Create README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
language:
|
| 3 |
+
- en
|
| 4 |
+
tags:
|
| 5 |
+
- stable-diffusion
|
| 6 |
+
- text-to-image
|
| 7 |
+
license: bigscience-bloom-rail-1.0
|
| 8 |
+
inference: false
|
| 9 |
+
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
| model | init model | lr | bs | acc | total steps | training samples | training resolution | models trained |
|
| 13 |
+
|--- |--- | --- | --- | --- | --- | --- | --- | --- |
|
| 14 |
+
| eva-fusion-v2 |compvis 1-4| 2.057e-06 | 1 | 1 | 8,000 | 1,143 (captioned just "picture in the style of evangelion") | 512x384 (4:3) | unet |
|
| 15 |
+
| eva-fusion-v2.1 | eva-fusion-v2 | 1.313e-06 | 1 | 1 | 10,000 | + 560 (hand captioned) | 512x384 (4:3) | unet |
|
| 16 |
+
| eva-fusion-v2.22 "you are (not) HD" | previous models + compvis1-4 + wd1.3 at various ratios | x | x | x | x | x | x | x |
|
| 17 |
+
|
| 18 |
+
examples generated with an unfinished version of [Whatchamacallit](https://colab.research.google.com/github/aicrumb/whatchamacallit/blob/main/Whatchamacallit.ipynb)
|
| 19 |
+
|
| 20 |
+
prompt: a [complex mech, angel, cityscape, mechanical brain] in the style of Evangelion
|
| 21 |
+
|
| 22 |
+
negative: blurry jpeg, multiple views
|
| 23 |
+
|