|
--- |
|
license: creativeml-openrail-m |
|
tags: |
|
- text-to-image |
|
- safetensors |
|
- stable-diffusion |
|
--- |
|
### Wriggly's-Extra-Gum-artstyle-waifudiffusion Dreambooth model trained by Kagerage with [TheLastBen's fast-DreamBooth](https://colab.research.google.com/github/TheLastBen/fast-stable-diffusion/blob/main/fast-DreamBooth.ipynb) notebook |
|
|
|
|
|
Test the concept via A1111 Colab [fast-Colab-A1111](https://colab.research.google.com/github/TheLastBen/fast-stable-diffusion/blob/main/fast_stable_diffusion_AUTOMATIC1111.ipynb) |
|
Or you can run your new concept via `diffusers` [Colab Notebook for Inference](https://colab.research.google.com/github/huggingface/notebooks/blob/main/diffusers/sd_dreambooth_inference.ipynb) |
|
|
|
As the name suggests, this model was trained on that weird hand-drawn looking artwork that you'd find on the inside of a pack of Wriggly's Extra gum, ontop of Waifu Diffusion 1.3. |
|
|
|
PROMPTING ADVICE: Best results come from using the trigger word like "gvgtgm lineart drawing", or "gvgtgm badly drawn lineart drawing" (Oof...) for a more true to training data image |
|
|
|
prompt for either "(anime name) anime 1boy/1girl/whatever", "1boy/1girl/whatever" for something more akin to the training data, and either "modern anime 1boy/1girl/whatever" or "quality anime 1boy/1girl/whatever" for an inbetween of the training data and a general anime style |
|
|
|
anything else should be added at the end, so prompt would look like "gvgtgm lineart drawing, jojo anime 1boy, sweater and jeans, snow, park, trees, upper-body portrait" |
|
 |
|
|
|
Recommended sampler is anything non-ancestral, as to avoid softness. CFG 7 seems to work fine. Looks like it generates decent results without the Waifu Diffusion VAE, not sure how it acts with it enabled. |
|
|
|
Sample pictures of this concept: |
|
 |
|
 |
|
 |
|
|
|
|
|
Bonus images from trial and error |
|
 |
|
 |
|
 |
|
 |
|
 |
