How to use diffusers-internal-dev/private-model with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("diffusers-internal-dev/private-model", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0]
Update transformer config to use joint_attention_dim and make it so that pos_embed_max_size is configurable in order to deal with multiple model sizes.
joint_attention_dim
pos_embed_max_size
· Sign up or log in to comment
