Flux.1-Dev-Sketch-Card-LoRA
| Property | Value |
|---|---|
| Base Model | black-forest-labs/FLUX.1-dev |
| License | CreativeML OpenRAIL-M |
| Training Images | 13 |
| Network Dimensions | 64 |
| Optimal Dimensions | 768 x 1024, 1024 x 1024 |
What is Flux.1-Dev-Sketch-Card-LoRA?
Flux.1-Dev-Sketch-Card-LoRA is a specialized LoRA model designed for generating sketch card images. Built by prithivMLmods, this model is currently in the training phase and is optimized for creating detailed cartoon-style illustrations on card-like surfaces. It leverages the FLUX.1-dev base model with specific training parameters to achieve its unique artistic output.
Implementation Details
The model implements a constant learning rate scheduler with AdamW optimizer, featuring a network dimension of 64 and alpha of 32. Training was conducted over 16 epochs with a noise offset of 0.03 and multires noise iterations of 10. The model uses florence2-en for natural language processing in English.
- Network Architecture: 64 dimensions with 32 alpha
- Training Configuration: 16 epochs with 1990 steps
- Optimization: AdamW with constant learning rate
- Noise Parameters: 0.03 offset, 0.1 discount
Core Capabilities
- Generation of detailed sketch card illustrations
- Optimal performance at 768x1024 resolution
- Cartoon-style character rendering
- Hand-held card perspective generation
Frequently Asked Questions
Q: What makes this model unique?
The model specializes in creating sketch card images with a specific trigger word "sketch card", trained on a carefully curated dataset of 13 images. It's particularly effective at rendering cartoon characters on card-like surfaces with hand-held perspectives.
Q: What are the recommended use cases?
This model is ideal for creating illustrated cards featuring cartoon characters, trading card mockups, and artistic sketch presentations. It works best with the specified dimensions of 768x1024 or 1024x1024.
