Except hair coloe change only, but hair style of some results are change

[kasim0226]

I want to change hair color on FFHQ data, however hairstyle of some of results are change. Did I do wrong? The following is my command

python scripts/inference.py \ --exp_dir=./experiment \ --checkpoint_path=../pretrained_models/hairclip.pt \ --latents_test_path=./latents.pt \ --editing_type=color \ --input_type=text \ --color_description=red

[wty-ustc]

It looks like your run is fine. I doubt if there is some gap between the data, you can test the CelebA-HQ data to check if there is any problem, if not, you may need to retrain a HairCLIP on the FFHQ dataset for better results.

[wty-ustc]

I just checked the test results and found that for people with very short hair there may be a problem with visual hairstyle changes due to non-uniform coloring. For other lengths of hair there is no such problem.

[wty-ustc]

However, another version of the training does not have this problem, you can retrain HairCLIP and maybe the problem will disappear.

[kasim0226]

Got it. Thank you for your reply.

If I only want color change, would the follwing setting help when I train new model? --hairstyle_manipulation_prob=0 \ --color_manipulation_prob=1 \ --both_manipulation_prob=0 \ --color_text_manipulation_prob=1 \

[wty-ustc]

Yes, and it probably converges very fast. Probably tens of thousands of iterations later it's already trained.

[kasim0226]

Thank you for your suguesstions.

[wty-ustc]

Have fun with it!