How to use optima-tools-ch/image-medium with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("optima-tools-ch/image-medium", 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/optima-tools-ch/image-medium/resolve/main/tokenizer/vocab.json
hf download hf://optima-tools-ch/image-medium/tokenizer/vocab.json
curl -L -o vocab.json https://huggingface.co/optima-tools-ch/image-medium/resolve/main/tokenizer/vocab.json
