Fine-tuning a model is a laborious task, and testing its performance hundreds or thousands of times is exhausting.
Your support, even just a cup of coffee's worth, can help me make better content for you and release it faster.
☕https://ko-fi.com/albedobond
AlbedoBase XL (SFW&NSFW)
The refiner is unnecessary, and VAE is included.
Leaving the negative prompt blank is the way to achieve nice quality.
GOAL
Stable Diffusion XL has 6.6 billion parameters, which is about 6.6 times more than the SD v1.5 version. I believe that this is not just a number, but a number that can lead to a significant improvement in performance.
It has been a while since we realized that the overall performance of SD v1.5 has improved beyond imagination thanks to the explosive contributions of our community. Therefore, I am working on completing this AlbedoBase XL model in order to optimally reproduce the performance improvement that occurred in v1.5 in this XL version as well.
My goal is to directly test the performance of all Checkpoints and LoRAs that are publicly uploaded to Civitai, and merge only the resources that are judged to be optimal after passing through several filters. This will surpass the performance of image-generating AI of companies such as Midjourney.
As of now, AlbedoBase XL v0.4 has merged exactly 55 selected checkpoints and 138 LoRAs.
- The spec grid of the model can be downloaded through this link:
https://ko-fi.com/s/7ae29c7676
More details:
https://civitai.com/models/140737/albedobase-xl