Instructions to use Danrisi/NiceGirls_Anima with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use Danrisi/NiceGirls_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("Danrisi/NiceGirls_Anima", dtype=torch.bfloat16, device_map="cuda") prompt = "RAW photo, photography, amateur quality, candid style. spider-gwen from Spider-Verse kneeling on the floor, she is barefoot, femine body with wide hips, sexy soles, blond hair, relaxed expression, looking back at the viewer, from back view angle, on kneels. her ankles locked in wooden stocks," image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
- DiffusionBee
I didn't get this results, how do you do it?
#1
by gabluz - opened
Hi. I'm trying to train Anima lora models with cosplay models, some real stuff too rsrs, but their faces get too blurry... how did you manage to get these results? I'm using ultrafine anima3 as base. Do you have a script you could share? I can train anime models or cartoons just fine.