import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("nebulette/aniportrait-lfm", dtype=torch.bfloat16, device_map="cuda")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]UNet
Flow matching (time_shift_type is 'linear') and the LFM2.5 text encoder on the top of Aniimage.
Due to the lack of training data, the only prompt it understands is anime portraits.
What is more interesting is that the model did not forget all the CLIP embeddings with
the new v-prediction, despite it has been trained only on LFM embeddings. See the image below:
Source data:
- anime_style_portrait
- gelbooru (landscape)
- portraits_512
- wikiart_face
- Downloads last month
- 8
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for nebulette/aniportrait-lfm
Base model
8BitStudio/Aniimage-2