| Property | Value |
|---|---|
| Base Model | black-forest-labs/FLUX.1-dev |
| License | CreativeML OpenRAIL-M |
| Network Dimensions | 64 |
| Optimal Resolution | 1024x1024 |
What is Coloring-Book-Flux-LoRA?
Coloring-Book-Flux-LoRA is a specialized LoRA model trained on the FLUX.1-dev base model, designed to generate black and white coloring book-style images. The model was trained on 10 high-resolution images using specific parameters including AdamW optimizer and constant learning rate scheduler, with a network alpha of 32.
Implementation Details
The model leverages advanced training parameters including a noise offset of 0.03 and multires noise iterations of 10. It requires the trigger word "Coloring Book" to generate images and operates optimally at 1024x1024 resolution.
- Trained with florence2-en labeling for natural language processing
- Utilizes constant learning rate scheduler with AdamW optimizer
- Features 10 epochs with saves every epoch
- Implements multires noise discount of 0.1
Core Capabilities
- Generation of detailed black and white line art
- Creation of sketch-style illustrations
- Ability to render complex scenes with architectural elements
- Support for various subjects including vehicles, animals, and landscapes
Frequently Asked Questions
Q: What makes this model unique?
This model specializes in creating coloring book-style images with clear line work and detailed compositions, utilizing a carefully tuned LoRA architecture with the FLUX.1-dev base model.
Q: What are the recommended use cases?
The model is ideal for creating coloring book pages, black and white illustrations, and sketch-style artwork. It's particularly suited for educational materials, children's activity books, and artistic projects requiring line art.