Carlyx

Hi, your work is awesome. Could you release the code for training?

evaluate_PRMSE_AUCON

1

When I run utils.py, errors were called: 'Detector' object has no attribute 'detect_facepose' 'Fex' object has no attribute 'facepose' 'Fex' object has no attribute 'Pitch'

Hi, I have some questions about the selection of dataset in your work. You put the index of training data into the txt file. However, could you tell me according...

Hi，your work is amazing! I am currently performing related experiments, but the face detection part is always not satisfactory. It may be a problem with my code. Could you release...

KeyError: 'cond_stage_model.transformer.text_model.embeddings.token_embedding.weight'

2

https://github.com/adobe-research/custom-diffusion/blob/51a498fa135ccdbac8e947e830710ae7d32b2d38/train.py#L765 And I run : ``` bash scripts/finetune_real.sh "cat" data/cat real_reg/samples_cat cat finetune_addtoken.yaml delta_cat.ckpt ```

ID Consistency

1

Hi, awesome work! In fact, I use a dancing video as input, and try to change hair by "+ with red hair". However, I just get a different result in...

Transfer SMPL

2

Hi, if I don't set '--view_transfer' for smpl transfer, the normal rendered is abnormal. But if I set '--view_transfer', the human in normal is fixed in one position to perform...