Upload 2214707/2635939/README.md with huggingface_hub
Browse files- 2214707/2635939/README.md +61 -3
2214707/2635939/README.md
CHANGED
|
@@ -1,10 +1,68 @@
|
|
| 1 |
---
|
| 2 |
license: other
|
| 3 |
tags:
|
| 4 |
-
-
|
|
|
|
|
|
|
| 5 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 6 |
Author: [Ray3780](https://civitai.com/user/Ray3780)
|
| 7 |
|
| 8 |
-
Model: [
|
|
|
|
|
|
|
| 9 |
|
| 10 |
-
|
|
|
|
| 1 |
---
|
| 2 |
license: other
|
| 3 |
tags:
|
| 4 |
+
- aesthetic
|
| 5 |
+
- style
|
| 6 |
+
- z-image
|
| 7 |
---
|
| 8 |
+
|
| 9 |
+
# Z-Image-Aesthetic(Base & Turbo) - Base v1 - 2635939
|
| 10 |
+
|
| 11 |
+
**Model Type**: LORA
|
| 12 |
+
|
| 13 |
+
**Base Model**: ZImageBase
|
| 14 |
+
|
| 15 |
+
**Trigger Words**: None
|
| 16 |
+
|
| 17 |
+
**Tags**: aesthetic, style, z-image
|
| 18 |
+
|
| 19 |
+
## Gallery
|
| 20 |
+
|
| 21 |
+
<table>
|
| 22 |
+
<tr>
|
| 23 |
+
<td><img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/780ef5af-cf21-403f-b98a-b7af7304fed7/original=true/119014972.jpeg" width="200"></td>
|
| 24 |
+
<td><img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/29a487b2-d46b-4f3c-a06e-678ff27a8674/original=true/119014986.jpeg" width="200"></td>
|
| 25 |
+
<td><img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/529038e8-b067-46b0-aa74-9c707c470172/original=true/119015277.jpeg" width="200"></td>
|
| 26 |
+
</tr>
|
| 27 |
+
<tr>
|
| 28 |
+
<td><img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/924c38eb-959d-45e8-914e-3e1867f3d45f/original=true/119015278.jpeg" width="200"></td>
|
| 29 |
+
<td><img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/6481d86c-7302-4e2d-b77c-7c76a3a5f776/original=true/119015279.jpeg" width="200"></td>
|
| 30 |
+
<td><img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/a264986b-341e-4c72-82eb-276f46794dbe/original=true/119015281.jpeg" width="200"></td>
|
| 31 |
+
</tr>
|
| 32 |
+
<tr>
|
| 33 |
+
<td><img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/46207ea5-63d9-4ef5-a5e5-4873895bc05d/original=true/119015276.jpeg" width="200"></td>
|
| 34 |
+
<td><img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/43957dbb-1d2a-427a-9f6c-01298b7d2f0d/original=true/119015280.jpeg" width="200"></td>
|
| 35 |
+
<td><img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/0a3b890f-006e-4f5d-a4dc-5cd630540a32/original=true/119015282.jpeg" width="200"></td>
|
| 36 |
+
</tr>
|
| 37 |
+
<tr>
|
| 38 |
+
<td><img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/f853c694-5859-4097-a99a-47acd1742ab0/original=true/119015283.jpeg" width="200"></td>
|
| 39 |
+
</tr>
|
| 40 |
+
</table>
|
| 41 |
+
|
| 42 |
+
## Description
|
| 43 |
+
|
| 44 |
+
Z-Image Lora training test, Used for Z-Image aesthetic enhancement, improving illustration and artistic concepts.
|
| 45 |
+
|
| 46 |
+
Z image turbo v1: Recommended settings: heunpp2 + linear\_quadratic, cfg: 1.5, step: 20, 0.8-1.2
|
| 47 |
+
|
| 48 |
+
Z image Base v1: euler\_ancesral + beta,30 step,4 cfg,0.6-1 weight
|
| 49 |
+
|
| 50 |
+
Try it online: [Tensor](https://tensor.art/zh/models/958963906376694050/Z-Image-Aesthetic-BASE-TEST1) | [Seaart](https://www.seaart.ai/zhCN/models/detail/dc4b265266868ae7fc75ae4256900b8d) | [Liblib](https://www.liblib.art/modelinfo/a2b0057dd5ce4c008419ce9f7057be0e?from=personal_page&versionUuid=f1c4e9664417420b979967f8cfe3d1c7)
|
| 51 |
+
|
| 52 |
+
Z image turbo v1: The LoRa dataset uses a variety of training sets, which affects various styles, including realism, illustration, and animation. It also fixes the aesthetic issues of Z-image. Because LoRa training disrupts the acceleration effect, it requires 20 steps and cfg 1.5-2.0 to be effective. You can try the others yourself.
|
| 53 |
+
|
| 54 |
+
Due to the difficulty of Z-Image training, the step count and CFG need to be increased. I will update this when a better training method is available in future Base versions. Have fun!
|
| 55 |
+
|
| 56 |
+
Z image Base v1: Z image Base v1 has been updated; other versions are only released on TensorArt.
|
| 57 |
+
|
| 58 |
+
we sincerely apologize to users who previously downloaded the z-image base v1 version. as there was no Zimagebase category on Civita at the time of the lora's release, it was mistakenly labeled as Zimgturbo. please try using the [base version](https://civitai.com/models/2342797/z-image-base). or try it on [tensorart](https://tensor.art/zh/models/958963906376694050/Z-Image-Aesthetic-BASE-TEST1) online
|
| 59 |
+
|
| 60 |
+
---
|
| 61 |
+
|
| 62 |
Author: [Ray3780](https://civitai.com/user/Ray3780)
|
| 63 |
|
| 64 |
+
Model: [CivitAI Model Page](https://civitai.com/models/2214707?modelVersionId=2635939)
|
| 65 |
+
|
| 66 |
+
Archive: [CivArchive Page](https://civarchive.com/models/2214707?modelVersionId=2635939)
|
| 67 |
|
| 68 |
+
<!-- Version: 20260422_v4_update -->
|