Improved Vector Quantized Diffusion Models
Paper • 2205.16007 • Published
import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("microsoft/vq-diffusion-ithq", dtype=torch.bfloat16, device_map="cuda")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]VQ Diffusion
Authors: Shuyang Gu, Dong Chen, et al.
#!pip install diffusers[torch] transformers
import torch
from diffusers import VQDiffusionPipeline
pipeline = VQDiffusionPipeline.from_pretrained("microsoft/vq-diffusion-ithq", torch_dtype=torch.float16)
pipeline = pipeline.to("cuda")
output = pipeline("teddy bear playing in the pool", truncation_rate=1.0)
image = output.images[0]
image.save("./teddy_bear.png")
Contribution: This model was contribution by williamberman in VQ-diffusion.
- Downloads last month
- 74
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support