tags:
- text-to-image
- stable-diffusion
- lora
- diffusers
- template:sd-lora
widget:
- text: '-'
output:
url: images/dollx-00002.png
- text: '-'
output:
url: images/dollx-00004.png
- text: '-'
output:
url: images/dollx-00007.png
- text: '-'
output:
url: images/dollx-00009.png
- text: '-'
output:
url: images/dollx-00010.png
- text: '-'
output:
url: images/dollx-00013.png
- text: '-'
output:
url: images/dollx-00014.png
- text: '-'
output:
url: images/dollx-00017.png
base_model: stabilityai/stable-diffusion-xl-base-1.0
instance_prompt: xdlx style
license: artistic-2.0
Dollx Style
Model description
dollx style This Lora is trained on the style of AI artist @darkestdollx and creates a hyperwave type of image heavy in pinks and colorful spectrums with glitch and vaporwave vibes. It does not exactly reproduce their style and is intended as a fun tribute to their work. This LoRA was trained for 40 epochs using the prodigy optimizer on 24 images at 1280 x 1280 with a batch setting of 4 and a gradient accumulation of 6. This is different from my normal training settings of 4 x 2. Images were captioned with GPTV using my art captioning prompt and captions were manually edited for succinctness. Loss charts were different than I expected with the different training settings than I usually use. After reviewing test images i chose to share the final epoch 40. Images in the accompanying post were creating with comfy UI and the Proteus Run Diffusion model with the tempest model as a refiner stage.
Trigger words
You should use xdlx style
to trigger the image generation.
Download model
Weights for this model are available in Safetensors format.
Download them in the Files & versions tab.