do you recommend just using this instead of SUPIR? I'm guessing supir might be slightly better but n
do you recommend just using this instead of SUPIR? I'm guessing supir might be slightly better but not generally worth it?
Fcan you make a fresh install and send me install logs
Fsupir is best to upscale existing images
Fbut if you fine tune flux latent upscale works even better to add more details and fix errors
Jhuh okay gotta try that, thx!
Fsure. where can i find the install logs?
FTried new install. Now this command prompt closes abruptly after that line "creating venv".
Finstall logs means the output on cmd which you can copy
Fwell restart pc and try again
AGuys if I want to remove false letters and labels from a shirt for example , how do I prompt with flux fill dev so that it removes the letters and keeps the texture/ color of the shirt?
Dbrother is there any RVC Retrieval-based Voice Conversion tutorial?
FResolved it by running this command git config --global --add safe.directory D:/AI/Kohya_Dreambooth/kohya_ss
Fsadly not yet
Fah it was permission related
P@Dr. Furkan Gözükara when I am using the upscaler you told to use the generated images are looking not realistic
Pthey are get bad textures like dolls
Pthe hands and other things did improve but the skin isnt' looking fully real
Fyou probably need bigger training dataset
Fit improves realism
Falso are you using my said upscaler?
Pyes
Fim an admin user. I dont know why it was making an issue
M@Dr. Furkan Gözükara I've watched the tutorial on Flux Tools in SwarmUI, and I have a question.I see that you generate the image directly with the model, meaning you load canny.dev or redux.dev instead of the original Flux model. These are tools that, in theory, are compatible with the original Flux models. So, could I use flux-dev together with flux.redux to get the most out of it? Or is there something I'm not understanding?
MFor example, if I have a fine-tuned model with my face and I want to generate a character with my face in a specific pose, such as with open arms, how can I combine a depth image (using the depth tool) while also using my own fine-tuned model in SwarmUI?
Fdepends on windows installation
Fyes flux redux works with flux dev best
Fsadly others are not working very good 
Mso I can't combine my own flux finetuned model with the depth or canny modls?
Fi made huge improvement to idm vton app
Fgonna update
Fsadly not. you can use their loras but especially canny lora so bad
MOk I get it, thanks
Fnew idm vton published with new features
FPatreon
Get more from SECourses: FLUX, Tutorials, Guides, Resources, Training, Scripts on Patreon
Vhttps://ia.acs.org.au/article/2021/police-mistake-bitcoin-mine-for-cannabis-farm.html
maybe they mistake you for a grower
also is your computer cloud or local computer? If local then I guess its getting pretty hot in that room
maybe they mistake you for a grower
also is your computer cloud or local computer? If local then I guess its getting pretty hot in that room
Information Age
Raid on suspected hydroponic setup uncovers illicit mining operation.
V@Furkan Gözükara SECourses what would be the way to kind of automate the flux finetuning process more? is there a way to create an image that has fixed flux version etc that you can just load up on cloud computer?
this would not be possible with massed compute?
with runpod?
or is there a way to make this more automated.... not exactly sure how... but maybe with lambda from AWS? any idea?
this would not be possible with massed compute?
with runpod?
or is there a way to make this more automated.... not exactly sure how... but maybe with lambda from AWS? any idea?
Fautomate = software development skills or $$$$$
Vhaha... yeah I got a computer science degree and cloud certification but not sure yet which are the plattforms or tools to use.... so can tell me which are the suited plattforms for quick protoyping, also cheap would be good.... because it seems massed compute is cheapest but has super limited resources and you cannot upload prebaked images? Didnt have a look at how runpod works yet... Before somebody mentioned somehting about "replicate"....
I mean I could create an image for AWS instance.... then add api gateway, lambdas etc... but I have to look actually how much these gpus cost on AWS platform directly... will have a look tomorrow regarding pricing...
but then I would need to create some kind of application with api running on the aws instance which then creates the images etc...
but not sure yet which are the plattforms or tools to use.... so can tell me which are the suited plattforms for quick protoyping, also cheap would be good.... because it seems massed compute is cheapest but has super limited resources and you cannot upload prebaked images? Didnt have a look at how runpod works yet... Before somebody mentioned somehting about "replicate"....I mean I could create an image for AWS instance.... then add api gateway, lambdas etc... but I have to look actually how much these gpus cost on AWS platform directly... will have a look tomorrow regarding pricing...
but then I would need to create some kind of application with api running on the aws instance which then creates the images etc...
Fi never researched to be frank
Vhmmm... yeah maybe the replicate api... then combine it with some other things... I guess there are also some turnkeysolutions for user interfaces.... Need to look a bit more
from replicate:
Nvidia L40S GPU (gpu-l40s, $3.51/hr)
Nvidia A100 GPU (gpu-a100-large, $5.04/hr)
but it says the api use is billed per second
from replicate:
Nvidia L40S GPU (gpu-l40s, $3.51/hr)
Nvidia A100 GPU (gpu-a100-large, $5.04/hr)
but it says the api use is billed per second
VActually somebody saw the pictures I generated with the flux and wants me now to create some images for him for money so yeah....
RHey Doc, I just saw the IDM VTON app. Have you compared IDM VTON with CAT VTON and/or Flux Redux?
Fye people using replicate
Fi havent compared with cat vton yet
Fflux redux works different
NYou want to share?
I'll be sure to test it
And here's a question, has
https://huggingface.co/spaces/tencent/Hunyuan3D-2/tree/main
I'll be sure to test it
And here's a question, has
Hunyuan3D-2 been deployed yet? Who knows can advise solutions for 4090rtx? https://huggingface.co/spaces/tencent/Hunyuan3D-2/tree/main
�Kohya implemented this - https://github.com/kohya-ss/sd-scripts/pull/1864 can you please tell me how to start this in kohya. It will be a great factor to analyze how the lora or dreambooth is training.
GitHub
Related #1856 #1858 #1165 #914
Original implementation by @rockerBOO
Timestep validation implementation by @gesen2egee
Updated implementation for sd3/flux by @hinablue
I went through and tried to m...
Original implementation by @rockerBOO
Timestep validation implementation by @gesen2egee
Updated implementation for sd3/flux by @hinablue
I went through and tried to m...
Jtrying to generate 4 images at the same time (using 4 L40) but it seems like it will only make 2 at a time?
If I leave OverQueue=1 (default) then 2 will generate exactly the same time, and then the next 2.
If I set OverQueue=0 then it still takes about 40 seconds before the fourth image starts to generate, so ends up taking just as much time. Like the first photo will be finished before the fourth one starts.
Shouldn't all 4 photos just start generating at the same time?
If I ask to generate 8 images at the same time, all 4 GPU's will run from the start like it should though...
On Massedcompute.
If I leave OverQueue=1 (default) then 2 will generate exactly the same time, and then the next 2.
If I set OverQueue=0 then it still takes about 40 seconds before the fourth image starts to generate, so ends up taking just as much time. Like the first photo will be finished before the fourth one starts.
Shouldn't all 4 photos just start generating at the same time?
If I ask to generate 8 images at the same time, all 4 GPU's will run from the start like it should though...
On Massedcompute.
Ttry looking at debug logs
Jah yea should've sent that. forgot to look and have closed down now
PHi guys, I'm testing a new upscaler technique and I'd like your opinion on the result, what do you think? I'm going to send 2 images, one in 1024x768 and the other in 4096x3072 upscaler.
