Update README.md
Browse files
README.md
CHANGED
|
@@ -65,34 +65,38 @@ PrometheusV1 is presumed to be the first full rank finetune of Playground v2.5,
|
|
| 65 |
|
| 66 |
Presumed First Full Rank Finetune of Playground v2.5:
|
| 67 |
|
| 68 |
-
|
| 69 |
-
|
| 70 |
|
| 71 |
|
| 72 |
Enhanced Accessibility:
|
| 73 |
|
| 74 |
-
|
| 75 |
-
|
| 76 |
-
|
| 77 |
|
| 78 |
|
| 79 |
Output Characteristics:
|
| 80 |
|
| 81 |
-
|
| 82 |
-
|
| 83 |
|
| 84 |
|
| 85 |
Training Approach:
|
| 86 |
|
| 87 |
-
|
| 88 |
-
|
| 89 |
-
|
| 90 |
|
| 91 |
|
| 92 |
-
Custom CLIP Integration:
|
| 93 |
-
|
| 94 |
-
|
| 95 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
| 96 |
|
| 97 |
|
| 98 |
|
|
|
|
| 65 |
|
| 66 |
Presumed First Full Rank Finetune of Playground v2.5:
|
| 67 |
|
| 68 |
+
- Complete parameter update of Playground v2.5 architecture
|
| 69 |
+
- Unique approach to fine-tuning this particular base model
|
| 70 |
|
| 71 |
|
| 72 |
Enhanced Accessibility:
|
| 73 |
|
| 74 |
+
- Custom sampling methods have been removed through brute force techniques
|
| 75 |
+
- Designed to be more compatible with standard open-source tools and workflows
|
| 76 |
+
- post processing applied to ensure backwards compatibility with most SDXL LoRAs and tools
|
| 77 |
|
| 78 |
|
| 79 |
Output Characteristics:
|
| 80 |
|
| 81 |
+
- Aims to provide a balance between consistency and diversity in outputs
|
| 82 |
+
- May exhibit some stylistic tendencies inherited from the training process
|
| 83 |
|
| 84 |
|
| 85 |
Training Approach:
|
| 86 |
|
| 87 |
+
- Utilizes the extensive Proteus datasets of over 400,000 images
|
| 88 |
+
- Brute force at scale training methodology
|
| 89 |
+
- Focused on maintaining model capabilities while increasing compatibility
|
| 90 |
|
| 91 |
|
| 92 |
+
Advanced Custom CLIP Integration:
|
| 93 |
+
|
| 94 |
+
- Incorporates a meticulously trained custom CLIP model
|
| 95 |
+
- Steadily developed over an extended period
|
| 96 |
+
- Further fine-tuned for specific qualities in Proteus and Prometheus
|
| 97 |
+
- Estimated to contribute 90% of the model's performance improvements
|
| 98 |
+
- Requires a clip skip setting of 2 for optimal performance
|
| 99 |
+
|
| 100 |
|
| 101 |
|
| 102 |
|