Update README.md
Browse files
README.md
CHANGED
|
@@ -2,6 +2,16 @@
|
|
| 2 |
license: apache-2.0
|
| 3 |
---
|
| 4 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5 |
Nowadays, text-to-image (T2I) models are growing stronger but larger, which limits their practical applicability, especially on consumer-level devices.
|
| 6 |
To bridge this gap, we distilled the **12B** `Flux-dev` model into a **3.2B** `Flux-mini` model, trying to preserve its strong image generation capabilities.
|
| 7 |
Specifically, we prune the original `Flux-dev` by reducing its depth from `19 + 38` (number of double blocks and single blocks) to `5 + 10`.
|
|
|
|
| 2 |
license: apache-2.0
|
| 3 |
---
|
| 4 |
|
| 5 |
+
# Flux-Mini
|
| 6 |
+
<div align="center">
|
| 7 |
+
<img src="assets/flux_distill-flux-mini-teaser.jpg" width="800" alt="Teaser image">
|
| 8 |
+
</div>
|
| 9 |
+
|
| 10 |
+
|
| 11 |
+
A distilled Flux-dev model for efficient text-to-image generation
|
| 12 |
+
|
| 13 |
+
|
| 14 |
+
|
| 15 |
Nowadays, text-to-image (T2I) models are growing stronger but larger, which limits their practical applicability, especially on consumer-level devices.
|
| 16 |
To bridge this gap, we distilled the **12B** `Flux-dev` model into a **3.2B** `Flux-mini` model, trying to preserve its strong image generation capabilities.
|
| 17 |
Specifically, we prune the original `Flux-dev` by reducing its depth from `19 + 38` (number of double blocks and single blocks) to `5 + 10`.
|