Creates a color palette of the provided image. It can be triggered on all models with the following prompt:
create a color palette for this imageCalifornia AB 2013 Training Data Disclosure
This LoRA was fine-tuned using visual data consisting entirely of synthetic still images. The training data may include copyrighted material owned by third parties. No training data was licensed or purchased. This LoRA is provided for non-commercial use only under the terms of its distribution.
The dataset consists of 57 image sets (114 images total). Each set was created by locating, downloading, or generating an image, then pairing it with an appropriate color palette. Some color palettes were provided alongside the original image, and others were generated for this dataset by utilizing existing Color Palette tools. Palette images were then manually modified as-appropriate in Affinity Designer 2. Dataset was compiled/created in 2026.
Image data was processed through standard resizing, cropping, normalization, and labeling steps. Synthetic images were included as part of the training dataset.
This model is intended for non-commercial, experimental, and educational use. Generated outputs may reflect copyrighted visual styles or themes associated with the underlying training data. Users are responsible for ensuring compliance with applicable copyright law, other intellectual property laws, and all other applicable laws.
Description
FAQ
Comments (8)
This is a really cool idea! Could a reverse be possible too, recoloring a picture based on a color palette?
Thank you! And this model isn’t capable, but it’s funny you should mention that; I actually made this model as a stepping stone for a synthetic dataset to train a model capable of doing exactly that. A Color Palette Apply model is in the works :)
@ReltivlyObjectv Oh that's awesome!
@kaileykk That reverse color palette idea is amazing
The Apply Color Palette model is now up!
I'd love to make it work with Qwen Edit 2511, but this Lora seems incompatible ? (the image generated is basically the input image with more saturated colors)
Unfortunately I believe the two are different enough that LoRAs don't work well between them and is a limitation of the model.
有配套使用的提取色盘和应用调色盘的工作流吗?





