CrispyFeSo4

Sorry to bother! But I can't find the section for the Implicit Position Encoding module. Did I miss anything? Please inform. Thank you for your assistance!

Questions about Input Latent for Appearance Control Model

5

Could you please clarify whether the input to the appearance control model is the latent of the reference image or the noisy latent after DDIM inversion processing? thanks!!

RuntimeError: tokens must have 4 dimensions

3

`File "/home/dust3r/croco/models/curope/curope2d.py", line 22, in forward _kernels.rope_2d( tokens, positions, base, F0 ) RuntimeError: tokens must have 4 dimensions` I encountered this error, can anyone tell me how to fix it?...

RuntimeError: tokens must have 4 dimensions

2

`File "/home/dust3r/croco/models/curope/curope2d.py", line 22, in forward _kernels.rope_2d( tokens, positions, base, F0 ) RuntimeError: tokens must have 4 dimensions` I encountered this error, can anyone tell me how to fix it?...

huggingface/tokenizers ERROR

1

``` Epoch 019 Step 00270: psnr: 19.72 l_rgb: 0.010838 l_depth: 0.001648 l_trans: 0.000423: 100%|█| 270/270 [00:31