dataautogpt3
commited on
Commit
•
4e16299
1
Parent(s):
090d156
Update README.md
Browse files
README.md
CHANGED
@@ -13,6 +13,9 @@ Proteus serves as a sophisticated enhancement over OpenDalleV1.1, leveraging its
|
|
13 |
|
14 |
In pursuit of optimal performance, numerous LORA (Low-Rank Adaptation) models are trained independently before being selectively incorporated into the principal model via dynamic application methods. These techniques involve targeting particular segments within the model while avoiding interference with other areas during the learning phase. Consequently, Proteus exhibits marked improvements in portraying intricate facial characteristics and lifelike skin textures, all while sustaining commendable proficiency across various aesthetic domains, notably surrealism, anime, and cartoon-style visualizations.
|
15 |
|
|
|
|
|
|
|
16 |
|
17 |
## Settings for ProteusV0.4-Lightning
|
18 |
Use these settings for the best results with ProteusV0.4-Lightning :
|
|
|
13 |
|
14 |
In pursuit of optimal performance, numerous LORA (Low-Rank Adaptation) models are trained independently before being selectively incorporated into the principal model via dynamic application methods. These techniques involve targeting particular segments within the model while avoiding interference with other areas during the learning phase. Consequently, Proteus exhibits marked improvements in portraying intricate facial characteristics and lifelike skin textures, all while sustaining commendable proficiency across various aesthetic domains, notably surrealism, anime, and cartoon-style visualizations.
|
15 |
|
16 |
+
finetuned/trained on a total of 400k+ images at this point.
|
17 |
+
|
18 |
+
|
19 |
|
20 |
## Settings for ProteusV0.4-Lightning
|
21 |
Use these settings for the best results with ProteusV0.4-Lightning :
|