artokun
Start here
SkillNo. 01Core ComfyUI knowledge covering workflow format, node typesComfyUI Core Knowledge
artokun/comfyui-mcp · by artokunCore ComfyUI knowledge covering workflow format, node types, pipeline patterns, and MCP tool usage★ 759 GitHub starsFree
SkillNo. 02Common ComfyUI errors and fixesComfyUI Troubleshooting Guideartokun/comfyui-mcp · by artokunCommon ComfyUI errors and fixes. OOM, missing nodes, dtype mismatches, black images, and debugging strategies★ 759 GitHub starsFree
SkillNo. 03Build Lightricks LTX-2 / LTX-2.3 video workflows coveringartokun/comfyui-mcp · by artokunBuild Lightricks LTX-2 / LTX-2.3 video workflows covering text-to-video, image-to-video, GGUF and bundled checkpoints, distilled model, camera control LoRAs, synchronize…★ 759 GitHub starsFreeSkillCore ComfyUI knowledge covering workflow format, node typesComfyUI Core Knowledgeartokun/comfyui-mcp · by artokunCore ComfyUI knowledge covering workflow format, node types, pipeline patterns, and MCP tool usage★ 759 GitHub starsFreeSkillCommon ComfyUI errors and fixesComfyUI Troubleshooting Guideartokun/comfyui-mcp · by artokunCommon ComfyUI errors and fixes. OOM, missing nodes, dtype mismatches, black images, and debugging strategies★ 759 GitHub starsFreeSkillBuild Lightricks LTX-2 / LTX-2.3 video workflows coveringartokun/comfyui-mcp · by artokunBuild Lightricks LTX-2 / LTX-2.3 video workflows covering text-to-video, image-to-video, GGUF and bundled checkpoints, distilled model, camera control LoRAs, synchronize…★ 759 GitHub starsFree
SkillFull production pipeline covering story to scenesDirector — Story-to-Video Production Pipelineartokun/comfyui-mcp · by artokunFull production pipeline covering story to scenes, Z-Image start frames, Qwen Edit end frames, WAN FLF video clips, ffmpeg concatenation★ 759 GitHub starsFree
SkillKeep the ComfyUI sidebar panel node-pack in stepKeep the panel node-pack in sync with the orchestratorartokun/comfyui-mcp · by artokunKeep the ComfyUI sidebar panel node-pack (comfyui-agent-panel) in step with the orchestrator after comfyui-mcp updates. Use this whenever the orchestrator was just updat…★ 759 GitHub starsFree
SkillExtend / continue a video temporally with Pusa 2.2Video Extension (Pusa 2.2 — temporal flowmatching)artokun/comfyui-mcp · by artokunExtend / continue a video temporally with Pusa 2.2 in ComfyUI. Temporal flowmatching (the flowmatch_pusa scheduler + WanVideoAddPusaNoise) on the WanVideoWrapper stack w…★ 759 GitHub starsFree
SkillInstall Triton + SageAttention to accelerate ComfyUITriton + SageAttention (ComfyUI acceleration)artokun/comfyui-mcp · by artokunInstall Triton + SageAttention to accelerate ComfyUI (the sageattn attention_mode and inductor torch.compile used by WanVideoWrapper / many video graphs). Windows-first…★ 759 GitHub starsFree
SkillBuild WAN 2.2 First-Last-Frame video workflowsWAN 2.2 First-Last-Frame (FLF) Video Workflowsartokun/comfyui-mcp · by artokunBuild WAN 2.2 First-Last-Frame video workflows. Native dual hi-lo (required), and WanVideoWrapper VACE approaches★ 759 GitHub starsFree
SkillBuild Qwen Image Edit workflows covering model loadingartokun/comfyui-mcp · by artokunBuild Qwen Image Edit workflows covering model loading, conditioning, LoRAs, prompt patterns, and XY plot testing★ 759 GitHub starsFree
