|
--- |
|
license: creativeml-openrail-m |
|
tags: |
|
- text-to-image |
|
- art |
|
widget: |
|
- text: duskypie |
|
language: |
|
- en |
|
pipeline_tag: text-to-image |
|
--- |
|
### DuskfallTest Dreambooth model trained by Duskfallcrew with [Hugging Face Dreambooth Training Space](https://huggingface.co/spaces/multimodalart/dreambooth-training) with the v1-5 base model |
|
|
|
You 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). Don't forget to use the concept prompts! |
|
|
|
WARNING: This is trained largely on a small data set of our own art with a focus on the fact that our art, and any stable/midjourney outputs we included in this are related to our Dissoicative Identity Disorder. May actually retrain a larger data set later on. |
|
|
|
Sample Outputs: |
|
 |
|
 |
|
 |
|
 |
|
|
|
|
|
|
|
Sample pictures that it was trained on: |
|
 |
|
 |
|
 |
|
|
|
Trained using the MultiModel Dreambooth App, sitting on a friday afternoon doing absolute squat. |
|
Please DO NOT re-upload the sample pictures that it was trained on, except in the instance you are inspired to use img2img.. |
|
In which we dutifully ask you to spam the community section with your outputs. |
|
|
|
Figured might as well make this public for giggles, it's not a perfect model. Am cleaning up some of the concept folder as some of the concepts its trained on are not ones we want in the public eye. |
|
Model is under the creativeml-openrail-m, and of course - trained on 99% lazy afternoons. |
|
|
|
Model sampling data includes: Digital artwork by Duskfall, Midjourney & Stable Diffusion outputs, Traditional scanned artwork by Duskfall. Second Life /3D outputs that were created by us long ago, some re-done in the application called FACEAPP. We'd like to do a larger training with more time and money but need to learn how these work first! |
