Instructions to use Chroma111/CivitAI-Archive-2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use Chroma111/CivitAI-Archive-2 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("Chroma111/CivitAI-Archive-2", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
Upload 817285/921261/README.md with huggingface_hub
Browse files- 817285/921261/README.md +87 -4
817285/921261/README.md
CHANGED
|
@@ -1,11 +1,94 @@
|
|
| 1 |
-
|
| 2 |
---
|
| 3 |
license: other
|
| 4 |
tags:
|
| 5 |
-
-
|
|
|
|
|
|
|
|
|
|
|
|
|
| 6 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 7 |
Author: [tarakozushi](https://civitai.com/user/tarakozushi)
|
| 8 |
|
| 9 |
-
Model: [
|
|
|
|
|
|
|
| 10 |
|
| 11 |
-
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
license: other
|
| 3 |
tags:
|
| 4 |
+
- character
|
| 5 |
+
- girls
|
| 6 |
+
- photorealistic
|
| 7 |
+
- unrealistic
|
| 8 |
+
- woman
|
| 9 |
---
|
| 10 |
+
|
| 11 |
+
# WhippeMilk_2D(Asian Girl SDXL) - beta - 921261
|
| 12 |
+
|
| 13 |
+
**Model Type**: LoCon
|
| 14 |
+
|
| 15 |
+
**Base Model**: SDXL 1.0
|
| 16 |
+
|
| 17 |
+
**Trigger Words**: None
|
| 18 |
+
|
| 19 |
+
**Tags**: character, girls, photorealistic, unrealistic, woman
|
| 20 |
+
|
| 21 |
+
## Gallery
|
| 22 |
+
|
| 23 |
+
<table>
|
| 24 |
+
<tr>
|
| 25 |
+
<td><img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/6a47c54c-100d-4c43-9f86-352b2c09cb83/original=true/32777270.jpeg" width="200"></td>
|
| 26 |
+
<td><img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/390280c8-74bb-4eaf-8cd6-5212e5201a7f/original=true/32778093.jpeg" width="200"></td>
|
| 27 |
+
<td><img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/bda2bf66-3cf4-4c3d-9e90-da804bbd84d2/original=true/32778116.jpeg" width="200"></td>
|
| 28 |
+
</tr>
|
| 29 |
+
<tr>
|
| 30 |
+
<td><img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/2c0264e6-93a3-4497-b370-541f8b5f7cd5/original=true/32778126.jpeg" width="200"></td>
|
| 31 |
+
<td><img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/fe7e5532-a4cb-4740-8ddc-dcf4bd85d857/original=true/33329839.jpeg" width="200"></td>
|
| 32 |
+
</tr>
|
| 33 |
+
</table>
|
| 34 |
+
|
| 35 |
+
## Description
|
| 36 |
+
|
| 37 |
+
東洋系の美しい女性を出せるよう学習したLoRAです。
|
| 38 |
+
学習モデルにアニメモデルとして人気のあるAnimagineXLを使用することにより、
|
| 39 |
+
手・指や細部の描画向上を目指しました。
|
| 40 |
+
|
| 41 |
+
リアルな中に絶妙にブレンドされた2.5D感の美しさや可愛らしさをお楽しみください。
|
| 42 |
+
|
| 43 |
+
学習モデル:Animagine XL V31(SDXL)
|
| 44 |
+
推奨サンプラー:DPM++2M SDE Karras / DPM++2Sa Karras / Euler a
|
| 45 |
+
サンプリングステップ:25
|
| 46 |
+
CFG Scale:3.5
|
| 47 |
+
A Detailer
|
| 48 |
+
1st: mediapipe face mesh eyes only
|
| 49 |
+
2nd: hand\_yolov8n.pt
|
| 50 |
+
LoRAのウェイトは0.6〜1.0推奨
|
| 51 |
+
※数値や設定は自由に変更してみてください。LoRAのウェイトを落とすことにより2.5D感、アニメ感が強調されます。
|
| 52 |
+
|
| 53 |
+
プロンプトについて/
|
| 54 |
+
AnimagineXLのプロンプト記述ルールに則っています。
|
| 55 |
+
SDXLの自然言語プロンプトではなくタグ記述となります。
|
| 56 |
+
"Quality Modifiers(評価修飾子)"と”Aesthetic Tags(美的タグ)”は
|
| 57 |
+
特に意識して使用するのがお勧めです。
|
| 58 |
+
|
| 59 |
+
詳しいプロンプトのコツやライセンスについて
|
| 60 |
+
AnimagineXLのモデルのページをご確認ください。
|
| 61 |
+
|
| 62 |
+
✣ ✣ ✣ ✣ ✣
|
| 63 |
+
|
| 64 |
+
LoRA is trained to produce beautiful oriental women.
|
| 65 |
+
By using Animagine XL, a popular anime model, as the learning model,
|
| 66 |
+
we aimed to improve the drawing of hands, fingers, and details.
|
| 67 |
+
|
| 68 |
+
Enjoy the beauty and cuteness of a 2.5D feel that is exquisitely blended with realism.
|
| 69 |
+
|
| 70 |
+
Learning model: Animagine XL V31 (SDXL)
|
| 71 |
+
Recommended sampler: DPM++2M SDE Karras / DPM++2Sa Karras / Euler a
|
| 72 |
+
Sampling step: 25
|
| 73 |
+
CFG Scale: 3.5
|
| 74 |
+
A Detailer
|
| 75 |
+
1st: mediapipe face mesh eyes only
|
| 76 |
+
2nd: hand\_yolov8n.pt
|
| 77 |
+
\*Feel free to change the values and settings. By reducing the weight of LoRA, the 2.5D and anime feel is emphasized.
|
| 78 |
+
|
| 79 |
+
About prompts/
|
| 80 |
+
Follows the prompt description rules of AnimagineXL.
|
| 81 |
+
These are tag descriptions rather than SDXL natural language prompts.
|
| 82 |
+
We recommend that you pay particular attention to the use of "Quality Modifiers" and "Aesthetic Tags".
|
| 83 |
+
|
| 84 |
+
For detailed prompt tips and licenses, please check the AnimagineXL model page.
|
| 85 |
+
|
| 86 |
+
---
|
| 87 |
+
|
| 88 |
Author: [tarakozushi](https://civitai.com/user/tarakozushi)
|
| 89 |
|
| 90 |
+
Model: [CivitAI Model Page](https://civitai.com/models/817285?modelVersionId=921261)
|
| 91 |
+
|
| 92 |
+
Archive: [CivArchive Page](https://civarchive.com/models/817285?modelVersionId=921261)
|
| 93 |
|
| 94 |
+
<!-- Version: 20260426_upload -->
|