SkillDiscover Civitai models with the BUILT-IN downloadmodelCivitai + comfyui-mcpartokun/comfyui-mcp · by artokunDiscover Civitai models with the BUILT-IN download_model action:"search_civitai" and install/generate them locally. Find a checkpoint/LoRA/embedding on Civitai, download…★ 759 GitHub starsFree
SkillLay out and organize a ComfyUI workflow cleanlyComfyUI Workflow Layout & Organizationartokun/comfyui-mcp · by artokunLay out and organize a ComfyUI workflow cleanly on the live panel canvas. Dependency-layered node placement with no overlaps, subgraphs, colored group boxes, and subgrap…★ 759 GitHub starsFree
SkillCurated download URLs and target directoriesModel registryartokun/comfyui-mcp · by artokunCurated download URLs and target directories, organized by family (Flux, WAN, LTX, Qwen, Z-Image, SD15/SDXL), for every model the comfyui-mcp skills reference, covering…★ 759 GitHub starsFree
SkillBuild Krea 2 Turbo txt2img workflows with the native krea2Krea 2 Text-to-Image Workflowsartokun/comfyui-mcp · by artokunBuild Krea 2 Turbo txt2img workflows with the native krea2 CLIPLoader, Qwen3-VL encoder, Qwen image VAE, 8-step turbo settings, and Ideogram-style JSON prompting★ 759 GitHub starsFree
SkillRun the ComfyUI agent locally for FREE with no subscriptionRun the agent locally for free (Ollama + our fine-tuned models)artokun/comfyui-mcp · by artokunRun the ComfyUI agent locally for FREE with no subscription, no API key, and fully offline, using our gemma4 models fine-tuned on the comfyui-mcp tool suite via Ollama.…★ 759 GitHub starsFree
SkillPick the right ComfyUI startup flags for VRAM, attentionComfyUI launch/performance flagsartokun/comfyui-mcp · by artokunPick the right ComfyUI startup flags for VRAM, attention, caching, and speed. The full decision matrix for OOM (--novram / --cache-none / --disable-smart-memory), shared…★ 759 GitHub starsFree
SkillBuild Baidu ERNIE-Image / ERNIE-Image-Turbo workflowsartokun/comfyui-mcp · by artokunBuild Baidu ERNIE-Image / ERNIE-Image-Turbo workflows, primarily TEXT-TO-IMAGE. Pick ERNIE when you need precise multilingual text rendering, posters/signage, manga/anim…★ 759 GitHub starsFree
SkillBuild Flux txt2img workflows with Flux.1 Dev Flux Text-to-Image Workflowsartokun/comfyui-mcp · by artokunBuild Flux txt2img workflows with Flux.1 Dev (SRPO), Flux 2 Klein 9B, Turbo LoRAs, FluxGuidance, and DualCLIPLoader patterns★ 759 GitHub starsFree
SkillDrive the LTX Director nodeLTX Director (Timeline)artokun/comfyui-mcp · by artokunDrive the LTX Director (Timeline) node. Its Add Image/Text/Audio buttons are DOM-only and cannot be clicked by an agent; edit the hidden timeline_data JSON widget instea…★ 759 GitHub starsFree
SkillUpscale and restore video in ComfyUIVideo Upscaling & Restorationartokun/comfyui-mcp · by artokunUpscale and restore video in ComfyUI. Both the quick local path (per-frame ESRGAN like 4x_foolhardy_Remacri via ImageUpscaleWithModel + 4x→2x supersample, with its tempo…★ 759 GitHub starsFree
SkillBuild Z-Image txt2img workflowsZ-Image Text-to-Image Workflowsartokun/comfyui-mcp · by artokunBuild Z-Image txt2img workflows. RedCraft checkpoint, Z-Image Turbo/Base LoRAs, ControlNet, and sampler presets★ 759 GitHub starsFree
