Recraft V4 Styles Pro is the higher-resolution raster model in Recraft’s dedicated V4 Styles family. It creates a new image from a text brief and a visual style supplied through reference images or a saved style. The model is intended for campaigns, brand illustration and other image sets where rendering, texture and compositional character need to carry from one asset to the next. It is separate from Recraft V4 Pro and V4.1 Pro, whose style input is optional rather than the defining requirement of the model.
Styles Pro produces 2K raster output, with lossless WebP or PNG formats. A square output in the producer size table is 2048 × 2048 pixels, while a 16:9 output is 2688 × 1536; other supported ratios have their own dimensions. Pro’s larger output can be useful for detailed campaign visuals and larger layouts. The vector variants instead produce SVG and have no fixed pixel size, so this raster Pro edition should not be selected when the intended deliverable is an editable vector file.
Every generation in the Styles family requires a style. Supply one to ten PNG, JPG or WebP reference images, or reuse a compatible saved style; a style identifier and new references are alternative inputs rather than a pair to combine. The producer workflow permits up to 64 MB across references, with each file under 20 MB. Style creation does not require a user-run training step. One clear reference can establish a coherent direction, and several references help when they already share the same visual language rather than competing looks. Each reference must have a shortest side of at least 256 pixels, a longest side of no more than 4,096 pixels and a total resolution of no more than 16 megapixels.
Flexible style matching is the default and allows a looser interpretation of the reference. Precise matching follows rendering, palette, composition and lighting more closely. The reference defines the visual language; the text brief still needs to describe the new subject, action, scene and framing. For a detailed product campaign, specify a glass bottle on a pale stone surface, a three-quarter view, soft side lighting and clear space for a headline, while the supplied reference carries the photographic treatment.
The model accepts prompts up to 10,000 characters, supports preferred colours and a desired background colour, and can use a random seed. The documented generation workflow can return one to six images. Its useful controls differ from older Recraft editions: curated style names, negative_prompt and text_layout are not supported, and the Styles family does not provide image-to-image or inpainting. A reference is a style source, not a mask or an instruction to preserve an existing photograph pixel for pixel.
Prepare clean, sufficiently detailed reference assets and reuse the same style when developing a set. If outputs become repetitive, change the subject, pose, camera angle or scene in the text brief instead of adding an unrelated reference. Exact reference-to-output colour matching is not guaranteed; preferred-colour controls express a direction rather than a colour-proofing result. For the final campaign asset, assess the image at its intended display or print size and check whether the subject, useful negative space and visual treatment match the brief.
", "aboutText": "Recraft V4 Styles Pro is the higher-resolution raster model in Recraft’s dedicated V4 Styles family. It creates a new image from a text brief and a visual style supplied through reference images or a saved style. The model is intended for campaigns, brand illustration and other image sets where rendering, texture and compositional character need to carry from one asset to the next. It is separate from Recraft V4 Pro and V4.1 Pro, whose style input is optional rather than the defining requirement of the model.\n\nStyles Pro produces 2K raster output, with lossless WebP or PNG formats. A square output in the producer size table is 2048 × 2048 pixels, while a 16:9 output is 2688 × 1536; other supported ratios have their own dimensions. Pro’s larger output can be useful for detailed campaign visuals and larger layouts. The vector variants instead produce SVG and have no fixed pixel size, so this raster Pro edition should not be selected when the intended deliverable is an editable vector file.\n\nEvery generation in the Styles family requires a style. Supply one to ten PNG, JPG or WebP reference images, or reuse a compatible saved style; a style identifier and new references are alternative inputs rather than a pair to combine. The producer workflow permits up to 64 MB across references, with each file under 20 MB. Style creation does not require a user-run training step. One clear reference can establish a coherent direction, and several references help when they already share the same visual language rather than competing looks. Each reference must have a shortest side of at least 256 pixels, a longest side of no more than 4,096 pixels and a total resolution of no more than 16 megapixels.\n\nFlexible style matching is the default and allows a looser interpretation of the reference. Precise matching follows rendering, palette, composition and lighting more closely. The reference defines the visual language; the text brief still needs to describe the new subject, action, scene and framing. For a detailed product campaign, specify a glass bottle on a pale stone surface, a three-quarter view, soft side lighting and clear space for a headline, while the supplied reference carries the photographic treatment.