How to use Tencent-Hunyuan/HunyuanDiT-Diffusers-Distilled with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("Tencent-Hunyuan/HunyuanDiT-Diffusers-Distilled", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0]
Are there any other methods for generating in one or more steps that support hyper sd? Can accelerate image generation, currently generating slower
· Sign up or log in to comment
