Update README.md
Browse files
README.md
CHANGED
|
@@ -4,22 +4,32 @@ We have achieved some initial promising experimental results, but it is still no
|
|
| 4 |
|
| 5 |
If you would like to test it, please contact the NewBieAi administrator. We may grant you access and testing permission after evaluating your situation.
|
| 6 |
|
| 7 |
-
Basic Information:
|
| 8 |
-
|
|
|
|
|
|
|
| 9 |
>Text Encoder:
|
| 10 |
Google/Gemma3-4b-it
|
| 11 |
Jina Ai/Jina Clip v2
|
| 12 |
Total: approximately 5b
|
|
|
|
| 13 |
>Networks:
|
| 14 |
Next-DIT (modified from 26 layers to 36 layers) 3.5b
|
|
|
|
| 15 |
>VAE:
|
| 16 |
Flux 1 Dev-VAE
|
|
|
|
| 17 |
Pretrain Dataset: full dan + 1m e621
|
|
|
|
| 18 |
Use 8*h200 train for four months (23000 h200 hour)
|
| 19 |
-
|
| 20 |
Restructure text data use XML format
|
|
|
|
|
|
|
| 21 |
The model is currently in the train phase (60% complete).
|
|
|
|
| 22 |
Overall progress is approximately 80%.
|
|
|
|
| 23 |
The model is expected to be open sourced on Hugging Face on December 31, 2025.
|
| 24 |
|
| 25 |
exampleοΌ
|
|
|
|
| 4 |
|
| 5 |
If you would like to test it, please contact the NewBieAi administrator. We may grant you access and testing permission after evaluating your situation.
|
| 6 |
|
| 7 |
+
>Basic Information:
|
| 8 |
+
|
| 9 |
+
>Anime Type
|
| 10 |
+
|
| 11 |
>Text Encoder:
|
| 12 |
Google/Gemma3-4b-it
|
| 13 |
Jina Ai/Jina Clip v2
|
| 14 |
Total: approximately 5b
|
| 15 |
+
|
| 16 |
>Networks:
|
| 17 |
Next-DIT (modified from 26 layers to 36 layers) 3.5b
|
| 18 |
+
|
| 19 |
>VAE:
|
| 20 |
Flux 1 Dev-VAE
|
| 21 |
+
|
| 22 |
Pretrain Dataset: full dan + 1m e621
|
| 23 |
+
|
| 24 |
Use 8*h200 train for four months (23000 h200 hour)
|
| 25 |
+
|
| 26 |
Restructure text data use XML format
|
| 27 |
+
|
| 28 |
+
|
| 29 |
The model is currently in the train phase (60% complete).
|
| 30 |
+
|
| 31 |
Overall progress is approximately 80%.
|
| 32 |
+
|
| 33 |
The model is expected to be open sourced on Hugging Face on December 31, 2025.
|
| 34 |
|
| 35 |
exampleοΌ
|