|
--- |
|
tags: |
|
- text-to-image |
|
- stable-diffusion |
|
- lora |
|
- diffusers |
|
- template:sd-lora |
|
widget: |
|
- text: '-' |
|
output: |
|
url: images/BS-Pepe-V1_00001_.png |
|
- text: '-' |
|
output: |
|
url: images/BS-Pepe-V1_00006_.png |
|
- text: '-' |
|
output: |
|
url: images/BS-Pepe-V1_00009_.png |
|
- text: '-' |
|
output: |
|
url: images/BS-Pepe-V1_00010_.png |
|
- text: '-' |
|
output: |
|
url: images/BS-Pepe-V1_00013_.png |
|
- text: '-' |
|
output: |
|
url: images/BS-Pepe-V1_00015_.png |
|
- text: '-' |
|
output: |
|
url: images/BS-Pepe-V1_00026_.png |
|
- text: '-' |
|
output: |
|
url: images/BS-Pepe-V1_00034_.png |
|
- text: '-' |
|
output: |
|
url: images/BS-Pepe-V1_00040_.png |
|
- text: '-' |
|
output: |
|
url: images/BS-Pepe-V1_00049_.png |
|
- text: '-' |
|
output: |
|
url: images/BS-Pepe-V1_00073_.png |
|
- text: '-' |
|
output: |
|
url: images/BS-Pepe-V1_00085_.png |
|
- text: '-' |
|
output: |
|
url: images/BS-Pepe-V1_00089_.png |
|
- text: '-' |
|
output: |
|
url: images/BS-Pepe-V1_00079_.png |
|
- text: '-' |
|
output: |
|
url: images/BS-Pepe-V1_00059_.png |
|
- text: '-' |
|
output: |
|
url: images/BS-Pepe-V1_00021_.png |
|
base_model: stabilityai/stable-diffusion-xl-base-1.0 |
|
instance_prompt: >- |
|
pepe, girl pepe, close-up, medium-shot, 3d render, meme, cartoon, anime, |
|
digital art, painting, pepe family tree, minifig lego, web comic, CCTV, this |
|
is fine, feels bad man, print |
|
license: artistic-2.0 |
|
--- |
|
# BS-Pepe-V1 |
|
|
|
<Gallery /> |
|
|
|
## Model description |
|
|
|
SDXL PEPE LoRA |
|
Building on the previous and most excellent work of Dr. Diffusion's Pepe SDXL LoRA (https://civitai.com/models/161611/pepe-xl-lora), I decided to try an expanded SDXL Pepe LoRA. I added 469 new dalle3 Pepe images/captions to Dr. Diffusions original dataset for a total of 569 (nice) images. Trained for 50 epochs using the prodigy optimizer with a batch size of 4. Images were captioned in a similar style to the original DD model and all of the original tags should work but I added some new tags including Lego Minifig, CCTV, digital art, family tree, print, game cartridge, anime, girl pepe and N64 render. |
|
|
|
## Trigger words |
|
|
|
You should use `pepe` to trigger the image generation. |
|
|
|
You should use `girl pepe` to trigger the image generation. |
|
|
|
You should use `close-up` to trigger the image generation. |
|
|
|
You should use `medium-shot` to trigger the image generation. |
|
|
|
You should use `3d render` to trigger the image generation. |
|
|
|
You should use `meme` to trigger the image generation. |
|
|
|
You should use `cartoon` to trigger the image generation. |
|
|
|
You should use `anime` to trigger the image generation. |
|
|
|
You should use `digital art` to trigger the image generation. |
|
|
|
You should use `painting` to trigger the image generation. |
|
|
|
You should use `pepe family tree` to trigger the image generation. |
|
|
|
You should use `minifig lego` to trigger the image generation. |
|
|
|
You should use `web comic` to trigger the image generation. |
|
|
|
You should use `CCTV` to trigger the image generation. |
|
|
|
You should use `this is fine` to trigger the image generation. |
|
|
|
You should use `feels bad man` to trigger the image generation. |
|
|
|
You should use `print` to trigger the image generation. |
|
|
|
|
|
## Download model |
|
|
|
Weights for this model are available in Safetensors format. |
|
|
|
[Download](/BlaireSilver13/BS-Pepe-V1/tree/main) them in the Files & versions tab. |
|
|