Skip to content

issues Search Results · repo:facebookresearch/stable_signature language:"Jupyter Notebook"

Filter by

37 results
 (60 ms)

37 results

infacebookresearch/stable_signature (press backspace or delete to remove)

facebookresearch/stable_signature
Which dataset is being used for whitening and how many images?

In the code, I see that there is a block where it does the whitening if whitened decoder is not provided. But it uses train_dir, is this the same dataset used to train the LDM? as in the Readme.md it states ...
  • JosTheBossX
  • 1
  • Opened 
    14 days ago
  • #39

facebookresearch/stable_signature
Can we finetune the LDM decoder from diffusers library instead of ldm folder which you gave?

  • ypradhan222
  • 1
  • Opened 
    17 days ago
  • #38

facebookresearch/stable_signature
A question regarding training the HiDDeN model

First of all, thank you so much for sharing your code. It has been incredibly helpful. I have a question about training the HiDDeN model. Did you use the entire COCO train2014 dataset (approximately 80,000 ...
  • UtaeJeong
  • 2
  • Opened 
    on Feb 6
  • #37

facebookresearch/stable_signature
How evaluation is done from captions of Validation Set

Hello author, Can you please share how evaluation is done on generation om prompts from validation set of COCO dataset(Appendix A.3) in Text-to-Image. It would be helpful if you could share how evaluation ...
  • deepikachettri29
  • 6
  • Opened 
    on Jan 20
  • #36

facebookresearch/stable_signature
About finetune LDM decoder

Hello! I had some frustrating problems when finetuning the LDM decoder. I use 10000 COCO images as train set and 1000 as test set, after train a HIDDEN encoder_decoder with 64bits and image size 512x512 ...
  • ewave12138
  • 1
  • Opened 
    on Jan 11
  • #35

facebookresearch/stable_signature
There is a misleading guidance in README.md for loading a checkpoint created from finetune_ldm_decoder.py.

图片1
  • QuestaYan
  • 2
  • Opened 
    on Dec 19, 2024
  • #34

facebookresearch/stable_signature
Question about optimizer

Hello, Reading your paper and your StableDiffusion/Hidden code, I noticed that you are using the LAMB optimizer… Why did you choose to use LAMB instead of AdamW / RAdam? I tried to replicate your experiment ...
  • darktanuki
  • 1
  • Opened 
    on Dec 18, 2024
  • #33

facebookresearch/stable_signature
About baseline method FNNS

Could you please share the codes for this baseline? In your paper, you mentioned FNNS as one of the baselines, but it was used to replace the original SteganoGan with HiDDeN. I found the implementation ...
  • fenghe12
  • 1
  • Opened 
    on Dec 9, 2024
  • #32

facebookresearch/stable_signature
If the pretrained model is suitable for sdxl

If the pretrained model is suitable for sdxl，ths
  • hitlmt
  • 1
  • Opened 
    on Sep 5, 2024
  • #31

facebookresearch/stable_signature
About specific details of whitening the pretrained extractor

Hi, thank you for your amazing work! I m still a little confused how the whitened extractor checkpoint is obtained. From the appendix of the paper, I think the linear layer used for whitening should be ...
  • mcl0
  • 3
  • Opened 
    on Aug 29, 2024
  • #30
Issue origami icon

Learn how you can use GitHub Issues to plan and track your work.

Save views for sprints, backlogs, teams, or releases. Rank, sort, and filter issues to suit the occasion. The possibilities are endless.Learn more about GitHub Issues
ProTip! 
Press the
/
key to activate the search input again and adjust your query.
Issue origami icon

Learn how you can use GitHub Issues to plan and track your work.

Save views for sprints, backlogs, teams, or releases. Rank, sort, and filter issues to suit the occasion. The possibilities are endless.Learn more about GitHub Issues
ProTip! 
Restrict your search to the title by using the in:title qualifier.
Issue search results · GitHub