erkam's picture
End of training
a4af27c
metadata
license: creativeml-openrail-m
base_model: stabilityai/stable-diffusion-2
tags:
  - stable-diffusion
  - stable-diffusion-diffusers
  - text-to-image
  - diffusers
  - lora
inference: true

LoRA text2image fine-tuning - https://huggingface.co/erkam/sd-clevr-scene-graph

These are LoRA adaption weights for https://huggingface.co/erkam/sd-clevr-scene-graph. The weights were fine-tuned on the erkam/clevr-with-depth dataset. You can find some example images in the following.

img_0 img_1 img_2 img_3