# Krea 2 Medium LoRA Training

> Run Krea 2 Medium LoRA Training by krea online or via API. $0.50/training run, no setup.

**URL:** https://inference.sh/apps/krea/krea-2-medium-train
**Last updated:** 2026-10-31

---

Train custom LoRA styles for Krea 2 Medium generation

- app: `krea/krea-2-medium-train`
- maker: [krea](https://inference.sh/apps/krea.md)
- category: [image](https://inference.sh/apps/category/image.md)
- tasks: [training](https://inference.sh/apps/tag/training.md), [lora](https://inference.sh/apps/tag/lora.md)
- price: $0.50/training run
- runs via: api, javascript and python sdk, belt cli, mcp

## krea-2-medium-train API Guide

### About
train custom lora styles for krea 2 medium generation

### Get an API Key
Create one in [settings → api keys](https://app.inference.sh/settings/keys). The examples read it from `INFERENCE_API_KEY`.

```bash
export INFERENCE_API_KEY="inf_your_key"
```

### 1. Calling the API

#### Install the Client

```bash
pip install inferencesh
```

#### Run and Get Result
Submit a request and wait for the final result.

```python
import os
from inferencesh import inference

client = inference(api_key=os.environ["INFERENCE_API_KEY"])

## version @4pqv2mpd pinned
result = client.run({
        "app": "krea/krea-2-medium-train@4pqv2mpd",
        "input": {
            "name": "name",
            "images": [
                "https://example.com/file.png"
            ]
        }
    })

print(result["output"])
```

#### Stream Live Updates
Get real-time progress updates as the task runs.

```python
import os
from inferencesh import inference

client = inference(api_key=os.environ["INFERENCE_API_KEY"])

## version @4pqv2mpd pinned
## stream=True yields updates as they arrive
for update in client.run({
        "app": "krea/krea-2-medium-train@4pqv2mpd",
        "input": {
            "name": "name",
            "images": [
                "https://example.com/file.png"
            ]
        }
    }, stream=True):
    if update.get("progress"):
        print(f"progress: {update['progress']}%")
    if update.get("output"):
        print(f"output: {update['output']}")
```

#### Run in the Background
Start the task and get its id back right away, then check on it with `GET /tasks/{id}`. It is done when `status` is 10 (completed), 11 (failed) or 12 (cancelled).

```python
import os
from inferencesh import inference, TaskStatus

client = inference(api_key=os.environ["INFERENCE_API_KEY"])

## returns as soon as the task is created
task = client.run({
        "app": "krea/krea-2-medium-train@4pqv2mpd",
        "input": {
            "name": "name",
            "images": [
                "https://example.com/file.png"
            ]
        }
    }, wait=False)

## later: read its current state
state = client.tasks.get(task["id"]).data
if state["status"] == TaskStatus.COMPLETED:
    print(state["output"])
```

### 2. Files

#### Automatic Upload

```python
## local file paths are automatically uploaded
result = client.run({
    "app": "krea/krea-2-medium-train@4pqv2mpd",
    "input": {
        "image": "/path/to/local/image.png",  # detected & uploaded
        "audio": "https://example.com/audio.mp3",  # url passed through
    }
})
```

#### Manual Upload

```python
## upload and get a hosted URL
file = client.files.upload("/path/to/file.png")
print(file.uri)  # https://cloud.inference.sh/...
```

### 3. Schema

#### Input
- **name** (string) *required*: Name for the trained style.
- **images** (array) *required*: Training images (5-20 recommended).
- **type** (string): Training type: style, object, or character.
- **trigger_word** (string): Trigger word to activate the style in prompts.
- **max_train_steps** (integer): Maximum training steps (1-2000).

#### Output
- **name** (string): Name of the trained style.
- **style_id** (string): Trained style ID for use in Krea 2 Medium generation.

## other image apps

- [Gemini Nano Banana 2.1](https://inference.sh/apps/google/gemini-nano-banana-2-1.md): $1.50/M input, $0.0336–$0.1134/image (1K–4K), +$0.014/query Google Search
- [Grok Imagine Image 2.0](https://inference.sh/apps/xai/grok-imagine-image-2-0.md): $0.04/img low 1k, $0.06/img low 2k, $0.06/img med 1k, $0.08/img med 2k; $0.01/source img (edits)
- [GPT Image 2.5 Sunburst](https://inference.sh/apps/openai/gpt-image-2-5-sunburst.md): $0.006-$0.21 per 1024x1024 image: low $0.006, medium $0.013, high $0.053, xhigh $0.094, max $0.21. Larger sizes cost more; edits add ~$0.008 per reference image.
- [GPT Image 2.5 Flare](https://inference.sh/apps/openai/gpt-image-2-5-flare.md): $0.006-$0.21/image at 1024x1024: low $0.0059, medium $0.0132, high $0.0527, xhigh $0.0937, max $0.2107. Larger sizes cost more; edits add ~$0.0083 per reference image.
- [Image Resize & Crop](https://inference.sh/apps/eval/resize.md): from $0.00000277/sec

## faq

### how much does Krea 2 Medium LoRA Training cost?

$0.50/training run. you pay per run from your inference shell credits. no subscription is required.

### how do I run Krea 2 Medium LoRA Training via api?

call krea/krea-2-medium-train with the javascript or python sdk, the rest api, or `belt app run krea/krea-2-medium-train` from a terminal. the api reference on this page lists every input.

### who makes Krea 2 Medium LoRA Training?

Krea 2 Medium LoRA Training is made by krea and runs on inference shell. every krea app is listed at https://inference.sh/apps/krea.

### can my agent use Krea 2 Medium LoRA Training?

yes. agents call it as a tool through the inference shell mcp server (https://api.inference.sh/mcp), the belt cli or the sdk, and pay per run like you do.

### what are the alternatives to Krea 2 Medium LoRA Training?

other image apps on inference shell include Gemini Nano Banana 2.1, Grok Imagine Image 2.0, GPT Image 2.5 Sunburst, GPT Image 2.5 Flare. they run through the same api, so switching is a one-line change.