Instructions to use eimiss/EimisAnimeDiffusion_1.0v with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use eimiss/EimisAnimeDiffusion_1.0v with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("eimiss/EimisAnimeDiffusion_1.0v", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
- DiffusionBee
Was the leaked NAI model, or a merge containing it, the base for this model?
For the sake of removing the possibility of accidentally using the leaked model in further finetuning, an answer to this would be very much appreciated, many thanks :)
A base - no. A merge yes, could be because of the models I merged it with. Can't confirm it because I forgot which models I merged it with. Next update I will purely gonna use only waifu diffusion or something from the not "leaked" category.
However, I don't want to update it right now, because the model itself is not going to improve anymore. I pretty much maxed out everything what I could have done with it, and "remaking" it is going to be expensive and for now a bit of the time waste. I will try to update it again when WD 1.4 releases. Purely on that model as a base and nothing more.