|
|
|
--- |
|
license: creativeml-openrail-m |
|
base_model: recoilmex/ColorfulSSD-1B_v08 |
|
dataset: recoilme/colorful_s_1024 |
|
tags: |
|
- stable-diffusion-xl |
|
- stable-diffusion-xl-diffusers |
|
- text-to-image |
|
- diffusers |
|
inference: true |
|
--- |
|
|
|
# Text-to-image finetuning - recoilme/ColorfulSSD-1B_v09 |
|
|
|
This pipeline was finetuned from **/workspace/ColorfulSSD-1B_v08** on the **recoilme/colorful_s_1024** dataset. Below are some example images generated with the finetuned pipeline using the following prompt: beautiful woman and her elegant cat, hyper realistic, ambient lighting: |
|
|
|
![img_0](./image_0.png) |
|
![img_1](./image_1.png) |
|
![img_2](./image_2.png) |
|
![img_3](./image_3.png) |
|
|
|
|
|
![image/png](https://cdn-uploads.huggingface.co/production/uploads/63a2d82b528eba15b1392902/r75H1KTghBzu4-FM9OqP9.png) |
|
|
|
Special VAE used for training: madebyollin/sdxl-vae-fp16-fix. |
|
|