vq-diffusion-ithq

---

README(From Huggingface)

VQ Diffusion

• Paper

• Original Repo

• Authors: Shuyang Gu, Dong Chen, et al.

#!pip install diffusers[torch] transformers
import paddle
from diffusers import VQDiffusionPipeline

pipeline = VQDiffusionPipeline.from_pretrained("microsoft/vq-diffusion-ithq", dtype=paddle.float16)
pipeline = pipeline

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.

Model Files

• README.md (850.0 B)

• learned_classifier_free_sampling_embeddings/config.json (157.0 B)

• learned_classifier_free_sampling_embeddings/model_state.pdparams (154.3 KB)

• model_index.json (534.0 B)

• scheduler/scheduler_config.json (248.0 B)

• text_encoder/model_config.json (266.0 B)

• text_encoder/model_state.pdparams (241.0 MB)

• tokenizer/added_tokens.json (2.0 B)

• tokenizer/merges.txt (512.3 KB)

• tokenizer/special_tokens_map.json (377.0 B)

• tokenizer/tokenizer_config.json (799.0 B)

• tokenizer/vocab.json (1.0 MB)

• transformer/config.json (396.0 B)

• transformer/model_state.pdparams (5.1 GB)

• vqvae/config.json (603.0 B)

• vqvae/model_state.pdparams (244.2 MB)

Back to Main