Krea 2 Turbo with LoRA support runs custom LoRAs (trained on Krea 2 Raw, comfy or diffusers naming) on the 8-step distilled Krea 2 engine, generating personalized images natively at 1K to 2K resolution, with both text-to-image and image-to-image supported. Ready-to-use REST inference API, best performance, no cold starts, affordable pricing.
Idle

$0.018per run·~55 / $1

A graceful young woman in a dramatic black ballet-inspired dress, captured mid-turn with one leg extended and arms curved elegantly, dark feathers and layered fabric sweeping outward, spotlight cutting through a dim theater, pale skin, intense gaze, fine-art fashion photography, expressive movement, artistic and cinematic, highly detailed.

A rugged handsome foreign man standing in a dusty frontier town at sunset, captured in the moment of tossing a wide-brimmed hat upward with one hand while the other rests near his belt, long coat moving in the wind, leather boots, subtle stubble, golden dust in the air, cinematic western art style, dramatic backlight, richly textured realism.
Krea 2 Turbo LoRA is a fast, aesthetic-first image generation model for both text-to-image and image-to-image workflows. It supports native 1k and 2k output, and adds on-the-fly LoRA loading so you can apply up to 3 LoRAs in a single request for more targeted style and subject control.
Native high-resolution generation
Generate images at 1k or 2k resolution without relying on a separate upscaling pass.
Fast Turbo workflow
The Turbo checkpoint is optimized for fast generation, making it suitable for quick prompt iteration and production workflows.
LoRA support
Load up to 3 LoRAs per request, each with its own scale, for stronger style, subject, or concept control.
Text-to-image and image-to-image
Generate from a text prompt alone, or provide an image input for guided restyling and variation.
Flexible image-to-image strength
Use strength to control how strongly the model follows or repaints the source image.
Wide aspect ratio support
Supports square, portrait, landscape, tall, wide, and cinematic aspect ratio presets.
| Parameter | Required | Description |
|---|---|---|
| prompt | Yes | Text description of the desired image. |
| resolution | No | Output resolution: 1k or 2k. |
| aspect_ratio | No | Output aspect ratio. Options: 1:1, 1:2, 2:1, 1:3, 3:1, 2:3, 3:2, 3:4, 4:3, 4:5, 5:4, 9:16, 16:9, 9:21, or 21:9. |
| image | No | Source image URL. When provided, the model runs image-to-image generation. |
| strength | No | Controls how strongly the source image is repainted in image-to-image mode. Range: 0–1. |
| loras | No | Up to 3 LoRA objects. Each object uses {path, scale}, where path is a direct .safetensors URL and scale controls LoRA intensity. |
| seed | No | Random seed. Use -1 for a random seed. |
1k for faster iteration or 2k for higher-resolution output.image when using image-to-image generation.path and scale.Pricing is based on selected resolution.
| Resolution | Cost per image |
|---|---|
| 1k | $0.018 |
| 2k | $0.03 |
2k when you need more detailed final output.1k for faster testing and 2k for final-quality output.strength around 0.4–0.6 usually preserves more composition, while 0.7–0.9 allows more aggressive repainting.scale around 0.8–1.0, then lower it if the LoRA effect becomes too dominant.seed when comparing prompt or LoRA changes.Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/wavespeed-ai/krea-v2/turbo-lora with your input as JSON. The endpoint returns a prediction id. Start polling the result endpoint around every 2 seconds, increase the interval for long-running tasks, and stop on any terminal status. On completed, read output values from data.outputs. Examples for Krea v2 Turbo Lora below.
set -euo pipefail
: "${WAVESPEED_API_KEY:?Set WAVESPEED_API_KEY}"
REQUEST_BODY=$(cat <<'JSON'
{
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"aspect_ratio": "1:1",
"resolution": "1k",
"strength": 0.8,
"seed": -1
}
JSON
)
# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
-X POST "https://api.wavespeed.ai/api/v3/wavespeed-ai/krea-v2/turbo-lora" \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $WAVESPEED_API_KEY" \
-d "$REQUEST_BODY")
TASK=$(printf '%s' "$SUBMIT_RESPONSE" | jq 'if has("data") then .data else . end')
PREDICTION_ID=$(printf '%s' "$TASK" | jq -r '.id')
if [ -z "$PREDICTION_ID" ] || [ "$PREDICTION_ID" = "null" ]; then
printf 'Submission response did not contain a prediction id
' >&2
exit 1
fi
RESULT_URL=$(printf '%s' "$TASK" | jq -r '.urls.get // empty')
if [ -z "$RESULT_URL" ]; then
RESULT_URL="https://api.wavespeed.ai/api/v3/predictions/$PREDICTION_ID/result"
fi
# 2. Poll until the prediction finishes.
while true; do
RESPONSE=$(curl --silent --show-error --fail-with-body "$RESULT_URL" \
-H "Authorization: Bearer $WAVESPEED_API_KEY")
RESULT=$(printf '%s' "$RESPONSE" | jq 'if has("data") then .data else . end')
STATUS=$(printf '%s' "$RESULT" | jq -r '.status')
case "$STATUS" in
completed) printf '%s\n' "$RESULT" | jq '.outputs'; break ;;
failed|cancelled|timeout) printf '%s\n' "$RESULT" | jq . >&2; exit 1 ;;
created|processing) sleep 2 ;;
*) printf 'Unexpected status: %s
