Instructions to use Ava2000/Optional_Typo_Anima with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use Ava2000/Optional_Typo_Anima with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("oron1208/OOO_Anima", dtype=torch.bfloat16, device_map="cuda") pipe.load_lora_weights("Ava2000/Optional_Typo_Anima") prompt = "masterpiece, best quality," image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
- DiffusionBee
Optional Typo - Anima

- Prompt
- masterpiece, best quality,
- Negative Prompt
- worst quality, low quality, score_1, score_2, score_3, bad hands, mutated hands, extra fingers, missing fingers, extra digits, fewer digits, fused fingers, deformed hands, poorly drawn hands, bad anatomy, deformed fingers, hands with too many fingers, (artist name, watermark, username, english text, signature:1.5),

- Prompt
- masterpiece, best quality,
- Negative Prompt
- worst quality, low quality, score_1, score_2, score_3, bad hands, mutated hands, extra fingers, missing fingers, extra digits, fewer digits, fused fingers, deformed hands, poorly drawn hands, bad anatomy, deformed fingers, hands with too many fingers, (artist name, watermark, username, english text, signature:1.5),
Model description
The style of Optional Typo.
I made this lora to try and reproduce the style of Optional Typo. The style works well out of the box with the base quality tags. I myself also like the more sketch like images they created. You can recreate those with addin the following quality tags: 'traditional media, jaggy lines, sketch,'
For my positives I use: masterpiece, best quality,
And for my negatives: worst quality, low quality, score_1, score_2, score_3, bad hands, mutated hands, extra fingers, missing fingers, extra digits, fewer digits, fused fingers, deformed hands, poorly drawn hands, bad anatomy, deformed fingers, hands with too many fingers, (artist name, watermark, username, english text, signature:1.5),
My negatives are a bit different with this one, because the artist name got baked in (this was not the plan, but I forgot to check my old dataset). So that's why I added some more tags to counter it.
Trigger: typ0,
Artist trigger: optionaltypo, (could help getting the style exactly right)
Advised strength: 0.6-1.0
You can use the aDetailer plugin (NeoForge) with a face or eye model to get slightly better face and eye results.
Trigger words
You should use typ0 to trigger the image generation.
Download model
Download them in the Files & versions tab.
- Downloads last month
- 5
Model tree for Ava2000/Optional_Typo_Anima
Base model
nvidia/Cosmos-Predict2-2B-Text2Image