Image-to-Image
Transformers
Safetensors
English
unitok
computer-vision
image-reconstruction
vector-quantization
tokenizer
multimodal
# Load model directly
from transformers import UniTok
model = UniTok.from_pretrained("XuejiFang/UniTok_transformers", device_map="auto")Quick Links
UniTok Transformers
Key Features:
- 📦 Transformers Compatible: Standard
from_pretrained()andsave_pretrained()support
For more details, visit: https://github.com/XuejiFang/UniTok_transformers
Disclaimer
This is an unofficial implementation with Hugging Face integration. Original work: FoundationVision/UniTok
- Downloads last month
- 6
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-to-image", model="XuejiFang/UniTok_transformers")