Recraft AI Recraft V3
Playground
Try it on WaveSpeedAI!Recraft V3 (red_panda) is a state-of-the-art text-to-image model that excels with long text prompts and generates diverse, high-fidelity images across many styles. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
Features
Generate stunning images across a vast range of artistic styles with Recraft V3. From ultra-realistic portraits to pixel art and hand-drawn illustrations, this versatile model offers one of the most extensive style libraries available — perfect for any creative vision.
Why It Looks Great
- Massive style library: 20+ specialized styles covering realistic to stylized aesthetics.
- Ultra-realistic capability: Photorealistic output with fine detail like skin texture and pores.
- Digital illustration mastery: Comprehensive range of illustration sub-styles.
- Flexible aspect ratios: Multiple format options for any use case.
- Prompt Enhancer: Built-in tool to refine your descriptions automatically.
- Consistent quality: Professional-grade output across all style categories.
Parameters
| Parameter | Required | Description |
|---|---|---|
| prompt | Yes | Text description of the image you want to generate. |
| aspect_ratio | No | Output format: 1:1, 16:9, 9:16, 4:3, 3:4, etc. Default: 1:1. |
| style | No | Visual style preset (see Style Guide below). |
How to Use
- Write your prompt — describe the image you want to create in detail.
- Use Prompt Enhancer (optional) — click to automatically enrich your description.
- Set aspect ratio — choose the format that fits your use case.
- Choose style — select from the extensive style library.
- Run — click the button to generate.
- Download — preview and save your image.
Pricing
Flat rate per image generation.
| Output | Cost |
|---|---|
| Per image | $0.04 |
Style Guide
Realistic Styles
| Style | Description |
|---|---|
| realistic_image | Ultra-photorealistic output with fine details |
Digital Illustration Styles
| Style | Description |
|---|---|
| digital_illustration | General digital artwork |
| digital_illustration/pixel_art | Retro pixel-based graphics |
| digital_illustration/hand_drawn | Traditional hand-drawn aesthetic |
| digital_illustration/grain | Textured, grainy illustration style |
| digital_illustration/infantile_sketch | Childlike sketch aesthetic |
| digital_illustration/2d_art_poster | Bold poster art style |
| digital_illustration/handmade_3d | Crafted 3D-style illustrations |
| digital_illustration/hand_drawn_outline | Clean outline-based art |
| digital_illustration/engraving_color | Colored engraving aesthetic |
| digital_illustration/psychedelic | Trippy, vibrant psychedelic art |
| digital_illustration/pop_art | Bold pop art style |
| digital_illustration/watercolor | Watercolor painting effect |
| digital_illustration/japanese_ink | Traditional Japanese ink wash |
| digital_illustration/glow | Glowing, luminous effects |
| digital_illustration/stencil | Cut-out stencil aesthetic |
| digital_illustration/sticker_designs | Sticker-ready graphics |
| …and more | Additional styles available |
Best Use Cases
- Photorealistic Portraits — Create lifelike portraits with detailed skin texture and lighting.
- Digital Art & Illustration — Generate artwork in various artistic styles.
- Pixel Art & Retro — Create nostalgic pixel-based graphics for games and media.
- Poster & Print Design — Produce bold visual designs for marketing.
- Concept Art — Explore ideas across multiple visual aesthetics.
- Social Media Content — Generate eye-catching visuals in any style.
Example Prompts
- “Ultra-realistic portrait of a young woman with windswept hair, wearing a leather jacket, golden hour lighting, 85mm lens, cinematic color grading, visible skin texture and pores”
- “pixel art character sprite of a knight, 16-bit style, detailed armor, fantasy RPG”
- “hand drawn illustration of a cozy coffee shop interior, warm colors, sketch aesthetic”
- “psychedelic poster art of a cosmic owl, vibrant colors, swirling patterns”
- “watercolor painting of a Japanese garden in autumn, soft edges, traditional style”
- “pop art portrait in the style of Warhol, bold colors, high contrast”
Pro Tips for Best Results
- Use realistic_image style with detailed physical descriptions for photorealistic output.
- Include camera/lens details for realistic style: “85mm lens”, “f/1.4”, “bokeh”.
- For illustrations, match the sub-style to your intended use case.
- Explore different styles with the same prompt to find your preferred aesthetic.
- The style library is extensive — scroll through all options to discover more.
- Combine style selection with detailed prompts for maximum control.
Notes
- The style library contains many more options than listed — explore the dropdown.
