How to use callgg/fastvlm-caption with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("callgg/fastvlm-caption", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0]
https://huggingface.co/callgg/fastvlm-caption/resolve/main/vocab.json
hf download hf://callgg/fastvlm-caption/vocab.json
curl -L -o vocab.json https://huggingface.co/callgg/fastvlm-caption/resolve/main/vocab.json
