Qwen Image 2512 Support
#6
by
ProGamerGov
- opened
README.md
CHANGED
|
@@ -3,6 +3,7 @@ language:
|
|
| 3 |
- en
|
| 4 |
base_model:
|
| 5 |
- Qwen/Qwen-Image
|
|
|
|
| 6 |
pipeline_tag: text-to-image
|
| 7 |
tags:
|
| 8 |
- '360'
|
|
@@ -50,7 +51,9 @@ 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 |
-
Training
|
|
|
|
|
|
|
| 54 |
|
| 55 |
---
|
| 56 |
|
|
|
|
| 3 |
- en
|
| 4 |
base_model:
|
| 5 |
- Qwen/Qwen-Image
|
| 6 |
+
- Qwen/Qwen-Image-2512
|
| 7 |
pipeline_tag: text-to-image
|
| 8 |
tags:
|
| 9 |
- '360'
|
|
|
|
| 51 |
Training then continued at int8 quantization for another 16 epochs (4 epochs counting the original + augmentations as a single epoch):
|
| 52 |
- `qwen-360-diffusion-int8-bf16-v1.safetensors` was trained for a total of 48 epochs (2,304,000 steps)
|
| 53 |
|
| 54 |
+
Training then continued on [Qwen/Qwen-Image-2512](https://huggingface.co/Qwen/Qwen-Image-2512) at int8 quantization for another 14 epochs on (3.5 epochs counting the original + augmentations as a single epoch):
|
| 55 |
+
- The total number of equirectangular images increased to 35k, and regularization images were removed from the dataset.
|
| 56 |
+
- `qwen-360-diffusion-2512-int8-bf16-v2.safetensors` was trained for 62 epochs (2,794,000 steps)
|
| 57 |
|
| 58 |
---
|
| 59 |
|
qwen-360-diffusion-2512-int8-bf16-v2.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:11065421c2a4c8f503ee1be5d6dc0320a9ffb5bfaded2490813046fd2312578d
|
| 3 |
+
size 755039336
|