SkillAnime/illustration text-to-imageANIMA 1.0 (Anima Base Ultra) Text-to-Image Workflowsartokun/comfyui-mcp · by artokunAnime/illustration text-to-image (ANIMA 1.0, ~2B Cosmos DiT). Use for anime, manga, illustrated characters; accepts Danbooru tags + natural language; runs/trains on <6GB…★ 759 GitHub starsFree
SkillAuthoring & Publishing ComfyUI Custom Nodesartokun/comfyui-mcp · by artokunAuthoring & publishing ComfyUI custom nodes to the Comfy Registry, covering node structure, pyproject.toml spec, comfy-cli publishing, and CI★ 759 GitHub starsFree
SkillDiagnose and fix video/image color OBJECTIVELYColor Correction (measure, don't eyeball)artokun/comfyui-mcp · by artokunDiagnose and fix video/image color OBJECTIVELY with the get_image (action:"analyze_color") tool (scopes/stats such as black/white points, contrast, saturation, clipping,…★ 759 GitHub starsFree
SkillModel family compatibility matrix covering loadersComfyUI Model Compatibility Matrixartokun/comfyui-mcp · by artokunModel family compatibility matrix covering loaders, resolutions, samplers, CFG, VAE, ControlNet, and LoRA compatibility for SD 1.5, SDXL, Flux, SD3, and video models★ 759 GitHub starsFree
SkillDebug a WRONG or imperfect render by inspecting inputsDebugging renders with run-to-nodeartokun/comfyui-mcp · by artokunDebug a WRONG or imperfect render (not a hard error) by inspecting inputs and intermediate steps with run-to-node. Render one branch up to an output, preview-tap latents…★ 759 GitHub starsFree
SkillBuild Ideogram 4 txt2img and img2img workflowsIdeogram 4 (Ideogram Ultra) Workflowsartokun/comfyui-mcp · by artokunBuild Ideogram 4 (Ideogram Ultra) txt2img and img2img workflows with the local open-weights model, dual conditional/unconditional models with DualModelGuider, Qwen3-VL t…★ 759 GitHub starsFree
SkillOn-demand procedures for the ComfyUI sidebar panel agentPanel agent operationsartokun/comfyui-mcp · by artokunOn-demand procedures for the ComfyUI sidebar panel agent that are too long to sit in the system prompt. Read it when a task lands in one of these areas. subgraph boundar…★ 759 GitHub starsFree
SkillBuild Qwen Image 2512 text-to-image workflowsartokun/comfyui-mcp · by artokunBuild Qwen Image 2512 text-to-image workflows with QwenImageIntegratedKSampler, separate component loading, lightning LoRAs, and fine-tuned model variants★ 759 GitHub starsFree
SkillConfigure and author rgthree-comfyartokun/comfyui-mcp · by artokunConfigure and author rgthree-comfy nodes — Fast Groups Bypasser/Muter (group toggles), Power Lora Loader, Context/Context Big, Seed, Any Switch. Use when a workflow cont…★ 759 GitHub starsFree
SkillTrain a character/identity LoRA locally on FLUX.1-devTrain a Character LoRA (local, Flux.1-dev)artokun/comfyui-mcp · by artokunTrain a character/identity LoRA locally on FLUX.1-dev via the comfyui-mcp train_* tools (GPU Docker + ostris ai-toolkit). Use when the user wants to train a LoRA of a pe…★ 759 GitHub starsFree
SkillBuild WAN 2.2 Text-to-Video workflowsWAN 2.2 Text-to-Video (T2V) Workflowsartokun/comfyui-mcp · by artokunBuild WAN 2.2 Text-to-Video workflows. Dual hi-lo models, lightning LoRAs, VACE modules, and KSamplerAdvanced two-pass★ 759 GitHub starsFree
SkillBuild WAN MultiTalk audio-driven talking-avatar / lip-syncartokun/comfyui-mcp · by artokunBuild WAN MultiTalk audio-driven talking-avatar / lip-sync video workflows. MeiGen-AI MultiTalk on WAN 2.1 14B I2V via kijai WanVideoWrapper (portrait + audio → lip-sync…★ 759 GitHub starsFree
