Instructions to use Ava2000/Hachimitsu_Cute_Illustrious with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use Ava2000/Hachimitsu_Cute_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", torch_dtype=torch.bfloat16, device_map="cuda") pipe.load_lora_weights("Ava2000/Hachimitsu_Cute_Illustrious") prompt = "masterpiece, best quality, colorful, " image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
- DiffusionBee
Upload The style of Hachimitsu Cute.
Browse files
The style of Hachimitsu Cute.
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
The style of Hachimitsu Cute.
|
| 2 |
+
|
| 3 |
+
I made this lora to try and reproduce the style of Hachimitsu Cute. The style is trained on images that are in a balck and white style. If you wish to strengthen or weaken the effect you can use the 'monochrome' and 'greyscale' tags in the positives or negatives.
|
| 4 |
+
|
| 5 |
+
For my positives I use: masterpiece, best quality,
|
| 6 |
+
|
| 7 |
+
And for my negatives: 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, comic,
|
| 8 |
+
|
| 9 |
+
Trigger: hach1-cut3,
|
| 10 |
+
|
| 11 |
+
Advised strength: 0.6-1.0
|
| 12 |
+
|
| 13 |
+
I also use reForge with Adetailer (only the face model), CD Turner, FreeU and SelfAttentionGuidance (only for Illustrious), but they are not a must.
|