Update README.md
Browse files
README.md
CHANGED
@@ -44,8 +44,7 @@ widget:
|
|
44 |
# Anna Akhmatova Flux Low-Rank Adapter (LoRA) Version 2 by SilverAgePoets.com
|
45 |
Trained via Ostris' [ai-toolkit](https://replicate.com/ostris/flux-dev-lora-trainer/train) on 60 vintage photos (most of them colorized by us and/or by [Klimbim](https://klimbim2020.wordpress.com/)). <br>
|
46 |
And capturing the legendary **poet**: <br>
|
47 |
-
**Anna Andreevna Akhmatova** <br>
|
48 |
-
*(b.06/26/1889-d.03/05/1966)* <br>
|
49 |
|
50 |
For this LoRA we used highly detailed manually-composed paragraph captions. <br>
|
51 |
It was trained for 1200 steps at a Transformer Learning Rate of .0002, batch 1, AdamW8bit! Minimal synthetic data (just a few reluctant upscales), zero auto-generated captions! <br>
|
|
|
44 |
# Anna Akhmatova Flux Low-Rank Adapter (LoRA) Version 2 by SilverAgePoets.com
|
45 |
Trained via Ostris' [ai-toolkit](https://replicate.com/ostris/flux-dev-lora-trainer/train) on 60 vintage photos (most of them colorized by us and/or by [Klimbim](https://klimbim2020.wordpress.com/)). <br>
|
46 |
And capturing the legendary **poet**: <br>
|
47 |
+
**Anna Andreevna Akhmatova** <br> *(b.06/26/1889-d.03/05/1966)* <br>
|
|
|
48 |
|
49 |
For this LoRA we used highly detailed manually-composed paragraph captions. <br>
|
50 |
It was trained for 1200 steps at a Transformer Learning Rate of .0002, batch 1, AdamW8bit! Minimal synthetic data (just a few reluctant upscales), zero auto-generated captions! <br>
|