\n\nThe model accepts prompts up to 10,000 characters, supports preferred colours and a desired background colour, and can use a random seed. The documented generation workflow can return one to six images. Its useful controls differ from older Recraft editions: curated style names, negative_prompt and text_layout are not supported, and the Styles family does not provide image-to-image or inpainting. A reference is a style source, not a mask or an instruction to preserve an existing photograph pixel for pixel.\n\nPrepare clean, sufficiently detailed reference assets and reuse the same style when developing a set. If outputs become repetitive, change the subject, pose, camera angle or scene in the text brief instead of adding an unrelated reference. Exact reference-to-output colour matching is not guaranteed; preferred-colour controls express a direction rather than a colour-proofing result. For the final campaign asset, assess the image at its intended display or print size and check whether the subject, useful negative space and visual treatment match the brief.", "editorialOverlay": { "copy_fields": null, "copy_sha256": null, "copy_source": null, "html_sha256": "39d7d215797755ea1ddc6ccb1cba067bcf23628b84cf60277b6b86129e81df6d", "module_sha256": "ee9dc1c50b1e6a8fb7fa062030fcb4646b9aaaeb08be513b723a5a92a7290f06", "raw_model_unchanged": true, "schema": "ailoot-native-model-editorial-v1" }, "locale": "en", "methods": [ { "html": "recraft/recraft-v4-styles-proRecraft V4 Styles Pro generates 2K raster images in a reference-defined visual style. It is designed for detailed campaign assets and image sets whose texture, rendering, palette and overall look should remain consistent as the subject changes.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
Recraft V4 Styles Pro is the higher-resolution raster model in Recraft’s dedicated V4 Styles family. It creates a new image from a text brief and a visual style supplied through reference images or a saved style. The model is intended for campaigns, brand illustration and other image sets where rendering, texture and compositional character need to carry from one asset to the next. It is separate from Recraft V4 Pro and V4.1 Pro, whose style input is optional rather than the defining requirement of the model.
Styles Pro produces 2K raster output, with lossless WebP or PNG formats. A square output in the producer size table is 2048 × 2048 pixels, while a 16:9 output is 2688 × 1536; other supported ratios have their own dimensions. Pro’s larger output can be useful for detailed campaign visuals and larger layouts. The vector variants instead produce SVG and have no fixed pixel size, so this raster Pro edition should not be selected when the intended deliverable is an editable vector file.
Every generation in the Styles family requires a style. Supply one to ten PNG, JPG or WebP reference images, or reuse a compatible saved style; a style identifier and new references are alternative inputs rather than a pair to combine. The producer workflow permits up to 64 MB across references, with each file under 20 MB. Style creation does not require a user-run training step. One clear reference can establish a coherent direction, and several references help when they already share the same visual language rather than competing looks. Each reference must have a shortest side of at least 256 pixels, a longest side of no more than 4,096 pixels and a total resolution of no more than 16 megapixels.
Flexible style matching is the default and allows a looser interpretation of the reference. Precise matching follows rendering, palette, composition and lighting more closely. The reference defines the visual language; the text brief still needs to describe the new subject, action, scene and framing. For a detailed product campaign, specify a glass bottle on a pale stone surface, a three-quarter view, soft side lighting and clear space for a headline, while the supplied reference carries the photographic treatment.
The model accepts prompts up to 10,000 characters, supports preferred colours and a desired background colour, and can use a random seed. The documented generation workflow can return one to six images. Its useful controls differ from older Recraft editions: curated style names, negative_prompt and text_layout are not supported, and the Styles family does not provide image-to-image or inpainting. A reference is a style source, not a mask or an instruction to preserve an existing photograph pixel for pixel.
Prepare clean, sufficiently detailed reference assets and reuse the same style when developing a set. If outputs become repetitive, change the subject, pose, camera angle or scene in the text brief instead of adding an unrelated reference. Exact reference-to-output colour matching is not guaranteed; preferred-colour controls express a direction rather than a colour-proofing result. For the final campaign asset, assess the image at its intended display or print size and check whether the subject, useful negative space and visual treatment match the brief.