- Processing time may vary based on style complexity.
- Realistic style excels at portraits with fine details like skin texture.
- Each style is optimized for its specific aesthetic category.
Authentication
For authentication details, please refer to the Authentication Guide.
API Endpoints
Submit Task & Query Result
set -euo pipefail
export WAVESPEED_API_KEY="your-api-key"
REQUEST_BODY=$(cat <<'JSON'
{
"prompt": "A cinematic ocean wave at sunrise, highly detailed",
"aspect_ratio": "1:1",
"style": "realistic_image"
}
JSON
)
# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
-X POST "https://api.wavespeed.ai/api/v3/recraft-ai/recraft-v3" \
-H "Authorization: Bearer ${WAVESPEED_API_KEY}" \
-H "Content-Type: application/json" \
-d "${REQUEST_BODY}")
TASK=$(printf '%s' "${SUBMIT_RESPONSE}" | jq 'if type == "object" and has("data") then .data else . end')
PREDICTION_ID=$(printf '%s' "${TASK}" | jq -r '.id // empty')
if [ -z "${PREDICTION_ID}" ]; then
printf 'Submission response did not contain a prediction id
' >&2
exit 1
fi
RESULT_URL=$(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' "${RESPONSE}" | jq 'if type == "object" and has("data") then .data else . end')
STATUS=$(printf '%s' "${RESULT}" | jq -r '.status // empty')
case "${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
doneParameters
Task Submission Parameters
Request Parameters
| Parameter | Type | Required | Default | Range | Description |
|---|---|---|---|---|---|
| prompt | string | Yes | - | The positive prompt for the generation. | |
| aspect_ratio | string | No | 1:1 | 1:1, 16:9, 9:16, 4:3, 3:4 | The aspect ratio of the generated media. |
| style | string | No | - | realistic_image, digital_illustration, digital_illustration/pixel_art, digital_illustration/hand_drawn, digital_illustration/grain, digital_illustration/infantile_sketch, digital_illustration/2d_art_poster, digital_illustration/handmade_3d, digital_illustration/hand_drawn_outline, digital_illustration/engraving_color, digital_illustration/2d_art_poster_2, realistic_image/b_and_w, realistic_image/hard_flash, realistic_image/hdr, realistic_image/natural_light, realistic_image/studio_portrait, realistic_image/enterprise, realistic_image/motion_blur | Style of the generated image. |
| enable_base64_output | boolean | No | false | - | If set to `true`, the prediction's `output` strings are returned as **naked base64** (no `data:<mime>;base64,` prefix). When `false` (default), outputs are returned as URLs pointing to our CDN. |
Response Parameters
| Parameter | Type | Description |
|---|---|---|
| code | integer | HTTP status code (e.g., 200 for success) |
| message | string | Status message (e.g., “success”) |
| data.id | string | Unique identifier for the prediction, Task Id |
| data.model | string | Model ID used for the prediction |
| data.outputs | array | Output values, usually URL strings; some models return text strings or structured result objects (empty when status is not completed) |
| data.urls | object | Object containing related API endpoints |
| data.urls.get | string | URL to retrieve the prediction result |
| data.status | string | Status of the task: created, processing, completed, or failed |
| data.created_at | string | ISO timestamp of when the request was created (e.g., “2023-04-01T12:34:56.789Z”) |
| data.error | string | Error message (empty if no error occurred) |
| data.timings | object | Object containing timing details |
| data.timings.inference | integer | Inference time in milliseconds |
Result Request Parameters
| Parameter | Type | Required | Default | Description |
|---|---|---|---|---|
| id | string | Yes | - | Task ID |
Result Response Parameters
| Parameter | Type | Description |
|---|---|---|
| code | integer | HTTP status code (e.g., 200 for success) |
| message | string | Status message (e.g., “success”) |
| data | object | The prediction data object containing all details |
| data.id | string | Unique identifier for the prediction |
| data.model | string | Model ID used for the prediction |
| data.outputs | array<string | object> | Array of generated outputs (empty when status is not completed). Items are usually URL strings, but may be text strings or structured result objects, depending on the model. |
| data.urls | object | Object containing related API endpoints |
| data.urls.get | string | URL to poll for the prediction result |
| data.status | string | Status: created, processing, completed, or failed |
| data.created_at | string | ISO timestamp of when the request was created |
| data.error | string | Error message (empty if no error occurred) |
| data.timings | object | Object containing timing details |
| data.timings.inference | integer | Inference time in milliseconds |