN like 4x_foolhardy_Remacri via…

artokun/comfyui-mcp · plugin/skills/wan-flf-video/SKILL.md · Build WAN 2.2 First-Last-Frame video workflows. Native dual hi-lo (required), and WanVideoWrapper VACE approaches

artokun/comfyui-mcp · plugin/skills/wan-multitalk/SKILL.md · Build WAN MultiTalk audio-driven talking-avatar / lip-sync video workflows. MeiGen-AI MultiTalk on WAN 2.1 14B I2V via…

artokun/comfyui-mcp · plugin/skills/wan-scail-replacement/SKILL.md · SCAIL-2 in-video character replacement on WAN 2.1. WanSCAILToVideo + SCAIL2ColoredMask + SAM3, the reference-image…

artokun/comfyui-mcp · plugin/skills/wan-t2v-video/SKILL.md · Build WAN 2.2 Text-to-Video workflows. Dual hi-lo models, lightning LoRAs, VACE modules, and KSamplerAdvanced two-pass

artokun/comfyui-mcp · plugin/skills/workflow-layout/SKILL.md · Lay out and organize a ComfyUI workflow cleanly on the live panel canvas. Dependency-layered node placement with no…

artokun/comfyui-mcp · plugin/skills/z-image-txt2img/SKILL.md · Build Z-Image txt2img workflows. RedCraft checkpoint, Z-Image Turbo/Base LoRAs, ControlNet, and sampler presets