POST /v1/images/generationstext, imageimage| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits recraft/recraft-v4-styles-pro | Default— |
Fieldprompt | Typestring | RequirementRequired | Values & limits Minimum length: 1 | Default— |
Fieldaspect_ratio | Typestring | RequirementOptional | Values & limits 1:1, 2:1, 1:2, 3:2, 2:3, 4:3, 3:4, 5:4, 4:5, 16:9, 9:16, auto | Default— |
Fieldn | Typeinteger | RequirementOptional | Values & limits Minimum: 1 Maximum: 6 | Default— |
Fieldinput_references | Typearray | RequirementOptional | Values & limits Minimum items: 1 Maximum items: 10 | Default— |
Fieldprovider | Typeobject | RequirementOptional | Values & limits | Default— |
| 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}
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.
Match each charge to the conditions shown. Use one rate for each set of alternative configurations.
| Configuration | Rate schedule | Forecast quantity | Billing unit | Billing conditions | Charge |
|---|---|---|---|---|---|
| ConfigurationBase token rates | Rate scheduleBase rate | Forecast quantity— | Billing unit— | Billing conditions— | 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 |
| ConfigurationInput reference | Rate schedule— | Forecast quantity— | Billing unitper request | Billing conditionsStyle creation when generating with style references; once per request, in addition to the output-image price. | Charge Input · Input reference · Estimate for comparison only $0.01 per request |
| Configurationoutput image | Rate schedule— | Forecast quantity— | Billing unitper output image | Billing conditions— | Charge Output · output image · Estimate for comparison only $0.2 per output image |
| ConfigurationEstimated generation cost | Rate schedule— | Forecast quantityone generation estimate | Billing unit— | Billing conditions— | Charge Output · Estimated generation cost · Estimate for comparison only $0.2 estimate before generation This estimate is not an additional charge or a fixed rate for the completed generation. |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\nexport AILOOT_API_KEY\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np={'model': 'recraft/recraft-v4-styles-pro', 'prompt': 'a red panda astronaut floating in space, studio lighting'}\n\nPath("request.json").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/images/generations \\\n -H "Authorization: Bearer $AILOOT_API_KEY" -H 'Content-Type: application/json' \\\n --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport base64, json, os, subprocess\nfrom pathlib import Path\nfrom urllib.parse import urlsplit, urljoin\n\ndef save_images(items):\n if not items: raise SystemExit("No completed images; retain the full response")\n for index, item in enumerate(items):\n encoded=item.get("b64_json")\n uri=item.get("url", "")\n if not encoded and uri.startswith("data:image/"):\n header, separator, encoded=uri.partition(",")\n if not separator or ";base64" not in header: raise SystemExit("Unsupported image data URI")\n if encoded:\n raw=base64.b64decode(encoded,validate=True)\n elif uri:\n uri=urljoin("https://api.ailoot.ai",uri)\n parsed=urlsplit(uri)\n if parsed.scheme!="https" or not parsed.netloc or parsed.username or parsed.password:\n raise SystemExit("Invalid returned image URL")\n owned=parsed.netloc=="api.ailoot.ai" and parsed.path.startswith("/v1/media/assets/") and parsed.path.endswith("/content")\n args=["curl","--fail-with-body","--silent","--show-error",uri]\n if owned: args += ["-H","Authorization: Bearer "+os.environ["AILOOT_API_KEY"]]\n temporary=Path(f"image-{index}.bin")\n subprocess.run(args+["-o",str(temporary)],check=True)\n raw=temporary.read_bytes()\n temporary.unlink()\n else: raise SystemExit("Image has neither bytes nor URL")\n if not raw: raise SystemExit("Empty image result")\n 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"\n Path(f"image-{index}.{ext}").write_bytes(raw)\n print("Every returned image saved; complete response metadata retained")\nsave_images(json.loads(Path("result.json").read_text())["data"])\nPY_RESULT\nDownload 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}set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/media/assets \\\n -H "Authorization: Bearer $AILOOT_API_KEY" -o owned-assets.json\n# Preserve every returned asset and follow its exact signed content URL. Do not construct a signed token.\nSave 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.
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.
| Field | Type |
|---|---|
Fieldcreated | Type |
Fielddata[].url | Type |
Fielddata[].b64_json | Type |
Fieldusage | Type |
Ailoot Ultra recraft/recraft-v4-styles-pro
/v1/images