T2I-Adapter Lineart SDXL
| Property | Value |
|---|---|
| Parameter Count | 77M |
| Base Model | Stable Diffusion XL 1.0 |
| License | Apache 2.0 |
| Paper | arXiv:2302.08453 |
What is t2i-adapter-lineart-sdxl-1.0?
T2I-Adapter Lineart SDXL is an innovative adapter network developed by TencentARC that enhances Stable Diffusion XL's capabilities by providing additional conditioning through lineart detection. This model specializes in transforming line art inputs into detailed, high-quality images while maintaining precise control over the generation process.
Implementation Details
The model is implemented as a lightweight adapter network with 77M parameters that works alongside the much larger SDXL base model (2.6B parameters). It was trained on 3M high-resolution image-text pairs from LAION-Aesthetics V2, using a constant learning rate of 1e-5 and mixed precision training.
- Training Steps: 20,000
- Batch Size: 256 (16 per GPU)
- Architecture: T2I-Adapter framework
- Input Format: Monochrome lineart images
Core Capabilities
- Lineart-guided image generation
- High-resolution output support
- Seamless integration with SDXL
- Precise control over image generation through line art input
Frequently Asked Questions
Q: What makes this model unique?
This model is specifically designed for lineart-based image generation with SDXL, offering a lightweight solution for controlled image generation while maintaining the high-quality output capabilities of SDXL.
Q: What are the recommended use cases?
The model excels at converting line drawings into detailed images, making it ideal for artists, designers, and creators who want to transform sketches into fully rendered images. It's particularly useful for concept art development, character design, and artistic visualization.
