Instructions to use Benevolent/NyanchtaStyle with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use Benevolent/NyanchtaStyle with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("playgroundai/playground-v2.5-1024px-aesthetic", dtype=torch.bfloat16, device_map="cuda") pipe.load_lora_weights("Benevolent/NyanchtaStyle") prompt = "(best quality), (masterpiece), (highres), (depth of field), perfect lighting, detailed face, 1 girl, detailed eyes, (looking at viewer),(sharp focus) <lora:eula2-000009:0.8>, euladef, eularnd, yellow eyes, light blue hair, large breasts, hair down,<lora:Nyantcha:1>, <lora:Single bare shoulder shirt:1>, single bare shoulder shirt long, naked shirt, cleavage, bottomless, arms behind back, smile, looking at viewer, sitting on bed, bedroom, house, indoors, morning time," image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
- DiffusionBee
ThiccWithaQ

- Prompt
- (best quality), (masterpiece), (highres), (depth of field), perfect lighting, detailed face, 1 girl, detailed eyes, (looking at viewer),(sharp focus) <lora:eula2-000009:0.8>, euladef, eularnd, yellow eyes, light blue hair, large breasts, hair down,<lora:Nyantcha:1>, <lora:Single bare shoulder shirt:1>, single bare shoulder shirt long, naked shirt, cleavage, bottomless, arms behind back, smile, looking at viewer, sitting on bed, bedroom, house, indoors, morning time,
- Negative Prompt
- ng_deepnegative_v1_75t, easynegative, negative_hand, negative_hand-neg, lowres, (bad anatomy, bad proportions), blurry, text, error, missing fingers, missing arms, missing legs, short legs, extra digit, 2girls, out of frame, petite, distorted perspective, watermark, artist name, username,(censoring, censorship, white bars, black bars), head piece, hair accessory,
Trigger words
You should use <lora:Nyantcha:1> to trigger the image generation.
Download model
Weights for this model are available in Safetensors format.
Download them in the Files & versions tab.
- Downloads last month
- 8