Where communities thrive


  • Join over 1.5M+ people
  • Join over 100K+ communities
  • Free without limits
  • Create your own community
People
Activity
  • Mar 29 15:12
    stale[bot] closed #166
  • Mar 22 14:31
    stale[bot] labeled #166
  • Mar 21 15:16
    xhamsterlolman opened #170
  • Mar 20 07:48
    xrebel10 closed #167
  • Mar 20 07:47
    xrebel10 closed #169
  • Mar 10 02:15

    kolessios on master

    README improvements. README improvements. (compare)

  • Mar 10 02:14

    kolessios on canary

    README improvements. README improvements. Merge branch 'master' into cana… (compare)

rajmuppana
@rajmuppana
Hi Guys, Can any one tell me why lower half in the pictures is blurred out and how to fix it?
deeppppp
@deeppppp
No fix available yet.. working on it
Phenoiox
@Phenoiox
any news on updates? It’s been a long time since we seen anything
@deeppppp @kolessios
deeppppp
@deeppppp
the original still beats out the new, so I'm continuing the model training.
xd9811
@xd9811
is this project dead?
USB Type C
@USBTypeCEnthusiast_gitlab
given the last message was only a few days ago and the websites etc... still worked I'd be inclined to not at all be counting it out just yet
xd9811
@xd9811
true... just haven't seen any real updates on progress recently and with all the stuff about the servers not being able to be supported anymore it's just a bit concerning
deeppppp
@deeppppp
@xd9811 obviously this project is not 'dead'.
You may have noticed a pandemic happening right now that is throwing everything off..
crumbycrumbycrumby
@crumbycrumbycrumby
Hey @deeppppp , out of curiosity why do you think the new checkpoints aren't giving the desired results yet? Does the variety of new angles in the training set just require more time to train? Is there some other approach you're taking besides more training time to improve the results?
deeppppp
@deeppppp
it's a learning process, where every step takes weeks before you can see the results.
I'm introducing new code etc. because my goal is to be able to improve and go beyond the deepnude results.
I've had access to a Titan RTX now for 3 months and in that time made several revisions.. I'm very confident I'll get there, it just takes time and with the corona virus hitting hard.. I can't say when it will be ready, just rest assured work is done on it and results will become available :)
Usain Bolt
@ubolt11_gitlab
Maybe I'm too stupid to RTFM but I coulnd't find it so here we go: How can I nudify manually edited Maskfins? So if I understand correctly, I should be able to export generatd Masfins to photoshop, edit them accordingly and then feed it back to DreamTime. However I don't understand how the last part works. Any help would be kindly appreciated :)
elf (liam)
@elfkinx
i aint all that great with code, but i have 6 2080s and 3 titan xs and was wondering if i could put that to any good use
Piergiox
@Piergiox
@ubolt11_gitlab if you want to use dreamtime, in preferences you can choose “nudify and maskfin” and “nudify with maskfin”, so if you have already a maskfin, you must choose the last option. Then if you want to do all the process manually, you can execute dreampower via powershell, there’s a tutorial somewhere in the main website. If you cant’ find the tutorial, tell me, I have a document saved in my pc
Gasd96
@Gasd96
@Piergiox pls send the tutorial, i'm in the same situation
Piergiox
@Piergiox
Ok guys, I will send the instructions to process an image manually. Please wait a little bit, this morning I started the defragmentation of the hard disk of my pc so I can’t use it, when it is finished I will send it
Piergiox
@Piergiox
Ok guys, I made a written tutorial on pastebin, this is the link: https://pastebin.com/WJPvLGAa if you don't understand something, I'm sorry for my bad english, but don't be afraid to ask me explanations
crumbycrumbycrumby
@crumbycrumbycrumby
I actually wrote a tutorial and finished about the same time as @Piergiox . I'll share mine also as we probably do things a bit differently.
https://pastebin.com/swJNnfeJ
crumbycrumbycrumby
@crumbycrumbycrumby
I recommend you do all your mask editing on MaskdetToMaskfin, not MaskrefToMaskdet. Maskfin is much more precise, and in my experience the alg will sometimes make some major changes when generating a MaskdetToMaskfin from the MaskrefToMaskdet, which if you want precision then you probably don't want many changes happening.
xrebel1
@xrebel1
A little faster method is this 1. Create a New folder on Desktop and rename it to 1 (for example) 2. In the folder put your photo 3. Open Command Prompt 4. Paste cd C:\Users\ (Your Username)\AppData\Roaming\dreamtime\dreampower 4. If your photo is 512x512 paste dreampower.exe run -i C:\Users\ (Your Username)\Desktop\1\1.jpg -a C:\Users\ (Your Usename)\Desktop\1 -s 0:5 5. If your photo is not 512x512 paste dreampower.exe run -i C:\Users\ (your Username\Desktop\1\1.jpg -a C:\Users\ (Your Username\Desktop\1 --auto-resize -s 0:5
If you want to edit the masks first run steps 0:4, edit the MaskdetToMaskfin photo and the run step 5:5
Also in Command Prompt cd stands for change directory
Piergiox
@Piergiox
@crumbycrumbycrumby @xrebel1 guys I noticed that both of you go from phase 0 to 4 directly, but in my experience sometimes the algorithm select the wrong area in phase 1, how do you correct this? Do you edit also the green area in the 4th phase?
xrebel1
@xrebel1
@Piergiox You can run any stage and make any corrections if you want. I said 0:4 stages so you can have all stages together to see if you want to make any modifications and to which stage
Piergiox
@Piergiox
Ok, it’s right
xrebel1
@xrebel1
