duanlunhao
commited on
Commit
·
f286586
1
Parent(s):
e794ac7
update readme
Browse files
README.md
CHANGED
|
@@ -3,9 +3,9 @@
|
|
| 3 |
[](https://opensource.org/licenses/MIT)
|
| 4 |
[](https://github.com/AIDC-AI/UNIC-Adapter)
|
| 5 |
|
| 6 |
-
UNIC-Adapter is a unified image-instruction adapter that integrates multimodal instructions for controllable image generation. This
|
| 7 |
|
| 8 |
-
|
| 9 |
|
| 10 |
## Generated samples
|
| 11 |
|
|
@@ -21,7 +21,7 @@ In this repository, we release a model based on SD3 Medium, which supports the t
|
|
| 21 |
|
| 22 |
<img src='./examples/example_2.png' width='100%'/>
|
| 23 |
|
| 24 |
-
*(Left: condition image, Center: SD 3.5
|
| 25 |
|
| 26 |
<img src='./examples/example_3.png' width='75%'/>
|
| 27 |
|
|
|
|
| 3 |
[](https://opensource.org/licenses/MIT)
|
| 4 |
[](https://github.com/AIDC-AI/UNIC-Adapter)
|
| 5 |
|
| 6 |
+
UNIC-Adapter is a unified image-instruction adapter that integrates multimodal instructions for controllable image generation. This model card hosts the official models for the CVPR 2025 paper "UNIC-Adapter: Unified Image-instruction Adapter with Multi-modal Transformer for Image Generation".
|
| 7 |
|
| 8 |
+
On this model card, we release a model based on SD3 Medium, which supports the tasks described in our paper. In addition, we also provide two additional models: one built on SD3.5 Medium, which is capable of traditional computer vision perception tasks, and another on FLUX.1-dev, which supports both instruction-based image editing and traditional computer vision perception tasks.
|
| 9 |
|
| 10 |
## Generated samples
|
| 11 |
|
|
|
|
| 21 |
|
| 22 |
<img src='./examples/example_2.png' width='100%'/>
|
| 23 |
|
| 24 |
+
*(Left: condition image, Center: SD 3.5 Medium with UNIC-Adapter, Right: FLUX.1-dev with UNIC-Adapter)*
|
| 25 |
|
| 26 |
<img src='./examples/example_3.png' width='75%'/>
|
| 27 |
|