comfyui-image-gen

You automate multi-phase image generation pipelines in ComfyUI by orchestrating API calls with structured RenderSpec inputs. This manages drafting, refining, inpainting, and upscaling phases to produce reproducible image assets.

A RenderSpec is a structured input definition used to manage text-to-image workflows in ComfyUI. It defines reproducible generation parameters for multi-phase production loops, ensuring consistent results across multiple images.

Yes, you need ComfyUI API access to run custom workflows for ad-hoc image generation. The Skill executes direct API calls to process your custom workflow definitions and generate image outputs.

Yes, you maintain character consistency across multiple illustrations by defining structured RenderSpecs and running them through the draft, refine, and upscale pipeline. This ensures uniform style and character details across all outputs.

The best way to execute ad-hoc text-to-image generation is by running custom ComfyUI API workflows directly. This bypasses orchestrated pipelines, allowing immediate image generation from your scene inputs.

Yes, this approach supports inpainting and upscaling within automated generation loops. The orchestrated pipelines manage these phases alongside drafting and refining to produce final, high-resolution reproducible image assets.