Krea: Krea 2 Medium Turbo
Krea 2 Medium Turbo is Krea’s fast image-generation edition for exploring visual ideas and producing expressive drafts. It combines a distilled sampling schedule with text, source-image and style controls, including independent adjustments for intensity, complexity and implied motion.
About the model
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
Fast exploration within the Krea 2 family
Krea 2 Medium Turbo is the generation edition Krea presents as Krea 2 Turbo. Its model-specific interface identifies the Medium Turbo variant, and Krea’s user guide describes a distilled sampling schedule that reduces the work needed to generate an image. Krea positions it as the family’s fastest option for broad creative exploration, expressive rough drafts, illustration and graphic directions.
Use it when the immediate goal is to compare ideas: alternative compositions for a cover, visual treatments for a campaign or different illustration styles for the same scene. A concise, concrete starting brief makes comparisons easier. For example: “A folded red paper bird above a pale-blue desk, bold editorial illustration, hard afternoon shadow, simple geometric shapes, vertical composition with clear space at the bottom.” Keep the subject and frame steady while exploring the visual treatment, then develop the selected direction further.
Krea’s edition guidance favors Medium when a more stable illustration treatment is needed and Large for a photographic or raw-textured final direction. Turbo remains its own edition; a later pass in another model is a separate generation rather than an automatic quality upgrade or an identical continuation.
Prepare the prompt and visual inputs
The model’s generation schema requires a prompt, aspect ratio and resolution. Optional image-to-image input starts generation from a source image rather than pure noise. Its denoising strength runs from 0 to 1: 0 keeps the input, 1 fully replaces it, and the documented default is 0.99. Prepare the starting composition carefully and describe what should change; a high strength allows substantial replacement of the source.
Style references supply appearance through images rather than changing the starting-image strength. The model-specific schema limits source-image and style-reference URI strings to 1,024 characters. The model-specific request schema accepts up to ten references, each with influence from 0 to 1 and a default of 0.5. Select references with clear roles, such as a color palette, drawing treatment or lighting direction. The separate Krea workspace guide describes up to four style references in that interface; the two interfaces should be prepared with their respective limits.
Moodboards organize a coherent visual direction into a reusable input. Create the moodboard first and use its existing identifier when generating. The model schema accepts one moodboard, with influence from 0 to 1 and a default of 0.23. Trained styles, typically LoRAs, are another input selected by identifier and strength from -2 to 2. A source image, a style reference, a moodboard and a trained style have different roles, so avoid treating them as interchangeable ways to preserve every detail.
Adjust creativity and the three visual sliders
Creativity controls prompt expansion. Raw disables it; low, medium and high change how much interpretation is added to the brief. The model-specific schema defaults to low. Use a restrained setting to compare a precise brief, or increase interpretation when the purpose is to discover a broader range of ideas.
Intensity, Complexity and Movement are independent integer sliders from -100 to 100, with 0 neutral. Intensity moves between muted and bold treatment. Complexity moves between simpler compositions and denser detail. Movement changes pose, visual energy and implied motion. These sliders can be combined with references and moodboards, and they are separate from creativity’s prompt expansion.
For the paper-bird brief, first compare a clean composition with a more detailed one while holding the other settings steady. Then explore a stronger visual treatment or a more energetic pose. Change one control at a time and keep the optional seed, prompt and reference set recorded. Movement affects a still image’s character; it does not produce an animated bird, camera move or video sequence.
Frames, batches and completed images
The model-specific generation schema offers a 1K resolution scale and nine aspect ratios: 1:1, 4:3, 3:2, 16:9, 2.35:1, 4:5, 3:4, 2:3 and 9:16. Krea’s Turbo workspace guide also describes generating up to four images in a batch. That batch setting belongs to the documented workspace workflow; it is distinct from the individual generation request schema.
Select the frame for the intended asset before generation. A vertical cover needs a different balance of subject and open space from a wide editorial image. Keep the generation scale separate from any subsequent enhancement or finished-layout export.
