|
|
|
--- |
|
tags: |
|
- stable-diffusion-xl |
|
- stable-diffusion-xl-diffusers |
|
- text-to-image |
|
- diffusers |
|
- lora |
|
- template:sd-lora |
|
|
|
base_model: stabilityai/stable-diffusion-xl-base-1.0 |
|
instance_prompt: a photo of TOK dog |
|
license: openrail++ |
|
--- |
|
|
|
# SDXL LoRA DreamBooth - mushroomfleet/XLcorgydog_testLoRA |
|
|
|
<Gallery /> |
|
|
|
## Model description |
|
|
|
For direct comparison with New Advanced Lora SDXL Dreambooth training method using paired Textual Inversion trained in parallel to the LoRa. |
|
|
|
https://huggingface.co/mushroomfleet/XLcorgydog_test2LoRA. |
|
|
|
Both models are trained with identical settings on A100, with the same exact dataset. |
|
possible variance in the latter half of captioning provided by BLIP at time of training. |
|
|
|
|
|
These are mushroomfleet/XLcorgydog_testLoRA LoRA adaption weights for stabilityai/stable-diffusion-xl-base-1.0. |
|
|
|
The weights were trained using [DreamBooth](https://dreambooth.github.io/). |
|
|
|
LoRA for the text encoder was enabled: False. |
|
|
|
Special VAE used for training: madebyollin/sdxl-vae-fp16-fix. |
|
|
|
## Trigger words |
|
|
|
You should use a photo of TOK dog to trigger the image generation. |
|
|
|
## Download model |
|
|
|
Weights for this model are available in Safetensors format. |
|
|
|
[Download](mushroomfleet/XLcorgydog_testLoRA/tree/main) them in the Files & versions tab. |
|
|
|
|
