Views
No views yet
diffusers.Krea2Transformer2DModel / Krea2Pipeline (transformer keys renamed to the diffusers
layout, per-block modulation table reshaped, and the two final-layer up/down weights dropped to
match the diffusers Krea2 port). The vae, text_encoder, tokenizer and scheduler are the
standard diffusers components.1import torch
2from diffusers import Krea2Pipeline
3pipe = Krea2Pipeline.from_pretrained("ethanfel/Krea-2-Base-Diffusers", torch_dtype=torch.bfloat16)model.name_or_path: "ethanfel/Krea-2-Base-Diffusers" and
model.arch: "krea_2".scripts/convert_krea2_community_to_diffusers.py. Weights are redistributed under the
Krea 2 Community License.