Motivation: SDXL is a great model, especially for fine-tuning, but fine-tuning on SDXL's standard size is expensive, so i made a model which can generate images of 256x256px size. It allows faster and cheaper training experimentation and can improve a creative process through much faster inference time.

inspiration

Huuuuge thanks to Microsoft for providing GPU for training ❤️

Trained on LAION Improved Aesthetics 6plus.

Want to collaborate on open source together with me? Send me a message: [email protected] / telegram @kopyl

Check my other cool projects:

Check some cool images i was able to generate with this model. image/jpeg image/jpeg image/jpeg image/jpeg image/jpeg image/jpeg image/jpeg

Downloads last month
32
Inference Providers NEW
This model is not currently available via any of the supported third-party Inference Providers, and the model is not deployed on the HF Inference API.

Model tree for kopyl/miniSDXL

Finetuned
(1114)
this model

Space using kopyl/miniSDXL 1