metadata

base_model: stabilityai/stable-diffusion-xl-base-1.0
library_name: diffusers
license: creativeml-openrail-m
tags:
  - stable-diffusion
  - template:sd-lora
  - text-to-image
  - diffusers
  - diffusers-training
  - conan
  - lora
widget:
  - text: >-
      surprised, dark-haired male character in suit; background with dim purple
      hue and visible door or entrance.
    output:
      url: gen_res/prompt1-lora1.png
  - text: >-
      surprised, dark-haired male character in suit; background with dim purple
      hue and visible door or entrance.
    output:
      url: gen_res/prompt1-lora2.png
  - text: >-
      surprised, dark-haired male character in suit; background with dim purple
      hue and visible door or entrance.
    output:
      url: gen_res/prompt1-lora3.png
  - text: >-
      surprised, dark-haired male character in suit; background with dim purple
      hue and visible door or entrance.
    output:
      url: gen_res/prompt1-lora4.png
  - text: >-
      young woman with dark hair and red top in foreground with man in glasses;
      background crowd with outdoor setting; vibrant color palette
    output:
      url: gen_res/prompt2-lora1.png
  - text: >-
      young woman with dark hair and red top in foreground with man in glasses;
      background crowd with outdoor setting; vibrant color palette
    output:
      url: gen_res/prompt2-lora2.png
  - text: >-
      young woman with dark hair and red top in foreground with man in glasses;
      background crowd with outdoor setting; vibrant color palette
    output:
      url: gen_res/prompt2-lora3.png
  - text: >-
      young woman with dark hair and red top in foreground with man in glasses;
      background crowd with outdoor setting; vibrant color palette
    output:
      url: gen_res/prompt2-lora4.png
inference: true

SDXL-Conan

Prompt
surprised, dark-haired male character in suit; background with dim purple hue and visible door or entrance.

Prompt
young woman with dark hair and red top in foreground with man in glasses; background crowd with outdoor setting; vibrant color palette

These are LoRA adaption weights for stabilityai/stable-diffusion-xl-base-1.0. The weights were fine-tuned on the jugg1024/conan-gpt4-captions dataset.

LoRA for the text encoder was enabled.

Special VAE used for training: madebyollin/sdxl-vae-fp16-fix

Intended uses & limitations

How to use

# TODO: add an example code snippet for running this diffusion pipeline

Limitations and bias

currently the text decoder is also add a lora-adapter. So the results may be a little bit overfitting, will be recover soon

Training details

[TODO: describe the data used to train the model]