Krea’s documented generation flow returns a job that may initially be pending. Follow the job to completion and retrieve its resulting image locations. Compare the actual finished candidates for composition, shape, texture, palette and visible text, then preserve the selected image with its inputs and settings. If the asset needs precise lettering, place or correct that lettering in the finished design.
Turbo’s fast-exploration role does not guarantee a particular completion time, perfect lettering or an exact reconstruction of a reference image. Source-image strength and reference influence still require inspection of the result. Use the edition to resolve visual direction efficiently, select a concrete candidate, and make any final detail, layout or production corrections required by the intended use.
Ailoot Ultra · Images POST /v1/images/generations krea/krea-2-medium-turbo
krea/krea-2-medium-turboOverview
Krea 2 Medium Turbo is Krea’s fast image-generation edition for exploring visual ideas and producing expressive drafts. It combines a distilled sampling schedule with text, source-image and style controls, including independent adjustments for intensity, complexity and implied motion.
- Accepted inputs
- Text · Images
- Results
- Images
Available in Ailoot · inputs & methods
Ailoot Ultra · Images POST /v1/images/generations
- Input types
text,image- Output types
image
| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits krea/krea-2-medium-turbo | Default— |
Fieldprompt | Typestring | RequirementRequired | Values & limits Minimum length: 1 | Default— |
Fieldresolution | Typestring | RequirementOptional | Values & limits 1K | Default— |
Fieldaspect_ratio | Typestring | RequirementOptional | Values & limits 1:1, 4:3, 3:2, 16:9, 4:5, 2:3, 9:16 | Default— |
Fieldinput_references | Typearray | RequirementOptional | Values & limits Minimum items: 0 Maximum items: 1 | Default— |
Fieldprovider | Typeobject | RequirementOptional | Values & limits | Default— |
Method parameters and lifecycle
| Parameter | Contract |
|---|---|
Parametercontent_type | Contractapplication/json |
Parameterrequired | Contractmodel, prompt |
Parametermaterial_types | Contracttext, image |
Lifecycle: synchronous_result_then_owned_library
GET /v1/media/tasks/{task_id} · actual returned task_id or media library record
GET /v1/media/assets/{asset_id}/content
GET /v1/media/assets
GET /v1/media/assets/{asset_id}
Pricing
How the final charge is calculated
The displayed rates estimate the cost before generation. The final charge is calculated from the cost recorded for the original generation. Measured output duration and forecast quantities are not the final billable quantity.
Tariff references do not add request options. Supported parameters are listed for the selected method.
- Fast mode
- Not specified When fast mode is selected
- Flex mode
- Not specified When flex mode is selected
- Maximum reasoning effort
- Not specified When maximum reasoning effort uses the default adjustment
Estimated rates for comparison
Prices by configuration
Match each charge to the conditions shown. Use one rate for each set of alternative configurations.
