comfy

Parameter sweep generation across multiple values

Diff two ComfyUI workflows to see what changed

Convert between ComfyUI UI format and API format workflows

Diagnose why a ComfyUI workflow failed

Direct a short film from a story — generates scenes, frames, and video clips

Browse and inspect generated ComfyUI outputs

Generate an image with ComfyUI from a text prompt

Install a ComfyUI custom node pack

Generate a Claude skill for a ComfyUI custom node pack

Run a multi-step generation recipe (portrait, hires-fix, style-transfer, etc.)

Visualize a ComfyUI workflow as a mermaid diagram

Diagnoses ComfyUI workflow failures by analyzing logs, history, and node definitions

Explores ComfyUI custom node packs and generates comprehensive skills

Analyzes ComfyUI workflows for performance issues and suggests optimizations

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

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

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

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

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

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

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

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

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

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

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

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

3 hooks across 2 events