- ReferenceChainConditioning: Takes multiple images via UI, scales them, VAE encodes, and chains as reference latents into single conditioning - ReferenceChainConditioningBase64: Same functionality but accepts base64-encoded images for API usage Features: - Custom image list widget with drag-and-drop support - ComfyUI-native styling - Configurable scaling (megapixels) and upscale method - Outputs first scaled image for preview/further processing Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
16 lines
606 B
TOML
16 lines
606 B
TOML
[project]
|
|
name = "comfyui-referencechain"
|
|
description = "A ComfyUI node that takes multiple images, scales them, VAE encodes them, and chains them as reference latents into a single conditioning output. Useful for edit models like Flux-2-klein that accept multiple reference images."
|
|
version = "1.0.0"
|
|
license = {text = "MIT"}
|
|
dependencies = []
|
|
|
|
[project.urls]
|
|
Repository = "https://github.com/remingtonspaz/ComfyUI-ReferenceChain"
|
|
# Used by Comfy Registry https://comfyregistry.org
|
|
|
|
[tool.comfy]
|
|
PublisherId = "remingtonspaz"
|
|
DisplayName = "ComfyUI-ReferenceChain"
|
|
# Icon = "https://example.com/icon.png"
|