SkillTrain custom LoRAs with ostris AI-ToolkitAI-Toolkit LoRA Trainer (WAN 2.2 & Z-Image)artokun/comfyui-mcp · by artokunTrain custom LoRAs with ostris AI-Toolkit. Covers WAN 2.2/2.1 (people, styles, video motion) and Z-Image (Turbo & Base, low-VRAM image LoRAs). Use when the user wants to…★ 759 GitHub starsFree
SkillTrain a custom anime LoRA on the ANIMA base modelCitron Anima LoRA Trainerartokun/comfyui-mcp · by artokunTrain a custom anime LoRA on the ANIMA base model with Citron's local Gradio trainer (kohya sd-scripts), <6GB VRAM, character/style LoRAs; covers setup, dataset prep, tr…★ 759 GitHub starsFree
SkillComfyUI prompt engineering knowledge covering CLIP textartokun/comfyui-mcp · by artokunComfyUI prompt engineering knowledge covering CLIP text encoding syntax, weight modifiers, model-specific prompting strategies, and best practices★ 759 GitHub starsFree
SkillAuthoring ComfyUI v2 frontend extensionsComfyUI v2 Frontend Extension APIartokun/comfyui-mcp · by artokunAuthoring ComfyUI v2 frontend extensions with @comfyorg/extension-api, covering defineNode/defineExtension/defineWidget, shell UI (sidebar tabs, commands, hotkeys), type…★ 759 GitHub starsFree
SkillAuthor ComfyUI-LoRA-Manager nodes from the panelartokun/comfyui-mcp · by artokunAuthor ComfyUI-LoRA-Manager nodes from the panel. Use when adding a LoRA Manager loader, stacker, prompt, or text node, or when panel_add_node refuses AUTOCOMPLETE_TEXT_…★ 759 GitHub starsFree
SkillInstalling a model family from an installer packInstaller packsartokun/comfyui-mcp · by artokunUse when installing a model family from an installer pack, or when building/deriving a new pack from an upstream installer or a workflow JSON. Explains the manifest-driv…★ 759 GitHub starsFree
SkillSwap an OUTFIT or transfer CLOTHING onto a person LOCALLYKrea 2 Identity Edit — local outfit swapartokun/comfyui-mcp · by artokunSwap an OUTFIT or transfer CLOTHING onto a person LOCALLY, keeping their face, pose and background. Use for "put this jacket on her", "change his shirt", "clothes swap",…★ 759 GitHub starsFree
SkillBuild MiniMax H3 local video workflows with nativeMiniMax H3 (Hailuo) — local videoartokun/comfyui-mcp · by artokunBuild MiniMax H3 (Hailuo) local video workflows with native T2V/I2V/R2V nodes, Comfy-Org INT8 weights, turbo LoRAs for 8GB VRAM, 15-second stereo-audio clips, and the of…★ 759 GitHub starsFree
SkillSCAIL-2 in-video character replacement on WAN 2.1SCAIL-2 In-Video Character Replacement (WAN 2.1)artokun/comfyui-mcp · by artokunSCAIL-2 in-video character replacement on WAN 2.1. WanSCAILToVideo + SCAIL2ColoredMask + SAM3, the reference-image framing→scale rule, and the tuning/compositing pitfalls★ 759 GitHub starsFree
MCPDiagnoses ComfyUI workflow failures by analyzing logsComfy debuggerartokun/comfyui-mcp · by artokunDiagnoses ComfyUI workflow failures by analyzing logs, history, and node definitions★ 759 GitHub starsFree
MCPExplores ComfyUI custom node packs and generates completeComfy explorerartokun/comfyui-mcp · by artokunExplores ComfyUI custom node packs and generates complete skills★ 759 GitHub starsFree
MCPAnalyzes ComfyUI workflows for performance issuesComfy optimizerartokun/comfyui-mcp · by artokunAnalyzes ComfyUI workflows for performance issues and suggests optimizations★ 759 GitHub starsFree