' "$STATUS" >&2; exit 1 ;;
esac
doneconst submitUrl = "https://api.wavespeed.ai/api/v3/wavespeed-ai/krea-v2/turbo-lora";
const apiKey = process.env.WAVESPEED_API_KEY;
if (!apiKey) throw new Error('Set WAVESPEED_API_KEY');
async function requestJson(url, options = {}) {
const response = await fetch(url, options);
if (!response.ok) throw new Error(await response.text());
return response.json();
}
// 1. Submit the prediction.
const body = await requestJson(submitUrl, {
method: "POST",
headers: {
"Authorization": `Bearer ${apiKey}`,
"Content-Type": "application/json",
},
body: JSON.stringify({
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"aspect_ratio": "1:1",
"resolution": "1k",
"strength": 0.8,
"seed": -1
}),
});
const task = body.data ?? body;
if (!task.id) throw new Error("Submission response did not contain a prediction id");
const resultUrl = task.urls?.get ||
`https://api.wavespeed.ai/api/v3/predictions/${task.id}/result`;
// 2. Poll until the prediction finishes.
while (true) {
const resultBody = await requestJson(resultUrl, {
headers: { "Authorization": `Bearer ${apiKey}` },
});
const result = resultBody.data ?? resultBody;
if (result.status === "completed") {
console.log(result.outputs);
break;
}
if (["failed", "cancelled", "timeout"].includes(result.status)) throw new Error(JSON.stringify(result));
if (!["created", "processing"].includes(result.status)) throw new Error("Unexpected status: " + result.status);
await new Promise(resolve => setTimeout(resolve, 2000));
}import json
import os
import time
from urllib.request import Request, urlopen
api_key = os.environ["WAVESPEED_API_KEY"]
headers = {"Authorization": f"Bearer {api_key}", "Content-Type": "application/json"}
payload = {
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"aspect_ratio": "1:1",
"resolution": "1k",
"strength": 0.8,
"seed": -1
}
def request_json(url, data=None):
request = Request(url, data=data, headers=headers, method="POST" if data else "GET")
with urlopen(request) as response:
return json.load(response)
# 1. Submit the prediction.
body = request_json("https://api.wavespeed.ai/api/v3/wavespeed-ai/krea-v2/turbo-lora", json.dumps(payload).encode())
task = body.get("data", body)
if not task.get("id"):
raise RuntimeError("Submission response did not contain a prediction id")
result_url = task.get("urls", {}).get("get") or f"https://api.wavespeed.ai/api/v3/predictions/{task['id']}/result"
# 2. Poll until the prediction finishes.
while True:
result_body = request_json(result_url)
result = result_body.get("data", result_body)
status = result.get("status")
if status == "completed":
print(result.get("outputs", []))
break
if status in {"failed", "cancelled", "timeout"}:
raise RuntimeError(result)
if status not in {"created", "processing"}:
raise RuntimeError(f"Unexpected status: {status}")
time.sleep(2)Krea v2 Turbo Lora is a WaveSpeedAI model for AI inference, exposed as a REST API on WaveSpeedAI. Krea 2 Turbo with LoRA support runs custom LoRAs (trained on Krea 2 Raw, comfy or diffusers naming) on the 8-step distilled Krea 2 engine, generating personalized images natively at 1K to 2K resolution, with both text-to-image and image-to-image supported. Ready-to-use REST inference API, best performance, no cold starts, affordable pricing. You can call it programmatically or try it from the playground above.
POST your input parameters to the model's REST endpoint (shown in the API tab of this playground) with your WaveSpeedAI API key in the Authorization header. Submission returns a prediction ID. Poll the result endpoint starting around every 2 seconds, increase the interval for long-running tasks, and stop on any terminal status. The playground generates production-oriented Python, JavaScript, and cURL examples with timeouts, transient-error handling, and safe GET retries. Full request/response shape is documented at https://wavespeed.ai/docs/docs-api/wavespeed-ai/krea-v2-turbo-lora.
Krea v2 Turbo Lora starts at $0.018 per run. That figure is the base price — the final charge scales with the parameters you set in the form (output size, length, count, references, or whatever knobs this model exposes), so a higher-quality or larger output costs more than a minimal one. The exact cost for your current input is shown live next to the Generate button before you submit, and the actual per-call charge is recorded on the prediction afterwards.
Key inputs: `prompt`, `image`, `aspect_ratio`, `resolution`, `seed`, `enable_base64_output`. The full JSON schema (types, defaults, allowed values) is rendered above the Generate button and mirrored in the API reference at https://wavespeed.ai/docs/docs-api/wavespeed-ai/krea-v2-turbo-lora.
Sign up for a free WaveSpeedAI account to claim starter credits, copy your API key from /accesskey, then call the endpoint shown in the API tab of the playground. The playground also auto-generates a code sample in Python, JavaScript, or cURL for the parameters you've set.
Commercial usage rights depend on the model's license, set by its provider (WaveSpeedAI). The license summary appears on the model card above; see WaveSpeedAI's Terms of Service for platform-level conditions.