Update README.md
Browse files
README.md
CHANGED
|
@@ -28,7 +28,7 @@ We empirically found that different blocks have different impacts on the generat
|
|
| 28 |
The distillation process consists of three objectives: the denoise loss, the output alignment loss as well as the feature alignment loss.
|
| 29 |
The feature alignment loss is designed in a way such that the output of `block-x` in the student model is encouraged to match that of `block-4x` in the teacher model.
|
| 30 |
The distillation process is performed with `512x512` Laion images recaptioned with `Qwen-VL` in the first stage for `90k steps`,
|
| 31 |
-
and `1024x1024` images generated by `Flux` using the prompts in `JourneyDB` with another `90k steps`.
|
| 32 |
|
| 33 |
## Limitations
|
| 34 |
|
|
|
|
| 28 |
The distillation process consists of three objectives: the denoise loss, the output alignment loss as well as the feature alignment loss.
|
| 29 |
The feature alignment loss is designed in a way such that the output of `block-x` in the student model is encouraged to match that of `block-4x` in the teacher model.
|
| 30 |
The distillation process is performed with `512x512` Laion images recaptioned with `Qwen-VL` in the first stage for `90k steps`,
|
| 31 |
+
and `1024x1024` images generated by `Flux-schnell` using the prompts in `JourneyDB` with another `90k steps`.
|
| 32 |
|
| 33 |
## Limitations
|
| 34 |
|