Add paper link
#1
by
osanseviero
HF staff
- opened
README.md
CHANGED
@@ -22,7 +22,7 @@ The λ-ECLIPSE model is a light weight support for multi-concept personali
|
|
22 |
|
23 |
- **Project Page:** [https://eclipse-t2i.github.io/Lambda-ECLIPSE/](https://eclipse-t2i.github.io/Lambda-ECLIPSE/)
|
24 |
- **GitHub:** [https://github.com/Maitreyapatel/lambda-eclipse-inference](https://github.com/Maitreyapatel/lambda-eclipse-inference)
|
25 |
-
- **Paper (arXiv):** [
|
26 |
|
27 |
Importantly, λ-ECLIPSE works in pure CLIP latent space without any additional information. Hence, it's performance can be easily imporved via test-time adaption to increase the concept alignment while having solid composition alignment.
|
28 |
|
|
|
22 |
|
23 |
- **Project Page:** [https://eclipse-t2i.github.io/Lambda-ECLIPSE/](https://eclipse-t2i.github.io/Lambda-ECLIPSE/)
|
24 |
- **GitHub:** [https://github.com/Maitreyapatel/lambda-eclipse-inference](https://github.com/Maitreyapatel/lambda-eclipse-inference)
|
25 |
+
- **Paper (arXiv):** [https://arxiv.org/abs/2402.05195](https://arxiv.org/abs/2402.05195)
|
26 |
|
27 |
Importantly, λ-ECLIPSE works in pure CLIP latent space without any additional information. Hence, it's performance can be easily imporved via test-time adaption to increase the concept alignment while having solid composition alignment.
|
28 |
|