AWS Server

[harinath101515]

It is possible to run on AWS server

[theguaz]

I'm running it on a g5.8xlarge right now

[harinath101515]

I'm running it on a g5.8xlarge right now

are you using the git hub repository or you paid for the membership

[theguaz]

I just launched a g5 instance on my personal AWS account, then logged in using SSH and used it as any other computer, costs are not cheap tho.

[harinath101515]

I'm running it on a g5.8xlarge right now

i am talking about source code which source code you are using , are you using git hub source code or your brought 1 click installer scripts from https://www.patreon.com/ this website

[theguaz]

this exact repo, ny steps where like this;

Step 1: Clone the repository
git clone https://github.com/yisol/IDM-VTON

Step 2: Navigate inside the cloned repository
cd IDM-VTON

Step 3: Create virtual environment ( conda or venv)

Step 4: Activate virtual environment ( conda or venv)

Step 5: Install requirements using the yaml file, and also onnxruntime fpr Linux in my case

Step 6: Download checkpoints

1. IDM-VTON\ckpt\densepose
   https://huggingface.co/yisol/IDM-VTON/tree/main/densepose

2. IDM-VTON\ckpt\humanparsing (parsing_atr.onnx and parsing_lip.onnx)
   https://huggingface.co/levihsu/OOTDiffusion/tree/main/checkpoints/humanparsing

3. IDM-VTON\ckpt\openpose\ckpts
   https://huggingface.co/lllyasviel/ControlNet/blob/main/annotator/ckpts/body_pose_model.pth

Step 7: Download VTON models
mkdir yisol
cd yisol
git lfs install
git clone https://huggingface.co/yisol/IDM-VTON

Step 8: Launch the gradio UI
venv\scripts\activate
python gradio_demo/app.py

[harinath101515]

I need to try these all steps in aws g5

this exact repo, ny steps where like this;

Step 1: Clone the repository git clone https://github.com/yisol/IDM-VTON

Step 2: Navigate inside the cloned repository cd IDM-VTON

Step 3: Create virtual environment ( conda or venv)

Step 4: Activate virtual environment ( conda or venv)

Step 5: Install requirements using the yaml file, and also onnxruntime fpr Linux in my case

Step 6: Download checkpoints

1. IDM-VTON\ckpt\densepose
   https://huggingface.co/yisol/IDM-VTON/tree/main/densepose
2. IDM-VTON\ckpt\humanparsing (parsing_atr.onnx and parsing_lip.onnx)
   https://huggingface.co/levihsu/OOTDiffusion/tree/main/checkpoints/humanparsing
3. IDM-VTON\ckpt\openpose\ckpts
   https://huggingface.co/lllyasviel/ControlNet/blob/main/annotator/ckpts/body_pose_model.pth

Step 7: Download VTON models mkdir yisol cd yisol git lfs install git clone https://huggingface.co/yisol/IDM-VTON

Step 8: Launch the gradio UI venv\scripts\activate python gradio_demo/app.py

if i try these steps in aws g5 is it working

[harinath101515]

Can you explain how to execute code in cloud.

…

On Thu, 16 May, 2024, 05:29 Breno Silva, ***@***.***> wrote: Hi, I've done this and could execute using "accelerate launch inference.py". Can you guys help me get it working for a single image of mine? I want to make an app to capture from my webcam and put the clothes on me — Reply to this email directly, view it on GitHub <#62 (comment)>, or unsubscribe <https://github.com/notifications/unsubscribe-auth/APZXNWZMIAMEPPXF6BTLMXTZCPZHRAVCNFSM6AAAAABHVN7TM6VHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMZDCMJTGY3TAMBSGY> . You are receiving this because you authored the thread.Message ID: ***@***.***>

[FurkanGozukara]

i have a full cloud tutorial may help you : https://youtu.be/LeHfgq_lAXU

[nitinmukesh]

g5.8xlarge

I just checked the price. You could buy a very high end PC at that price. Unable to understand why are you paying such huge price?

2500 dollars for 1 hour
https://instances.vantage.sh/aws/ec2/g5.8xlarge?region=us-east-1&os=linux&cost_duration=hourly&reserved_term=Standard.noUpfront

[brenogibson]

g5.8xlarge

I just checked the price. You could buy a very high end PC at that price. Unable to understand why are you paying such huge price?

2500 dollars for 1 hour https://instances.vantage.sh/aws/ec2/g5.8xlarge?region=us-east-1&os=linux&cost_duration=hourly&reserved_term=Standard.noUpfront

It is 2,5 USD per hour, not 2 thousand