Upload 2398642/2725629/README.md with huggingface_hub
Browse files- 2398642/2725629/README.md +40 -3
2398642/2725629/README.md
CHANGED
|
@@ -1,10 +1,47 @@
|
|
| 1 |
---
|
| 2 |
license: other
|
| 3 |
tags:
|
| 4 |
-
-
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 6 |
Author: [funkytowns](https://civitai.com/user/funkytowns)
|
| 7 |
|
| 8 |
-
Model: [
|
|
|
|
|
|
|
| 9 |
|
| 10 |
-
|
|
|
|
| 1 |
---
|
| 2 |
license: other
|
| 3 |
tags:
|
| 4 |
+
- close-up
|
| 5 |
+
- concept
|
| 6 |
+
- cum on face
|
| 7 |
+
- facial
|
| 8 |
+
- photography
|
| 9 |
---
|
| 10 |
+
|
| 11 |
+
# Z Image Base - Facials - v1.0 3000 steps - 2725629
|
| 12 |
+
|
| 13 |
+
**Model Type**: LORA
|
| 14 |
+
|
| 15 |
+
**Base Model**: ZImageBase
|
| 16 |
+
|
| 17 |
+
**Trigger Words**: facial
|
| 18 |
+
|
| 19 |
+
**Tags**: close-up, concept, cum on face, facial, photography
|
| 20 |
+
|
| 21 |
+
## Gallery
|
| 22 |
+
|
| 23 |
+
<table>
|
| 24 |
+
<tr>
|
| 25 |
+
<td><img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/f8827310-507a-43b7-a5b7-6af608029388/original=true/122479920.jpeg" width="200"></td>
|
| 26 |
+
<td><img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/ce321d21-5723-4d64-942b-12abe5d16a25/original=true/122480118.jpeg" width="200"></td>
|
| 27 |
+
<td><img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/936ccee7-700a-4f8d-99d6-d4ef5d33d133/original=true/122480298.jpeg" width="200"></td>
|
| 28 |
+
</tr>
|
| 29 |
+
</table>
|
| 30 |
+
|
| 31 |
+
## Description
|
| 32 |
+
|
| 33 |
+
The lack of facial LoRAs for Z Image Base was troubling so I trained my own to my liking.
|
| 34 |
+
|
| 35 |
+
Trained on 104 manually-tagged images. The captions were a mix of danbooru-style tags and natural language.
|
| 36 |
+
|
| 37 |
+
The trigger word is "facial" and the LoRA was intended primarily for kneeling/lying down poses where the female subject is facing the subject straight-on and close-up, though it might be more flexible than that. It should output respectable loads on the face length-wise instead of those disappointing dribbles, puddles, or nonsense directions that I often see online.
|
| 38 |
+
|
| 39 |
+
---
|
| 40 |
+
|
| 41 |
Author: [funkytowns](https://civitai.com/user/funkytowns)
|
| 42 |
|
| 43 |
+
Model: [CivitAI Model Page](https://civitai.com/models/2398642?modelVersionId=2725629)
|
| 44 |
+
|
| 45 |
+
Archive: [CivArchive Page](https://civarchive.com/models/2398642?modelVersionId=2725629)
|
| 46 |
|
| 47 |
+
<!-- Version: 20260422_v4_update -->
|