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

Safetensors

Model size

0.4B params

Tensor type

F32

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

Finetuned

(1)

this model