How to use wavespeed/FLUX.1-dev-e4m3 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("wavespeed/FLUX.1-dev-e4m3", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0]
https://huggingface.co/wavespeed/FLUX.1-dev-e4m3/resolve/7a446aeee7bb4b397d4e95cc8dcb2bf420203dfa/tokenizer_2/tokenizer.json
hf download hf://wavespeed/FLUX.1-dev-e4m3@7a446aeee7bb4b397d4e95cc8dcb2bf420203dfa/tokenizer_2/tokenizer.json
curl -L -o tokenizer.json https://huggingface.co/wavespeed/FLUX.1-dev-e4m3/resolve/7a446aeee7bb4b397d4e95cc8dcb2bf420203dfa/tokenizer_2/tokenizer.json
