problem in simswap inference #483

New Issue

2025-03-10T17:13:07+01:00

Maryam483 commented

2025-03-10 17:13:07 +01:00

(Migrated from github.com)

@neuralchen @R3PO97 @luoxyhappy @bfirsh yes the above .zip file works , thanks alot, but when i run this code as per steps mention in colab file, then the resulting generated video has blurr faces like an image below i have attached ??? why???
https://colab.research.google.com/github/neuralchen/SimSwap/blob/main/SimSwap%20colab.ipynb#scrollTo=wwJOwR9LNKRz

when i run:
!python test_one_image.py --name people --Arc_path arcface_model/arcface_checkpoint.tar --pic_a_path crop_224/6.jpg --pic_b_path crop_224/ds.jpg --output_path output/

it generates warnings also:
-------------- End ----------------

/content/SimSwap/models/base_model.py:70: FutureWarning: You are using torch.load with weights_only=False (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for weights_only will be flipped to True. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via torch.serialization.add_safe_globals. We recommend you start setting weights_only=True for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
pretrained_dict = torch.load(save_path)
Pretrained network G has fewer layers; The following are not initialized:
['down0', 'first_layer', 'last_layer', 'up0']

and wrong image

@neuralchen @R3PO97 @luoxyhappy @bfirsh yes the above .zip file works , thanks alot, but when i run this code as per steps mention in colab file, then the resulting generated video has blurr faces like an image below i have attached ??? why??? https://colab.research.google.com/github/neuralchen/SimSwap/blob/main/SimSwap%20colab.ipynb#scrollTo=wwJOwR9LNKRz when i run: !python test_one_image.py --name people --Arc_path arcface_model/arcface_checkpoint.tar --pic_a_path crop_224/6.jpg --pic_b_path crop_224/ds.jpg --output_path output/ it generates warnings also: -------------- End ---------------- /content/SimSwap/models/base_model.py:70: FutureWarning: You are using torch.load with weights_only=False (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for weights_only will be flipped to True. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via torch.serialization.add_safe_globals. We recommend you start setting weights_only=True for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature. pretrained_dict = torch.load(save_path) Pretrained network G has fewer layers; The following are not initialized: ['down0', 'first_layer', 'last_layer', 'up0'] and wrong image ![Image](https://github.com/user-attachments/assets/f08fe60c-c4fd-46e6-8969-7a7357f34688)

Heimdall-Nss commented

2025-03-12 15:23:34 +01:00

(Migrated from github.com)

I have the same problem, did you solve it?

Maryam483 commented

2025-03-12 16:04:09 +01:00

(Migrated from github.com)

I have the same problem, did you solve it?

I have tried but no solution

> I have the same problem, did you solve it? I have tried but no solution

luoxyhappy commented

2025-03-13 11:06:34 +01:00

(Migrated from github.com)

you need to set crop_size to 224, run: !python test_one_image.py --name people --Arc_path arcface_model/arcface_checkpoint.tar --pic_a_path crop_224/6.jpg --pic_b_path crop_224/ds.jpg --output_path output/ --crop_size 224

👍 3

wangfei1204 commented

2025-04-28 14:52:39 +02:00

(Migrated from github.com)

you need to set crop_size to 224, run: !python test_one_image.py --name people --Arc_path arcface_model/arcface_checkpoint.tar --pic_a_path crop_224/6.jpg --pic_b_path crop_224/ds.jpg --output_path output/ --crop_size 224你需要将 crop_size 设置为 224，运行：！python test_one_image.py --name people --Arc_path arcface_model/arcface_checkpoint.tar --pic_a_path crop_224/6.jpg --pic_b_path crop_224/ds.jpg --output_path output/ --crop_size 224

Thank you!

> you need to set crop_size to 224, run: !python test_one_image.py --name people --Arc_path arcface_model/arcface_checkpoint.tar --pic_a_path crop_224/6.jpg --pic_b_path crop_224/ds.jpg --output_path output/ --crop_size 224你需要将 crop_size 设置为 224，运行：！python test_one_image.py --name people --Arc_path arcface_model/arcface_checkpoint.tar --pic_a_path crop_224/6.jpg --pic_b_path crop_224/ds.jpg --output_path output/ --crop_size 224 Thank you!

garychan22 commented

2025-07-08 07:25:09 +02:00

(Migrated from github.com)

still getting blurred faces. I am wondering do we need to align the face as in FFHQ before seeding our own images to the inference script

Sign in to join this conversation.

1 Participants

Notifications

Due Date

No due date set.

Dependencies

No dependencies set.

Reference: CalvinBackup/neuralchen-SimSwap#483