Update README.md
Browse files
README.md
CHANGED
|
@@ -20,7 +20,7 @@ The λ-ECLIPSE model is a light weight support for multi-concept personali
|
|
| 20 |
λ-ECLIPSE shows that we do not need to train the Personalized T2I (P-T2I) models on lot of resources. For instance, λ-ECLIPSE is trained on mere 74 GPU Hours (A100) compared to it's couterparts BLIP-Diffusion (2304 GPU hours) and Kosmos-G (12300 GPU hours).
|
| 21 |
|
| 22 |
- **Project Page:** [https://eclipse-t2i.github.io/Lambda-ECLIPSE/](https://eclipse-t2i.github.io/Lambda-ECLIPSE/)
|
| 23 |
-
- **GitHub:** [https://github.com/
|
| 24 |
- **Paper (arXiv):** [TBD](#)
|
| 25 |
|
| 26 |
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.
|
|
|
|
| 20 |
λ-ECLIPSE shows that we do not need to train the Personalized T2I (P-T2I) models on lot of resources. For instance, λ-ECLIPSE is trained on mere 74 GPU Hours (A100) compared to it's couterparts BLIP-Diffusion (2304 GPU hours) and Kosmos-G (12300 GPU hours).
|
| 21 |
|
| 22 |
- **Project Page:** [https://eclipse-t2i.github.io/Lambda-ECLIPSE/](https://eclipse-t2i.github.io/Lambda-ECLIPSE/)
|
| 23 |
+
- **GitHub:** [https://github.com/Maitreyapatel/lambda-eclipse-inference](https://github.com/Maitreyapatel/lambda-eclipse-inference)
|
| 24 |
- **Paper (arXiv):** [TBD](#)
|
| 25 |
|
| 26 |
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.
|