YanzuoLu / CFLD

[CVPR 2024 Highlight] Coarse-to-Fine Latent Diffusion for Pose-Guided Person Image Synthesis
MIT License
165 stars 11 forks source link

about Inference #7

Closed ButoneDream closed 6 months ago

ButoneDream commented 6 months ago

how can i inference with my own local images? image it seems like test all the testdataset?

YanzuoLu commented 6 months ago

We have a demonstration of arbitrary pose in the supplementary materials (haven't included in our arXiv preprint), which is in line with inferencing with our own images. I will clean it up and upload that .ipynb file later this week.

ButoneDream commented 6 months ago

thanks !

YanzuoLu commented 6 months ago

We upload the jupyter notebook for inference/reasoning. You could modify it as you want, e.g. replacing the conditional image with your customized one and randomly sampling a target pose from the test dataset.

justinday123 commented 2 months ago

Is there no way to use my own target pose?