R
RunPod•5mo ago
xsjiang

ComfyUI ValueError: not allowed to raise maximum limit

I deployed a comfyui with the comfyui_controlnet_aux plugin included, and when I run the test runpod locally it works fine, but after deploying to serveless I get the following error.
4 Replies
xsjiang
xsjiang•5mo ago
error log

message.txt

ashleyk
ashleyk•5mo ago
You can't raise the limits in RunPod, you need to either disable that or contact the devel;oper of the plugin to fix it.
xsjiang
xsjiang•5mo ago
Ok, thanks
Felipe Fontana
Felipe Fontana•3mo ago
@xsjiang could you resolve it?
Want results from more Discord servers?
Add your server
More Posts
Webhook duplicate requestsHi, I noticed webhook requests replay starting last night. I would like to know the behavior of webRequest Format Runpod VLLM Worker``` { "conversation": { "id": "some_conversation_id", "messages": [ { "sourcimage returns as base64I'm using the SD Anything v5 model. when im making a api call (RUNSYNC/RUN) im getting the image in Request stuck in "IN_QUEUE" statusHi, I tried to setup a endpoint for "rembg" package using cog. It seems to run fine locally, but wheGPUs look available via `runpod.api.ctl_commands.get_gpu()` which aren't available.I'm currently trying to find which types of GPUs are available (in order to programatically decide wRundpod VLLM Cuda out of MemoryHi I've been using the default runpod VLLM template with the mixtrial model loaded in the network voServerless endpoint long waits in "Initializing" stateRequests to a serverless endpoint at `/run` have an "Initializing" status in the dashboard for up tAutomate the generation of the ECR token in Serverless endpoint?I want to use AWS ECR to store my serverless images. However, the token expires and I do not find thFoooocus too slow on generationSD is very complexed, so i decided to use fooocus UI instead which im used to. The problem here is tImage Generation problemNansException: A tensor with all NaNs was produced in Unet. This could be either because there's not