How to use from the
Use from the
Transformers library
# Use a pipeline as a high-level helper
# Warning: Pipeline type "image-to-text" is no longer supported in transformers v5.
# You must load the model directly (see below) or downgrade to v4.x with:
# 'pip install "transformers<5.0.0'
from transformers import pipeline

pipe = pipeline("image-to-text", model="shadowlilac/visor")
# Load model directly
from transformers import AutoProcessor, AutoModelForImageTextToText

processor = AutoProcessor.from_pretrained("shadowlilac/visor")
model = AutoModelForImageTextToText.from_pretrained("shadowlilac/visor")
Quick Links

Visor - Natural language Anime Tagging

Visor is a natural-language-based image tagging model based on the BLIP model architecture.

Potential Use cases can be to caption anime images for training diffusion models

Downloads last month
14
Safetensors
Model size
0.5B params
Tensor type
BF16
ยท
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Space using shadowlilac/visor 1