README: note the bugs-and-botany and landscape subsets
Browse files
README.md
CHANGED
|
@@ -85,6 +85,8 @@ I can think of lots of things one _could_ do to perhaps improve the result, thou
|
|
| 85 |
|
| 86 |
- More dataset curation. The images were _relatively_ consistent, but the botanical illustrations are better than the mammals,
|
| 87 |
the engineering illustrations are different than the cityscapes, etc.
|
|
|
|
|
|
|
| 88 |
- Dataset augmentation. (I haven't yet turned to any of the tricks like mirroring the images, but I'm not sure if more is better at this point.)
|
| 89 |
- Multi-resolution training. Flux is usually pretty good over a range of sizes,
|
| 90 |
but this LoRA seems to suffer more when going below the megapixel size it was trained at.
|
|
|
|
| 85 |
|
| 86 |
- More dataset curation. The images were _relatively_ consistent, but the botanical illustrations are better than the mammals,
|
| 87 |
the engineering illustrations are different than the cityscapes, etc.
|
| 88 |
+
- [`trousset-bugs-and-botany-sources.txt`](./trousset-bugs-and-botany-sources.txt): mostly flowers, close-up detail illustrations with no backgrounds.
|
| 89 |
+
- [`trousset-landscape-sources.txt`](./trousset-landscape-sources.txt): cityscapes and landscapes and a few other scenes with a similar mostly-full-frame style.
|
| 90 |
- Dataset augmentation. (I haven't yet turned to any of the tricks like mirroring the images, but I'm not sure if more is better at this point.)
|
| 91 |
- Multi-resolution training. Flux is usually pretty good over a range of sizes,
|
| 92 |
but this LoRA seems to suffer more when going below the megapixel size it was trained at.
|