Add Readme
Browse files
README.md
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: diffusers
|
| 3 |
+
pipeline_tag: text-to-image
|
| 4 |
+
tags:
|
| 5 |
+
- stable-diffusion-xl
|
| 6 |
+
- v-prediction
|
| 7 |
+
- anime
|
| 8 |
+
- sparse-merge
|
| 9 |
+
license: openrail++
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
# Project-Cosmos-V1.3 (High Fidelity)
|
| 13 |
+
|
| 14 |
+
**Cosmos V1.3** is the direct evolution of the successful V1.1. It corrects the anatomical stiffness of V1.2 by reverting to V1.1's exact structural weights, while significantly improving texture detail.
|
| 15 |
+
|
| 16 |
+
## The Recipe
|
| 17 |
+
* **Anatomy (Input/Middle):** Reverted strictly to **V1.1 Settings** (Drop 70-80%, Strength 0.5-0.6). This guarantees the return of perfect fingers and poses.
|
| 18 |
+
* **Style (Output):** **Drop Rate Reduced to 25%** (from 40%). By allowing more fine-grained texture data from NoobAI to pass through (while slightly adjusting strength to 0.75), we achieve a "High Fidelity" look without compromising the structural integrity.
|
| 19 |
+
|
| 20 |
+
## Recommended Settings
|
| 21 |
+
* **Sampler:** Euler a / DPM++ 2M SDE
|
| 22 |
+
* **CFG:** 5.0 - 7.0
|
| 23 |
+
* **Steps:** 28+
|