Also you should rename your folder to 1,2,3 etc and your photos to 1,2,3 etc so it's easier to work with in the Command Prompt so it goes like this dreampower.exe run -i C:\Users\ (Your Username)\Desktop\1\1.jpg -a C:\Users\ (Your Usename)\Desktop\1 -s 0:5 and so on as I said above
For your convenience don't use complicated folder names and rename your photos to numerical style like 1,2,3 etc
crumbycrumbycrumby
@crumbycrumbycrumby
@Piergiox I discovered that you can do whatever you want to step 4 and it doesn't matter what the previous steps have in them. The masks generated step 0 through 3 could be totally off, but if you input a good mask manually in step 4 then the output will be fine
@xrebel1 If you keep all of your inputs in the same folder (Samples in my tutorial) then you don't have to edit the folder path in the command, just the image name. Same goes for output. I only have to change the image name and steps when moving from one image to another
xrebel1
@xrebel1
I don't understand what you are talking about. I don't use folders like Samples or Altered etc. I was giving an example with folder name 1 and photos named 1,2,3 etc. You don't need to change folders or anything.
xrebel1
@xrebel1
Personally I use a USB stick (F:), a folder name as 1 and png files so it goes like this dreampower.exe run -i F:\1\1.png -a F:\1 -s 0:5. I change only the photo name from 1.png to 2,3,4.png. So simple. No need for Samples and Altered folders and whatever.
Gasd96
@Gasd96
( point 6) "with your image editor you can edit correcttomask image..." it's correct? or i have to edit dresstocorrect file?
crumbycrumbycrumby
@crumbycrumbycrumby
You don't need to edit dressToCorrect. It wont actually do you any good if you do anyway.
crumbycrumbycrumby
@crumbycrumbycrumby
@xrebel1 Sorry, I thought you were saying something beyond just "you can name your folders whatever is easiest"
xrebel1
@xrebel1
No, I didn't say anything like that. I'm very specific on what I'm saying.
crumbycrumbycrumby
@crumbycrumbycrumby
Hmm, but you said "you should rename your folder to 1,2,3 etc and your photos to 1,2,3 etc so it's easier to work with". Am I missing something?
xrebel1
@xrebel1
For example dreampower.exe run -i F:\1\1.png -a F:\1 -s 0:5 (the command I use). F: =USB stick, 1=folder, 1-2-3.png = photos. Is it anything you don't understand? So why I should bother using names like Samples and Altered when I can use a command so simple?
Jacob DeWeese
@Rythoka
Hey eveyone, new guy here. Can someone explain what exactly the mask too in the editor does?
Or where to look for that info?
Piergiox
@Piergiox
@xrebel1 @crumbycrumbycrumby ok thank you for your advices
Lew30323
@Lew30323
@deeppppp This might be a bit outside of what you are currently doing but would it be possible to make a programme that will completely create the body from scratch with any photos of the person or multiple being used to get the face correct. This could somewhat solve the issue of not having photos that are ever going to work with the programme. I'm not saying this because I'm expecting it to be done at any point in the near future, just wondering if its a possibility.
crumbycrumbycrumby
@crumbycrumbycrumby
Ahh ok, so you're naming your folders whatever is easiest. Got it
@Rythoka Read through the information here to get a basic understanding of what the mask does.
https://github.com/dreamnettech/dreampower
Gasd96
@Gasd96
how do you use the "nudify with maskfin" function from dreamtime? I always get blue results...
xrebel1
@xrebel1
@crumbycrumbycrumby The easiest is the numerical style for both folder and photos
xrebel1
@xrebel1
@Lew30323 There is a basic principle about the algorithm that DreamTime/DreamPower uses. The Generative Adversarial Networks (GANs), a machine learning technology is based on a set of data (in Dreamtime/DreamPower these data are photos) which is used to train the GAN to produce realistic body assets. GANs can't produce results from nothing so a training set of data must be used. Your comment is a bit vague of what you want to achieve but the main goal here is to train the GAN (the algorithm) to produce realistic body assets based on a set of data (photos). I suggest you read a bit about GANs and how they work so you can have a better understanding of the machine learning techology.
Lew30323
@Lew30323
@xrebel1 I think I may have explained it badly, what i mean is that instead of relying on the masking to detect what needs to be replaced it would create a basic outline of the entire body and render the entire thing, instead of just the places that need to be replaced, yes it would be alot more work but it would allow you to work with almost any photo as an imput. Basically, instead of only masking the sections that it is currently doing it could mask each and every part seperately, at the moment it is impossible to work on fully clothed photos because it doesnt have enough data to go off, so why not train it to just create the entire body off the skin tone that is visible in the face. On another note, there is currently technology to create entire bodys automatically, there is also technology to place anyones face onto an existing person, why not put the two together? Throw in a load of photos of a person and generate whatever you want off that.
I know im saying that like it is easy, I know its not, like i said before, im just wondering if it is possible, im not expecting it to happen any time soon.
xrebel1
@xrebel1
@Lew30323 Now I got you. But with the current version of DreamTime/DreamPower you can transform clothed photos with decent results.
sebi321x
@sebi321x
hmm... bouncing off the recent topics, would there be any interesting/significant way to leverage something like this: https://topazlabs.com/mask-ai/