nDimensional
commited on
Commit
•
2efac46
1
Parent(s):
81134d8
Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,85 @@
|
|
| 1 |
---
|
| 2 |
license: creativeml-openrail-m
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
license: creativeml-openrail-m
|
| 3 |
+
tags:
|
| 4 |
+
- diffusers
|
| 5 |
+
- safetensors
|
| 6 |
+
- text-to-image
|
| 7 |
+
- stable-diffusion
|
| 8 |
+
- stable-diffusion-diffusers
|
| 9 |
+
language:
|
| 10 |
+
- en
|
| 11 |
+
library_name: diffusers
|
| 12 |
---
|
| 13 |
+
|
| 14 |
+
<div align="center">
|
| 15 |
+
<font size="12"><span style="color:Red">B</span>A<span style="color:Blue">M</span><span style="color:Yellow">!</span></font><br>
|
| 16 |
+
<font size="6"><span style="font-family:Comic Sans MS"><b>(Boomer Art Model)</span></b></font>
|
| 17 |
+
</div>
|
| 18 |
+
|
| 19 |
+
<img src="https://huggingface.co/Schisim/Boomer_Art_Model-SDXL/resolve/main/img/BAM_Grid.jpg" width=2048/>
|
| 20 |
+
|
| 21 |
+
---
|
| 22 |
+
1970s - 1990s Fantasy / Sci-fi illustrations for SDXL.
|
| 23 |
+
|
| 24 |
+
---
|
| 25 |
+
|
| 26 |
+
### Features
|
| 27 |
+
1. High-resolution images: Trained on 1024x1024 images (default for XL).
|
| 28 |
+
2. Various art-styles: Multiple artists/illustrators from the 1970s - 1990s. <i>A list of artists tags can be found bellow.</i>
|
| 29 |
+
3. Easy to prompt: Stylization of simple prompts can be achieved with as little as one special token (trigger) appended to the end of your prompt.
|
| 30 |
+
4. True to source: Special attention was payed to insure that the artstyle(s) being generated are as close to the individuals artstyle as possible.
|
| 31 |
+
5. Flexible: Can be easily merged with other SDXL checkpoints / LoRAs for more expansive generations.
|
| 32 |
+
6. Full parameter fine-tune: This is a full parameter fine-tune of the original SDXL base 1.0 model. Both the U-Net and both text-encoders were tuned during training.
|
| 33 |
+
|
| 34 |
+
<b>General Information</b>:
|
| 35 |
+
* Base model - SDXL v1.0
|
| 36 |
+
* VAE - <a href="https://huggingface.co/madebyollin/sdxl-vae-fp16-fix">sdxl-vae-fp16-fix</a>
|
| 37 |
+
* Type - Full-parameter fine-tune, including text-encoders, bfloat16 (bf16).
|
| 38 |
+
* Style - Painting, Drawling, Illustration, digital painting
|
| 39 |
+
|
| 40 |
+
---
|
| 41 |
+
### Usage
|
| 42 |
+
<b>Special Tokens</b>:
|
| 43 |
+
* `BAStyle`, a general prefix that is not strictly required but can help maintain the models style.
|
| 44 |
+
* Place at beginning of your prompt.
|
| 45 |
+
|
| 46 |
+
<b>Artist Tags</b>: Appending these tags to the end of your prompt will guide the model to generate an output in the style of the artist that's being tagged.
|
| 47 |
+
* by Boris Vallejo
|
| 48 |
+
* by Brom
|
| 49 |
+
* by Caza
|
| 50 |
+
* by Chris Foss
|
| 51 |
+
* by Clyde Caldwell
|
| 52 |
+
* by Col Price
|
| 53 |
+
* by Dave Dorman
|
| 54 |
+
* by Frank Frazetta
|
| 55 |
+
* sketches by Frank Frazetta
|
| 56 |
+
* by Kelly Freas
|
| 57 |
+
* by John Berkey
|
| 58 |
+
* by Gimenez
|
| 59 |
+
* by Ken Kelly
|
| 60 |
+
* modern art by Kirsi Salonen
|
| 61 |
+
* modern art by Kyu Yong Eom
|
| 62 |
+
* by Luis Royo
|
| 63 |
+
* by Michael Whelan
|
| 64 |
+
* by Mike Hoffman
|
| 65 |
+
* by Milo Manara
|
| 66 |
+
* by Moebius
|
| 67 |
+
* by Philippe Druillet
|
| 68 |
+
* by Sanjulian
|
| 69 |
+
* by Ted Nasmith
|
| 70 |
+
<br>
|
| 71 |
+
|
| 72 |
+
<i>A wildcard can be found in the 'files'.</i>
|
| 73 |
+
|
| 74 |
+
<b>Random Style Generation (RSG) Token</b>: The following token (trigger) is a made-up artist that generates an image in the style of a random artist. <i>It's not perfect but can yield interesting results.</i>
|
| 75 |
+
* by Gladius
|
| 76 |
+
|
| 77 |
+
---
|
| 78 |
+
### Limitations
|
| 79 |
+
BAM! inherits some (not all) of the limitations from the original SDXL v1.0 model.<br>
|
| 80 |
+
<b>BIAS</b>: This model is bias towards paintings, drawings, and illustrations from the 1970s - 1980s.
|
| 81 |
+
|
| 82 |
+
---
|
| 83 |
+
<i>Future updates are already in the works to bring SDXL up to — and beyond SD1.5 standards. If you want to contribute, DM me at the discord thread linked above. My goal is to create fine-tunes on unique styles or concepts SDXL struggles with, expanding the pool of models for merging.</i>
|
| 84 |
+
|
| 85 |
+
---
|