Upload folder using huggingface_hub
Browse files- .gitattributes +1 -1
- README.md +6 -2
- assets/mona_lisa.png +3 -0
- assets/siglip2_output.png +3 -0
- assets/siglip_output.png +3 -0
.gitattributes
CHANGED
|
@@ -33,4 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
-
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
*.png filter=lfs diff=lfs merge=lfs -text
|
README.md
CHANGED
|
@@ -9,12 +9,16 @@ tags:
|
|
| 9 |
- flux
|
| 10 |
- siglip2
|
| 11 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 12 |
|
| 13 |
-

|
| 14 |
|
| 15 |
# Flex.1-alpha-Redux [dev] — Enhanced with SigLIP-2
|
| 16 |
|
| 17 |
-
Flex.1-alpha-Redux [dev] is an adapter for all FLUX.1 base models for image variation generation.
|
| 18 |
Given an input image, Flex.1 Redux can reproduce the image with slight variation, allowing for refined visual generation. It integrates naturally into more complex workflows, enabling image restyling and editing via text.
|
| 19 |
|
| 20 |
This version of Redux has been updated with modules from [`SigLIP2`](https://huggingface.co/google/siglip2-so400m-patch16-512) replacing the following components:
|
|
|
|
| 9 |
- flux
|
| 10 |
- siglip2
|
| 11 |
---
|
| 12 |
+
**Input Image** | **Original FLUX Redux** | **SigLIP2-Enhanced**
|
| 13 |
+
:--:|:--:|:--:
|
| 14 |
+
<img src="./assets/mona_lisa.png" width="200" height="200"/> | <img src="./assets/siglip_output.png" width="200" height="200"/> | <img src="./assets/siglip2_output.png" width="200" height="200"/>
|
| 15 |
+
|
| 16 |
+
|
| 17 |
|
|
|
|
| 18 |
|
| 19 |
# Flex.1-alpha-Redux [dev] — Enhanced with SigLIP-2
|
| 20 |
|
| 21 |
+
Flex.1-alpha-Redux [dev] is an adapter for all FLUX.1 base models for image variation generation.
|
| 22 |
Given an input image, Flex.1 Redux can reproduce the image with slight variation, allowing for refined visual generation. It integrates naturally into more complex workflows, enabling image restyling and editing via text.
|
| 23 |
|
| 24 |
This version of Redux has been updated with modules from [`SigLIP2`](https://huggingface.co/google/siglip2-so400m-patch16-512) replacing the following components:
|
assets/mona_lisa.png
ADDED
|
Git LFS Details
|
assets/siglip2_output.png
ADDED
|
Git LFS Details
|
assets/siglip_output.png
ADDED
|
Git LFS Details
|