Instructions to use jiuhai/BLIP3o-Model-4B-Pretrain with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use jiuhai/BLIP3o-Model-4B-Pretrain with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("jiuhai/BLIP3o-Model-4B-Pretrain", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
Question about GenEval metric
#1
by fengyang0317 - opened
Thanks for releasing the pretrain checkpoint. I run the GenEval using this checkpoint and get overall score 0.45851. Is this expected? Using BLIP3o/BLIP3o-Model-4B, I can get overall score 0.81653.
Thank you.