Instructions to use Ava2000/Mimonel_illustrious with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use Ava2000/Mimonel_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/Mimonel_illustrious") prompt = "masterpiece, best quality, (traditional media,shiny skin, flat color)," image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
- DiffusionBee
Mimonel Style - Illustrious

- Prompt
- masterpiece, best quality, (traditional media,shiny skin, flat color),
- 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, comic,
Model description
The style of Mimonel.
I made this lora to try and reproduce the style of Mimonel. The style lora by itself gets really close, but is not able to capture it in complete perfection (could be the checkpoint or the dataset being mostly comic images). So adding the artist tag 'mimonel' could help with the finishing touches. Because this style uses comic almost exclusively comic pages in the dataset, it tends to add them as artifacts. So if you don't want those, then us 'comic' in your negatives and you might want to give 'solo' some extra strength for single characters.
For my positives I use: masterpiece, best quality, (traditional media,shiny skin, flat color),
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,
Trigger: m1m0n3l,
Advised strength: 0.6-1.0
I also use reForge with Adetailer (only the face model), CD Turner, FreeU and SelfAttentionGuidance (only for Illustrious), but they are not a must.
Trigger words
You should use m1m0n3l to trigger the image generation.
Download model
Download them in the Files & versions tab.
- Downloads last month
- 3
Model tree for Ava2000/Mimonel_illustrious
Base model
KBlueLeaf/kohaku-xl-beta5