102 skills · sorted by relevance
窓際族物語の動画をクラウドを使わずフルローカルで生成するワークフロー（MiniMax H3 + ComfyUI）。ユーザーから「ローカルで動画作成して」「ローカルLLMで動画を作って」と指示されたとき、MiniMax H3での動画生成・修正を頼まれたときに必ず使用する。台本→Irodori-TTS/VOICEVOX音声→draw-things-cliキーフレーム一括生成→Qwen3-VL（Ollama）による画像検証→チャプター毎のH3動画生成→ffmpeg結合まで全工程をローカルで完結させる。
The English summary is being prepared. Showing the original description.
Runs image, video and audio generation on a local ComfyUI server and guards the GPU before long renders. Trigger to generate an image, video, audio or music locally; to run, test or check a ComfyUI workflow before a long or queued render; when a video render crashed the machine, ran out of memory or hung in VAE decode; to render while LM Studio holds the GPU; to run a pixelsmith brief locally; or say comfyrunner (audit, check, test, run, status). Refuses an untiled video decode and scores resolution times frames. Briefs and judging art are pixelsmith's; sound briefs soundsmith's; freeing LM Studio lmstudiorunner's; schedules agentwright's.
The English summary is being prepared. Showing the original description.
Generate images, video, and audio with ComfyUI — install, launch, manage nodes/models, run workflows with parameter injection. Uses the official comfy-cli for lifecycle and direct REST/WebSocket API for execution.
The English summary is being prepared. Showing the original description.
Use when a task involves creating or editing a Scenario workflow graph through MCP: building an app from a brief, adding or rewiring nodes (models, prompts, approval gates, loops), authoring editor_info, publishing, unpublishing or renaming, importing an exported workflow JSON, migrating a graph built in Weavy, ComfyUI, or another node tool, copying a workflow, or turning a prompt chain into an app. Running or pricing a workflow is scenario-workflows. Keywords: node graph, editor_info, CEL.
The English summary is being prepared. Showing the original description.
Swap 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", "try on", "outfit transfer", "virtual try-on", "dress her in", "wear this outfit". Prefer this over API/cloud edit nodes and over generic img2img/inpainting. NOT for identity-preserving edits that are not about clothing (background swaps, relighting, age/expression changes, object removal). Use a general image-edit workflow for those.
The English summary is being prepared. Showing the original description.
Build 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 official MiniMax prompting guides (cite by link, do not copy).
The English summary is being prepared. Showing the original description.
Build Ideogram 4 (Ideogram Ultra) txt2img and img2img workflows with the local open-weights model, dual conditional/unconditional models with DualModelGuider, Qwen3-VL text encoder, and structured JSON ("compositional deconstruction") prompts for strong text rendering and layout control
The English summary is being prepared. Showing the original description.
Build Flux txt2img workflows with Flux.1 Dev (SRPO), Flux 2 Klein 9B, Turbo LoRAs, FluxGuidance, and DualCLIPLoader patterns
The English summary is being prepared. Showing the original description.
Use 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-driven packs/ system and tells you to invite the user to contribute new packs back upstream.
The English summary is being prepared. Showing the original description.
Build Lightricks LTX-2 / LTX-2.3 video workflows covering text-to-video, image-to-video, GGUF and bundled checkpoints, distilled model, camera control LoRAs, synchronized audio, two-stage upscaling, and swapping alternate/GGUF base models
The English summary is being prepared. Showing the original description.
Drive 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 instead. Load when a workflow contains LTXDirector / LTXDirectorGuide / PromptRelayEncodeTimeline, or when asked to add, move, retime, or remove timeline segments (image / text / audio / motion).
The English summary is being prepared. Showing the original description.
Build Qwen Image Edit workflows covering model loading, conditioning, LoRAs, prompt patterns, and XY plot testing
The English summary is being prepared. Showing the original description.
Build Qwen Image 2512 text-to-image workflows with QwenImageIntegratedKSampler, separate component loading, lightning LoRAs, and fine-tuned model variants
The English summary is being prepared. Showing the original description.
Build 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
The English summary is being prepared. Showing the original description.
Model family compatibility matrix covering loaders, resolutions, samplers, CFG, VAE, ControlNet, and LoRA compatibility for SD 1.5, SDXL, Flux, SD3, and video models
The English summary is being prepared. Showing the original description.
Build Baidu ERNIE-Image / ERNIE-Image-Turbo workflows, primarily TEXT-TO-IMAGE. Pick ERNIE when you need precise multilingual text rendering, posters/signage, manga/anime multi-panel layouts, or strong instruction following for complex multi-object scenes. Also supports denoise-based image-to-image refine (NOT instruction-grounded editing; use Qwen-Image-Edit or Flux Kontext for "change X in this photo" edits).
The English summary is being prepared. Showing the original description.
Full production pipeline covering story to scenes, Z-Image start frames, Qwen Edit end frames, WAN FLF video clips, ffmpeg concatenation
The English summary is being prepared. Showing the original description.
Debug 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/masks/preprocessor maps, localize the first bad stage, then fix. Use when a final image/video completes but looks wrong, such as artifacts, wrong subject/pose/composition/color, blur, a ControlNet/IPAdapter/mask/LoRA not taking, or a two-stage refiner or upscale degrading the result. For errors/OOM/missing nodes use the troubleshooting skill.
The English summary is being prepared. Showing the original description.
Build WAN 2.2 First-Last-Frame video workflows. Native dual hi-lo (required), and WanVideoWrapper VACE approaches
The English summary is being prepared. Showing the original description.
Build 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-synced video)
The English summary is being prepared. Showing the original description.
SCAIL-2 in-video character replacement on WAN 2.1. WanSCAILToVideo + SCAIL2ColoredMask + SAM3, the reference-image framing→scale rule, and the tuning/compositing pitfalls
The English summary is being prepared. Showing the original description.
Anime/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 VRAM; includes anime inpainting via Anima-LLLite ControlNet
The English summary is being prepared. Showing the original description.
Build WAN 2.2 Text-to-Video workflows. Dual hi-lo models, lightning LoRAs, VACE modules, and KSamplerAdvanced two-pass
The English summary is being prepared. Showing the original description.
Diagnose and fix video/image color OBJECTIVELY with the get_image (action:"analyze_color") tool (scopes/stats such as black/white points, contrast, saturation, clipping, cast) instead of eyeballing a contact sheet. Covers the "washed out" signature, why reference color-match (mkl/ColorMatch/ColorMatchAdobe) CAN'T add contrast a flat source lacks, the levels/contrast-stretch fix (core AdjustContrast / CurveEditor), the measure→fix→re-measure loop, the side-by-side sandbox pattern, and where to place the fix in a render graph (after decode, before save). Use when a render looks washed out / flat / dull / over-saturated / color-cast, or when deciding between a color-match and a contrast/levels fix.
The English summary is being prepared. Showing the original description.