looks like torch version related error
looks like torch version related error
![Digital [Starburst]](https://cdn.discordapp.com/avatars/220961909447458817/8ecbbb3132fc6e44312f3d6d2ae3df69.webp?size=40)
DI really like your Pixart Gradio ui you built. Do you think it would be possible to include more possible styles and models?
DThe more intricate the txt prompt, the longer it takes to generate the images.
DIt would be great if you could add txt2vid for up to 240 frame vids. I'm probably dreaming though. I've tried txt2vid with ComfyUI and it's been a dismal failure. I need some good training on creating good prompts. My prompts aren't generating any desired results. I know you must've created a tutorial somewhere, so I will use Ctrl-F to find it on Git.
![Digital [Starburst]](https://cdn.discordapp.com/avatars/220961909447458817/8ecbbb3132fc6e44312f3d6d2ae3df69.webp?size=16)
Fye this is a hard task :d
BI have this exact same issue. I have the indicated version of torch installed
Should we be using a newer version of torch?
Should we be using a newer version of torch?
JJust to guess, probably need to be at 2.1? Lots of stuff seems to need > 2
Just looking at their github repo they do:
&& conda install pytorch torchvision torchaudio pytorch-cuda=11.7 -c pytorch -c nvidia \
So im assuming it just installs the latest
Just looking at their github repo they do:
&& conda install pytorch torchvision torchaudio pytorch-cuda=11.7 -c pytorch -c nvidia \
So im assuming it just installs the latest
BI just upgraded to 2.1.1 just in case and it appears to be running but the problem is that Tortoise itself requests 1.13.1 from requirements.txt:
Hashes collapsed for brevity
Hashes collapsed for brevity
DThanks for your guide on Pixart. Ran it on RunPod and tested it, and yes, it is way better than SD. Probably because of the better encoder and the higher image quality training. Are you going to try and do a Dreambooth training ?
I will look into https://github.com/PixArt-alpha/PixArt-alpha/blob/master/asset/docs/pixart-dreambooth.md and see if it is any good.
I will look into https://github.com/PixArt-alpha/PixArt-alpha/blob/master/asset/docs/pixart-dreambooth.md and see if it is any good.
GitHub
Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis - PixArt-alpha/PixArt-alpha
BUpdate: Torch 2.1.1 seems to be working, however it took some effort.
1) I was accessing my machine remotely via RPD. RDP doesn't use the GPU by default. You have to change registry settings to enable the GPU via RDP
2) once the GPU was actually active I had to force reinstall torch and its related packages and then check that Cuda was enabled with the following:
My CPU is much happier now.
1) I was accessing my machine remotely via RPD. RDP doesn't use the GPU by default. You have to change registry settings to enable the GPU via RDP
2) once the GPU was actually active I had to force reinstall torch and its related packages and then check that Cuda was enabled with the following:
python -c "import torch; print(torch.cuda.is_available())"My CPU is much happier now.
Fyes i am searching for it
CCan you tell me the command you used to upgrade to Torch 2.1.1? I'm not a regular Python user. The Github doc still only has this instruction and I'm not sure how to convert it and/or if I need to uninstall first
Afinally got around to installing kohya. Does it work for SD 1.5 models?
Amaybe i can just use this from now on instead of a1111
Awith kohya it looks like i can even use dreambooth. Do i even need the A1111 version anymore?
Fyou need to activate venv and run command
F
Fit works both sdxl and sd 1.5
Fyou dont need
Fbut for sd 1.5 sadly i dont have good parameters yet
DI'm generating some pretty awesome images with your Pixart webui.
DI've been studying up on writing good prompts. I had no idea you should add open-ended questions. I didn't know curly brackets mean you want it in the image and square brackets mean you don't want it in the image (I thought that's what negative prompts were for).
DI have noob tattooed on my forehead.
Jwoah that is wild
DI've messed around with the video generation tools one of which is broken but the one for ComfyUI works. Other than a short GIF file you aren't going to get much, and it won't be very good at that.
DI guess I should've thought that if I get some of the results I end up with just with images then the possibility of getting much of a video aren't really all that great.
DSomeone 15 months ago took over the maintenance of text2video but I did my best to get it to work, and it has an issue with missing modules I know are properly installed with the correct version numbers and everything. I was hoping it would be a little more effective.
DDeforum works great
CTried that and got the same error
Fi am helping members minimum gold level by connecting their pc if you need such help
CI'm confused by this because I'm literally following the instructions by the letter from the Github link from your video. I think it has errors if this isn't working
Ftortoise-tts-fast is the thing of past
Fcocui is much better
Fi have even fine tuning script
F
Fbeginning talking made with Cocui fine tuning
FYouTubeSECourses
Master Stable Diffusion XL Training on Kaggle for Free! Welcome to this comprehensive tutorial where I'll be guiding you through the exciting world of setting up and training Stable Diffusion XL (SDXL) with Kohya on a free Kaggle account. This video is your one-stop resource for learning everything from initiating a Kaggle session with dual ...
Master Stable Diffusion XL Training on Kaggle for Free! Welcome to this comprehensive tutorial where I'll be guiding you through the exciting world of setting up and training Stable Diffusion XL (SDXL) with Kohya on a free Kaggle account. This video is your one-stop resource for learning everything from initiating a Kaggle session with dual ...Fi am still working on a tutorial
CCool. Looking forward to it. I agree that tortoise-tts-fast is looking pretty problematic right now
F
IHello guys! Someone have experience on the best tool for train a voice and apply on an already made song?
DI didn't know that if you ever sign up for Google Colab you're stuck with it, and Kaggle won't work unless you upgrade to Colab. I upgraded to the silver tier @Furkan Gözükara SECourses because I think learning how to use AI will be impossible without help.
Fi got voice training tutorial. preparing it
Ffor apply people using RVC but yet to research it
Fthank you so much
DCool
