dataautogpt3
commited on
Commit
•
0aee9aa
1
Parent(s):
c8fe4b6
Update README.md
Browse files
README.md
CHANGED
@@ -73,7 +73,7 @@ merged with RealCartoonXL to fix issues with inability to understand tags relate
|
|
73 |
|
74 |
Proteus serves as a sophisticated enhancement over OpenDalleV1.1, leveraging its core functionalities to deliver superior outcomes. Key areas of advancement include heightened responsiveness to prompts and augmented creative capacities. To achieve this, it was fine-tuned using approximately 220,000 GPTV captioned images from copyright-free stock images (with some anime included), which were then normalized. Additionally, DPO (Direct Preference Optimization) was employed through a collection of 10,000 carefully selected high-quality, AI-generated image pairs.
|
75 |
|
76 |
-
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,
|
77 |
|
78 |
|
79 |
## Settings for ProteusV0.2
|
|
|
73 |
|
74 |
Proteus serves as a sophisticated enhancement over OpenDalleV1.1, leveraging its core functionalities to deliver superior outcomes. Key areas of advancement include heightened responsiveness to prompts and augmented creative capacities. To achieve this, it was fine-tuned using approximately 220,000 GPTV captioned images from copyright-free stock images (with some anime included), which were then normalized. Additionally, DPO (Direct Preference Optimization) was employed through a collection of 10,000 carefully selected high-quality, AI-generated image pairs.
|
75 |
|
76 |
+
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.
|
77 |
|
78 |
|
79 |
## Settings for ProteusV0.2
|