serverless runpod/qwen-image-20b stays in initiating
Hi, I am trying to deploy serverless end point for this image runpod/qwen-image-20b... it just stays in initiating. I created a template with 20GB disk using NVIDIA GPU. Can anyone please help.
Regards,
Sameer
6 Replies
https://console.runpod.io/hub/playground/image/qwen-image-t2i
try our public endpoint, it is easier to get start
that works... I wanted to host as I need to generate several images
We have api, you can just calling api to generate multiple ones at the same time
yes, but it would turn out to be expensive. Plus in many instance the request is queued which delays the overall response time to the client. Deploying my own end point could help me avoid queues as well sas keep the cost down
so is there anyway you can guide me on how can I can deploy qwen-image on serverless? is runpod/qwen-image-20b the right image?
Sorry, that image is supposed to be private. You can use Qwen-Image with diffusers, they offer a sample in the model README. It shouldn't be too difficult to wire this up to the serverless SDK with a few input knobs :fbslightsmile:
https://huggingface.co/Qwen/Qwen-Image
ok thanks so much