Instructions to use Ava2000/Mosha_Illustrious with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use Ava2000/Mosha_Illustrious with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("calcuis/illustrious", dtype=torch.bfloat16, device_map="cuda") pipe.load_lora_weights("Ava2000/Mosha_Illustrious") prompt = "masterpiece, best quality, traditional media, sketch, jaggy lines," image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
- DiffusionBee
Upload Mosha Style
Browse files- Mosha Style +13 -0
Mosha Style
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
Mosha Style
|
| 2 |
+
|
| 3 |
+
This lora is made in the style of the artist Mosha. This artist disapeared years ago, so this style lora is my way of keeping this style alive.
|
| 4 |
+
|
| 5 |
+
For all versions I recommend you use: masterpiece, best quality, traditional media, sketch, jaggy lines, in your prompt and I myself am using the following negative prompt: text, long body, lowres, cropped, lowres, jpeg artifacts, (signature, artist name, watermark, username, english text, signature:1.4), simple background, conjoined, out of frame, out of frame, censored, bar censor,
|
| 6 |
+
|
| 7 |
+
The above showcase images were made with Addetailer extension enabled and using a face model.
|
| 8 |
+
|
| 9 |
+
This LoRa is trained on llustrious 0.1, but I made the above showcase images in different checkpoints, because their style was more to my liking.
|
| 10 |
+
|
| 11 |
+
The Trigger is: m0sha style,
|
| 12 |
+
|
| 13 |
+
Advised strength: 0.6-1.0
|