Hugging Face's logo

playgroundai
/
playground-v2-1024px-aesthetic

Text-to-Image
Diffusers
Safetensors
StableDiffusionXLPipeline
playground
Model card Files
xet
 Community
23

Could you disclose some model training details?

#8
by eeyrw - opened
Discussion
eeyrw

Such as batch size and steps for different resolution stage or other tricks.
keturn
•
edited Dec 8, 2023

I'd love to hear more as well! It's encouraging to see an independently-trained SDXL model. Knowing more about its training would help us know how to use it effectively.

  • What sorts of prompts was this trained on?
  • Do you always send the same prompt text to both of SDXL's text encoders?
  • Was it trained at different aspect ratios? How did you make use of SDXL's micro-conditioning fields, original_size, target_size, and crop_coords?
ehsanakh

Sorry, we're not planning to disclose our training recipe at this stage. Thanks for the questions though!
ehsanakh changed discussion status to closed

Sign up or log in to comment