Deploying Image LoRA adapter model

How to deploy Image LoRA adapter model

1. Navigate to the dashboard https://byteCompute.com/dash

2. Click on the 'New Deployment' button

3. Click on the 'LoRA text to image' tab

4. Fill the form:

   • LoRA model name: model name used to reference the deployment
   • Base Model: Select the base model for LoRA
   • Civital URL: URL of the LoRA model from civital.com

Prerequisites

1. Public LoRA model from civital.com
2. ByteCompute account

Deployment appears at https://byteCompute.com/dash/deployments with state "Initializing".

Deployment time varies from 5s to 1min depending on LoRA size. Once "Running", model is ready.

Inference Examples

Using direct API endpoint:

curl "https://api.byteCompute.com/yourname/yourmodel" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $ByteCompute_TOKEN" \
  -d '{
      "prompt": "A cat in anime style",
      "lora_scale": 0.7
    }'

Using OpenAI compatible API endpoint:

curl "https://api.byteCompute.com/v1/openai/images/generations" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $ByteCompute_TOKEN" \
  -d '{
      "model": "yourname/yourmodel",
      "prompt": "A cat in anime style",
    }'

Notes

• Only public Civitai models are supported
• Base models support same parameters as their original versions
• LoRA scale parameter controls adaptation strength