Instructions to use lorayap/Krea2_Asian_Character with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use lorayap/Krea2_Asian_Character with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("krea/Krea-2-Turbo", dtype=torch.bfloat16, device_map="cuda") pipe.load_lora_weights("lorayap/Krea2_Asian_Character") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Inference
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
- DiffusionBee
Update README.md
Browse files
README.md
CHANGED
|
@@ -4,54 +4,58 @@ tags:
|
|
| 4 |
- lora
|
| 5 |
- diffusers
|
| 6 |
- template:diffusion-lora
|
| 7 |
-
|
| 8 |
-
-
|
| 9 |
-
url: images/1.png
|
| 10 |
-
text: >-
|
| 11 |
-
harukakitano Full-body shot of a woman in a casual dress, high definition
|
| 12 |
-
with no noise, sharp photography, set against the streets of Kyoto, Japan.
|
| 13 |
-
- output:
|
| 14 |
-
url: images/2.png
|
| 15 |
-
text: >-
|
| 16 |
-
harukakitano Close-up upper body shot of a woman in a casual dress, high
|
| 17 |
-
definition with no noise, sharp photography, against a pure white studio
|
| 18 |
-
background.
|
| 19 |
base_model: krea/Krea-2-Turbo
|
| 20 |
-
instance_prompt: harukakitano
|
| 21 |
license: mit
|
| 22 |
---
|
| 23 |
|
| 24 |
-
#
|
| 25 |
|
| 26 |
-
|
| 27 |
|
| 28 |
**For learning and research purposes only.**
|
| 29 |
|
| 30 |
-
##
|
| 31 |
|
| 32 |
-
|
| 33 |
-
-
|
| 34 |
-
|
| 35 |
-
|
| 36 |
-
- **License**: MIT
|
| 37 |
|
| 38 |
-
|
| 39 |
|
| 40 |
-
|
| 41 |
|
| 42 |
-
##
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 43 |
|
| 44 |
-
|
| 45 |
-
2. Include the trigger word `harukakitano` in your prompt.
|
| 46 |
-
3. Start with a weight of 0.8 and adjust as needed.
|
| 47 |
|
| 48 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 49 |
|
| 50 |
-
|
|
|
|
|
|
|
| 51 |
|
| 52 |
-
##
|
| 53 |
|
| 54 |
-
|
| 55 |
|
| 56 |
---
|
| 57 |
|
|
|
|
| 4 |
- lora
|
| 5 |
- diffusers
|
| 6 |
- template:diffusion-lora
|
| 7 |
+
- krea2
|
| 8 |
+
- character
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 9 |
base_model: krea/Krea-2-Turbo
|
|
|
|
| 10 |
license: mit
|
| 11 |
---
|
| 12 |
|
| 13 |
+
# Krea2 Asian Character LoRA Collection
|
| 14 |
|
| 15 |
+
Open-source character LoRAs trained on **Krea-2-Turbo**, focused on Japanese / Asian female characters.
|
| 16 |
|
| 17 |
**For learning and research purposes only.**
|
| 18 |
|
| 19 |
+
## Available Characters
|
| 20 |
|
| 21 |
+
| Character | Trigger Word | File | Recommended Weight |
|
| 22 |
+
|-----------|--------------|------|--------------------|
|
| 23 |
+
| Kitano Haruka (北野遥) | `harukakitano` | `harukakitano.safetensors` | 0.8 ~ 1.0 |
|
| 24 |
+
| Nagi Hikaru (凪光) | `nagihikaru` | `nagihikaru.safetensors` | 0.8 ~ 1.0 |
|
|
|
|
| 25 |
|
| 26 |
+
> More characters will be added continuously.
|
| 27 |
|
| 28 |
+
---
|
| 29 |
|
| 30 |
+
## 1. Kitano Haruka (北野遥)
|
| 31 |
+
|
| 32 |
+
**Trigger**: `harukakitano`
|
| 33 |
+
**Weight**: 0.8 ~ 1.0
|
| 34 |
+
|
| 35 |
+

|
| 36 |
+

|
| 37 |
+
|
| 38 |
+
---
|
| 39 |
|
| 40 |
+
## 2. Nagi Hikaru (凪光)
|
|
|
|
|
|
|
| 41 |
|
| 42 |
+
**Trigger**: `nagihikaru`
|
| 43 |
+
**Weight**: 0.8 ~ 1.0
|
| 44 |
+
|
| 45 |
+

|
| 46 |
+

|
| 47 |
+
|
| 48 |
+
---
|
| 49 |
+
|
| 50 |
+
## Usage
|
| 51 |
|
| 52 |
+
1. Download the corresponding `.safetensors` file and place it in your LoRA folder (ComfyUI / Forge / A1111 etc.).
|
| 53 |
+
2. Add the **trigger word** in the prompt.
|
| 54 |
+
3. Start with weight **0.8**, then adjust.
|
| 55 |
|
| 56 |
+
## Base Model
|
| 57 |
|
| 58 |
+
- [krea/Krea-2-Turbo](https://huggingface.co/krea/Krea-2-Turbo)
|
| 59 |
|
| 60 |
---
|
| 61 |
|