ComfyTextures Unreal create-refine-upscale-edit texture chain

Unreal Engine editor plugin ComfyTextures captures viewport render passes of selected actors and runs them through a ComfyUI-orchestrated chain: a fast SDXL+LCM-LoRA pass creates a low-res draft texture, a slower SDXL base+refiner pass refines it, an inpainting workflow allows targeted edits, and a 4x-UltraSharp upscale finishes the result, which is applied back as a new material/texture on the actor.

Properties

family: draft-to-finish
modality: render capture -> image -> image -> image -> image
whyMultiModel: Distinct from baseline base-refiner-draft-to-finish (generic T2I draft/refine/upscale) and from StableGen because it operates purely on existing Unreal actor geometry via viewport-camera depth/canny ControlNet projection (no mesh-generation stage), and chains four separately-named modes (Create/Refine/Edit/Upscale) each backed by a distinct model or LoRA variant, wired directly into the UE material graph.
steps: [object Object], [object Object], [object Object] +1 more
controls: Actor/viewpoint selection in the UE editor, single or multi point-of-view projection, ControlNet weight (canny/depth), edit target (texture region vs whole object), workflow JSON is user-editable in ComfyUI
exampleStack: UE viewport capture -> depth/canny ControlNet -> SDXL+LCM Create -> SDXL Base+Refiner Refine -> SDXL inpaint Edit -> 4x-UltraSharp Upscale -> applied as UE material
useCases: [rapid environment art texturing directly inside the UE editor][iterative look-dev without leaving Unreal][targeted texture fixes on shipped game assets]
pitfalls: multi-viewpoint projection is explicitly marked work-in-progress in the plugin, so single-viewpoint consistency is the reliable path; needs 16GB+ VRAM recommended for SDXL workflows
source: ComfyTextures GitHub README

Provenance

Source: https://github.com/AlexanderDzhoganov/ComfyTextures

ComfyTextures Unreal create-refine-upscale-edit texture chain

Properties

family

draft-to-finish

modality

render capture -> image -> image -> image -> image

whyMultiModel

Distinct from baseline base-refiner-draft-to-finish (generic T2I draft/refine/upscale) and from StableGen because it operates purely on existing Unreal actor geometry via viewport-camera depth/canny ControlNet projection (no mesh-generation stage), and chains four separately-named modes (Create/Refine/Edit/Upscale) each backed by a distinct model or LoRA variant, wired directly into the UE material graph.

steps

[object Object], [object Object], [object Object] +1 more

controls

Actor/viewpoint selection in the UE editor, single or multi point-of-view projection, ControlNet weight (canny/depth), edit target (texture region vs whole object), workflow JSON is user-editable in ComfyUI

exampleStack

UE viewport capture -> depth/canny ControlNet -> SDXL+LCM Create -> SDXL Base+Refiner Refine -> SDXL inpaint Edit -> 4x-UltraSharp Upscale -> applied as UE material

useCases

[rapid environment art texturing directly inside the UE editor][iterative look-dev without leaving Unreal][targeted texture fixes on shipped game assets]

pitfalls

multi-viewpoint projection is explicitly marked work-in-progress in the plugin, so single-viewpoint consistency is the reliable path; needs 16GB+ VRAM recommended for SDXL workflows

source

ComfyTextures GitHub README