| Configuration | Rate schedule | Forecast quantity | Charge |
|---|---|---|---|
| ConfigurationBase token rates | Rate scheduleBase rate | Forecast quantity— | Charge Input · Input tokens · Estimate for comparison only — / 1K tokens Output · Output tokens · Estimate for comparison only — / 1K tokens Input · Cache read · Estimate for comparison only — / 1K tokens Input · Cache write · Estimate for comparison only — / 1K tokens Input · Cache write, 1 hour · Estimate for comparison only — / 1K tokens |
| ConfigurationEstimated generation cost | Rate schedule— | Forecast quantityone generation estimate | Charge Output · Estimated generation cost · Estimate for comparison only $0.03 estimate before generation This estimate is not an additional charge or a fixed rate for the completed generation. |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
Example requests
Ailoot Ultra · Images
set -eu
: "${AILOOT_API_KEY:?Set your Ailoot API key}"
export AILOOT_API_KEY
python3 - <<'PY_REQUEST'
import json,os
from pathlib import Path
p={'model': 'krea/krea-2-medium-turbo', 'prompt': 'a red panda astronaut floating in space, studio lighting'}
Path("request.json").write_text(json.dumps(p,ensure_ascii=False))
PY_REQUEST
curl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/images/generations \
-H "Authorization: Bearer $AILOOT_API_KEY" -H 'Content-Type: application/json' \
--data-binary @request.json -D response-headers.txt -o result.json
python3 - <<'PY_RESULT'
import base64, json, os, subprocess
from pathlib import Path
from urllib.parse import urlsplit, urljoin
def save_images(items):
if not items: raise SystemExit("No completed images; retain the full response")
for index, item in enumerate(items):
encoded=item.get("b64_json")
uri=item.get("url", "")
if not encoded and uri.startswith("data:image/"):
header, separator, encoded=uri.partition(",")
if not separator or ";base64" not in header: raise SystemExit("Unsupported image data URI")
if encoded:
raw=base64.b64decode(encoded,validate=True)
elif uri:
uri=urljoin("https://api.ailoot.ai",uri)
parsed=urlsplit(uri)
if parsed.scheme!="https" or not parsed.netloc or parsed.username or parsed.password:
raise SystemExit("Invalid returned image URL")
owned=parsed.netloc=="api.ailoot.ai" and parsed.path.startswith("/v1/media/assets/") and parsed.path.endswith("/content")
args=["curl","--fail-with-body","--silent","--show-error",uri]
if owned: args += ["-H","Authorization: Bearer "+os.environ["AILOOT_API_KEY"]]
temporary=Path(f"image-{index}.bin")
subprocess.run(args+["-o",str(temporary)],check=True)
raw=temporary.read_bytes()
temporary.unlink()
else: raise SystemExit("Image has neither bytes nor URL")
if not raw: raise SystemExit("Empty image result")
ext="png" if raw.startswith(b"\x89PNG") else "jpg" if raw.startswith(b"\xff\xd8") else "webp" if raw[:4]==b"RIFF" and raw[8:12]==b"WEBP" else "svg" if raw.lstrip().startswith((b"<svg",b"<?xml")) else "bin"
Path(f"image-{index}.{ext}").write_bytes(raw)
print("Every returned image saved; complete response metadata retained")
save_images(json.loads(Path("result.json").read_text())["data"])
PY_RESULT
Receive and save results
Ailoot Ultra · Images
Download each returned image or save its Base64 contents
GET /v1/media/tasks/{task_id}GET /v1/media/assets/{asset_id}/contentGET /v1/media/assetsGET /v1/media/assets/{asset_id}
Other content reads
set -eu
: "${AILOOT_API_KEY:?Set your Ailoot API key}"
curl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/media/assets \
-H "Authorization: Bearer $AILOOT_API_KEY" -o owned-assets.json
# Preserve every returned asset and follow its exact signed content URL. Do not construct a signed token.
Keep all completed results
Save every completed image; retrieve each returned URL or decode its Base64 contents.
Retain the complete response and headers, every actual output, original returned identifiers and all usage fields. Recover the original operation without submitting creation again.
If the original response needs checking
Keep the returned X-Client-Request-ID for reconciliation. Read only actual returned task_id/asset_id values or the owned media library; never build a task URL from the operation ID and never resubmit creation.
Response fields
| Field | Type |
|---|---|
Fieldcreated | Type |
Fielddata[].url | Type |
Fielddata[].b64_json | Type |
Fieldusage | Type |
Aliases
Model aliases
Ailoot Ultra krea/krea-2-medium-turbo
Method path aliases
/v1/images
Related caller IDs
FAQ · Krea: Krea 2 Medium Turbo
- What inputs and results are available?
POST /v1/images/generations·krea/krea-2-medium-turbo:text,image→image- Which fields does the request use?
POST /v1/images/generations·krea/krea-2-medium-turbo:model,prompt,resolution,aspect_ratio,input_references,provider