| --- |
| license: apache-2.0 |
| base_model: stabilityai/stable-diffusion-xl-base-1.0 |
| tags: |
| - art |
| - t2i-adapter |
| - stable-diffusion |
| - image-to-image |
| --- |
| |
| # T2I Adapter - SDXL |
|
|
| T2I Adapter is a network providing additional conditioning to stable diffusion. Each t2i checkpoint takes a different type of conditioning as input and is used with a specific base stable diffusion checkpoint. |
|
|
| This checkpoint provides conditioning on sketches for the stable diffusion XL checkpoint. |
|
|
| ## The Original Recipe Drives SDXL. |
|
|
| | | SD-V1.4/1.5 | SD-XL | T2I-Adapter | T2I-Adapter-SDXL | |
| | --- | --- |--- |--- |--- | |
| | Parameters | 860M | 2.6B |77 M | 77 M | | |
|
|
| ## Examples and Comparison |
|
|
| - Keypoint-guided |
| <p align="center"> |
| <img src="https://huggingface.co/TencentARC/T2I-Adapter/resolve/main/assets_XL/g_pose2.png" height=520> |
| </p> |
|
|
| - Sketch-guided |
| <p align="center"> |
| <img src="https://huggingface.co/TencentARC/T2I-Adapter/resolve/main/assets_XL/g_sketch.PNG" height=520> |
| </p> |
|
|
| - Canny-guided |
| <p align="center"> |
| <img src="https://huggingface.co/TencentARC/T2I-Adapter/resolve/main/assets_XL/g_canny.png" height=520> |
| </p> |
