Downloads · 30 days
130
4% of all-time downloads
broken-mirror-style
Kagerage/broken-mirror-style
broken-mirror-style is a text-to-image model from Kagerage. Use it when you need an image from a text prompt. It is set up for diffusers. The card lists the license as creativeml-openrail-m.
Test the concept via A1111 Colab fast-Colab-A1111 Or you can run your new concept via diffusers Colab Notebook for Inference
All-time downloads
3.1K
Public
Repo size
9.7 GB
Likes
1
Public
Repo makeup
Click a slice to open those files.
.bin4.5 GB · 46%
At a glance
- Task
- Text-to-Image
- Library
- diffusers
- License
- creativeml-openrail-m
- Access
- Public
- Created
- Dec 26, 2022
- Updated
- Jan 28, 2023
- SHA
- adad379e
Model card
From the Hugging Face model README
Broken-Mirror-Style Dreambooth model trained by Kagerage with TheLastBen's fast-DreamBooth notebook
Test the concept via A1111 Colab fast-Colab-A1111
Or you can run your new concept via diffusers Colab Notebook for Inference
In my experience, the best prompting style is "brkmror cracked and shattered mirror, professional photo, descriptor of location, portrait of person, bokeh", potentially with a negative prompt of "closed eyes"
Sampler DPM++ SDE Karras with at least 25 steps gives slightly better faces from my testing, CFG 7 seems fine, and since this is trained on top of 2.1, the minimum resolution is 768x768.
Or course though, feel free to experiment!
(NOTE!!! This 2.1 based model is FP16, so it may not render outputs properly without Xformers)
Sample pictures of this concept:
- Task
- Text-to-Image
- Library
- diffusers
- License
- creativeml-openrail-m
- Created
- Dec 26, 2022
- Updated
- Jan 28, 2023