Add note about Qwen Image 2512
Browse files
README.md
CHANGED
|
@@ -50,6 +50,8 @@ Training was first performed using nf4 quantization for 32 epochs (8 epochs coun
|
|
| 50 |
Training then continued at int8 quantization for another 16 epochs (4 epochs counting the original + augmentations as a single epoch):
|
| 51 |
- `qwen-360-diffusion-int8-bf16-v1.safetensors` was trained for a total of 48 epochs (2,304,000 steps)
|
| 52 |
|
|
|
|
|
|
|
| 53 |
---
|
| 54 |
|
| 55 |
|
|
|
|
| 50 |
Training then continued at int8 quantization for another 16 epochs (4 epochs counting the original + augmentations as a single epoch):
|
| 51 |
- `qwen-360-diffusion-int8-bf16-v1.safetensors` was trained for a total of 48 epochs (2,304,000 steps)
|
| 52 |
|
| 53 |
+
Training is currently being continued at int8 quantization for another set of epochs on the new [Qwen/Qwen-Image-2512](https://huggingface.co/Qwen/Qwen-Image-2512) base model.
|
| 54 |
+
|
| 55 |
---
|
| 56 |
|
| 57 |
|