Skip to main content
RunComfy Trainer lets you run inference with the same LoRA + base model inference setup in two different ways.
  • Both options keep training and inference parity (same base model, same setup, same defaults).
  • What changes is how you run it (on‑demand vs. your own dedicated endpoint) and how you’re billed.

Model API


On‑demand, no deployment, call a model_id and pass your LoRA in the request body.
Billing: per request

Serverless API (LoRA)


Deploy your LoRA as a dedicated endpoint (a deployment) and call it with a deployment_id.
Billing: GPU uptime, you can autoscale and scale down when idle

​
How to decide (10 seconds)

If your goal is simply:
  • “I trained/imported a LoRA and I want to generate with it on top of the base model”
Start with the Model API. Only choose the Serverless API (LoRA) when you specifically need a dedicated endpoint, for example:
  • you want to pick a GPU tier for your workload
  • you need to control how many runs can happen in parallel (autoscaling / concurrency)
  • you want to keep capacity warm so the first request isn’t slow (reduce cold starts)
  • you need more predictable response time for production traffic
Tip: If you’re unsure, start with the Model API. You can always deploy a dedicated endpoint later without changing your prompts or workflow logic.

​
Quick comparison

​
Same async pattern, different IDs

Both options are asynchronous. Model API
Serverless API (LoRA) (Deployment)

​
Option A — Model API (on‑demand, no deployment)

Use this when you want the fastest path from LoRA to generation.

​
What you do

  1. In Trainer > Run LoRA, select your LoRA’s base model, then open that base model page and copy its model_id.
    • This model_id represents the inference setup you’ll run (the model’s pipeline/workflow).
  2. Call the Model API with that model_id and include your LoRA as an input parameter (for example lora.path).
  3. Poll status and fetch results using the returned request_id.

​
Key thing to remember

The Model API will run whatever inference setup the model_id points to. For your trained LoRA inference:
  • model_id = the base model’s inference setup (from the model page)
  • LoRA = an input you provide on each request

​
Where to go next

​
Option B — Serverless API (LoRA) (dedicated endpoint / Deployment)

Use this when you need more control over runtime behavior (GPU choice, autoscaling, warm instances) and want to call your LoRA through a stable dedicated endpoint.

​
What you do

  1. In Trainer, turn your LoRA Asset into a Deployment (this creates the dedicated endpoint and pins the LoRA + base model + default settings).
  2. Copy the deployment_id from the Deployment details page.
  3. Submit inference to POST /prod/v2/deployments/{deployment_id}/inference.
  4. Poll status and fetch results (same async pattern, but scoped under the deployment).

​
Key thing to remember

With a Deployment, the LoRA is already part of the endpoint. That means:
  • deployment_id selects the endpoint
  • Your request body only includes the inputs defined by the deployment’s schema (prompt, images, params, etc.)
  • You typically do not pass lora.path because the LoRA is already attached

​
Where to go next