Update README.md
Browse files
README.md
CHANGED
|
@@ -18,6 +18,10 @@ tags:
|
|
| 18 |
|
| 19 |
To a certain extent, the problem of ZIB color deviation has been reduced, but it is recommended to adjust the color appropriately according to the art style
|
| 20 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 21 |
- inference cfg: 1.0（建议1.0）
|
| 22 |
- inference steps: 10（10-15步）
|
| 23 |
- sampler / scheduler: Euler / simple
|
|
@@ -25,6 +29,14 @@ To a certain extent, the problem of ZIB color deviation has been reduced, but it
|
|
| 25 |
The art style leans towards realism
|
| 26 |
Retains ZIB's creative ability and reduces the collapse of Human anatomy.
|
| 27 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 28 |
## Z-Image-Distilled V1 2026/1/30
|
| 29 |
|
| 30 |
This model is a **direct distillation-accelerated version** based on the original **Z-Image** (non-Turbo) source. Its purpose is to test LoRA training effects on the Z-Image (non-turbo) version while significantly improving inference/test speed. The model **does not incorporate any weights or style from Z-Image-Turbo** at all — it is a **pure-blood version** based purely on Z-Image, effectively retaining the original Z-Image's adaptability, random diversity in outputs, and overall image style.
|
|
|
|
| 18 |
|
| 19 |
To a certain extent, the problem of ZIB color deviation has been reduced, but it is recommended to adjust the color appropriately according to the art style
|
| 20 |
|
| 21 |
+
<p align="center">
|
| 22 |
+
<img src="6.png" width="1200"/>
|
| 23 |
+
</p>
|
| 24 |
+
|
| 25 |
- inference cfg: 1.0（建议1.0）
|
| 26 |
- inference steps: 10（10-15步）
|
| 27 |
- sampler / scheduler: Euler / simple
|
|
|
|
| 29 |
The art style leans towards realism
|
| 30 |
Retains ZIB's creative ability and reduces the collapse of Human anatomy.
|
| 31 |
|
| 32 |
+
<p align="center">
|
| 33 |
+
<img src="3.png" width="1200"/>
|
| 34 |
+
</p>
|
| 35 |
+
|
| 36 |
+
<p align="center">
|
| 37 |
+
<img src="4.png" width="1200"/>
|
| 38 |
+
</p>
|
| 39 |
+
|
| 40 |
## Z-Image-Distilled V1 2026/1/30
|
| 41 |
|
| 42 |
This model is a **direct distillation-accelerated version** based on the original **Z-Image** (non-Turbo) source. Its purpose is to test LoRA training effects on the Z-Image (non-turbo) version while significantly improving inference/test speed. The model **does not incorporate any weights or style from Z-Image-Turbo** at all — it is a **pure-blood version** based purely on Z-Image, effectively retaining the original Z-Image's adaptability, random diversity in outputs, and overall image style.
|