ImagineArt: ImagineArt 2.0
imagineart-2-0- Price
- From $0.05
- Modalities
- Image
About ImagineArt 2.0
ImagineArt 2.0 is a reasoning-based image model from ImagineArt, designed to follow detailed instructions. It reads the whole prompt as a scene brief before rendering, then draws realistic, cinematic, or illustrated results with a dedicated color step aimed at true-to-life saturation. It is used for text-to-image generation.
Where it works well
- A reasoning layer works out spatial relations, lighting, and composition from the full prompt before drawing.
- A dedicated color codec aims for vibrant, true-to-life color without washed-out output.
- Covers photorealism and cinematic looks as well as posters, illustrations, and anime.
- Typography is a stated focus: stylized lettering is meant to stay readable and balanced.
- Instruction-faithful output: long prompts with several subjects and constraints tend to be followed closely.
When to choose another model
- It generates from text prompts alone, without reference-image input or editing.
- Text-to-image output comes in 1K and 2K modes, so very large prints need upscaling.
- Exact spelling in rendered lettering still needs a check; keep quoted words short.
Getting started
Create API key
Create a key in Console, then use it with every model on the platform.
Send your first request
Copy the example for your language and run it against the endpoint.
Image editingText to imageTokenLab endpointPOST/v1/images/generationscurl -X POST "https://api.tokenlab.sh/v1/images/generations" \ -H "Authorization: Bearer sk-xxx" \ -H "Content-Type: application/json" \ -d '{ "operation": "text-to-image", "model": "imagineart-2-0", "prompt": "A minimalist product photo of matte black headphones on a soft blue background." }'
Parameters
Image editing
| Parameter | Values and limits | Default | Notes |
|---|---|---|---|
image | Inputs: ≥ 1, ≤ 1 | Not provided | Source image: a public image URL or a data URL (multipart file upload also works). Send one image. The output keeps the source aspect ratio at about 1.5K. |
image_url | Inputs: ≥ 1, ≤ 1 | Not provided | Source image: a public image URL or a data URL (multipart file upload also works). Send one image. The output keeps the source aspect ratio at about 1.5K. |
n | 1 | 1 | Use an integer. |
operation | Not provided | Not provided | Not provided |
output_format | jpeg, png, webp | Not provided | Default encoding is shared by these equivalent values: jpg, jpeg. |
prompt | Not provided | Not provided | Minimum length: 2 characters. Maximum length: 3000 characters. |
seed | ≥ 0, ≤ 9007199254740991 | Not provided | Use an integer. |
Text to image
| Parameter | Values and limits | Default | Notes |
|---|---|---|---|
height | 512, 560, 640, 768, 848, 1024, 1072, 1152, 1360, 1680, 2048 | 1024 | Use an integer. Use a listed width and height pair: 1024x1024 (1k, 1:1), 1680x560 (1k, 3:1), 560x1680 (1k, 1:3), 1360x768 (1k, 16:9), 768x1360 (1k, 9:16), 1024x768 (1k, 4:3), 768x1024 (1k, 3:4), 1152x768 (1k, 3:2), 768x1152 (1k, 2:3), 1488x640 (1k, 21:9), 848x1072 (1k, 4:5), 1072x848 (1k, 5:4), 2048x512 (1k, 4:1), 512x2048 (1k, 1:4). |
images | Not provided | Not provided | Text-to-image does not accept source images. Do not send this field for that operation. Use one of this model's declared image operations for source-image requests. |
n | 1 | 1 | Use an integer. |
operation | Not provided | Not provided | Not provided |
output_format | jpeg, png, webp | Not provided | Default encoding is shared by these equivalent values: jpg, jpeg. |
prompt | Not provided | Not provided | Minimum length: 2 characters. Maximum length: 3000 characters. |
seed | ≥ 0, ≤ 9007199254740991 | Not provided | Use an integer. |
width | 512, 560, 768, 848, 1024, 1072, 1152, 1360, 1488, 1680, 2048 | 1024 | Use an integer. Use a listed width and height pair: 1024x1024 (1k, 1:1), 1680x560 (1k, 3:1), 560x1680 (1k, 1:3), 1360x768 (1k, 16:9), 768x1360 (1k, 9:16), 1024x768 (1k, 4:3), 768x1024 (1k, 3:4), 1152x768 (1k, 3:2), 768x1152 (1k, 2:3), 1488x640 (1k, 21:9), 848x1072 (1k, 4:5), 1072x848 (1k, 5:4), 2048x512 (1k, 4:1), 512x2048 (1k, 1:4). |
Fields outside this contract are rejected.
Pricing
The Verified price applies to Verified, which costs less on most models. The Official price is the model maker's published price and applies to the more reliable Official route. Auto bills the route that completes the request.
Text to image
per image- Official price
- $0.05
- Verified price
- —
- Discount
- —
Image editing
per image- Official price
- $0.057
- Verified price
- —
- Discount
- —
| Official priceper image | Verified priceper image | Discount | |
|---|---|---|---|
| Text to image | $0.05 | — | — |
| Image editing | $0.057 | — | — |
Usage & activity
Success rate is the share of requests that completed. Latency is how long a full response takes; P95 means 95% of requests finished within that time.
Usage & availability
Last 24 hours- Requests
- Success rate
- P95 latency
- Total tokens
Data is based on aggregate user requests, excluding status checks.
Open in Console
Open ImagineArt 2.0 in Console with a prompt ready to edit or send.
Help me create an image with imagineart-2-0 using text-to-image at /v1/images/generations. Show the result, cost, and any limits I should know.
Use cases
Best for- Text to Image
Cinematic stills
Create film-style frames with specific lighting, lens feel, and color grading for mood boards or key art.
Poster and cover art
Render illustrated or photographic posters where a title needs to be set in a styled typeface inside the image.
Anime and illustration
Generate stylized character art with consistent palette and clean line work for storyboards and social content.
Prompt examples
A rain-soaked Tokyo alley at night, neon signs reflected in puddles, a courier on a scooter, 35mm film look, teal and magenta grade.
Poster for a jazz festival, saxophone silhouette, the title 'Blue Hour' in brush lettering, warm paper texture.
Anime-style girl reading on a train window seat, soft morning light, pastel palette, detailed background.
FAQ
What makes ImagineArt 2.0 a reasoning-based model?
ImagineArt says it evaluates the full prompt as a scene brief before rendering, resolving spatial relationships, lighting logic, and composition together. In practice that means long, detailed prompts tend to be followed more faithfully.
Can ImagineArt 2.0 edit images?
No. It is used for text-to-image generation from a written prompt. Describe the whole scene, including subject, lighting, and framing, because there is no reference input to carry details for you.
What styles does it handle?
Ultra realistic photography, cinematic and artistic looks, posters, illustrations, and anime. Style is steered through the prompt: describe lighting, mood, color grading, framing, and composition.
How good is its text rendering?
ImagineArt lists accurate, stylized typography as a feature. Put the exact words in quotes and keep them short, and proofread the output, since no generator renders text perfectly every time.
How much does ImagineArt 2.0 cost?
On TokenLab, ImagineArt 2.0 costs $0.05-$0.057 per image. The pricing table above shows the full breakdown. Rates depend on the billing unit, specification, and usage. Compare matching conditions in the model's detailed pricing; a single rate does not determine the total cost.
Which endpoint should ImagineArt 2.0 use?
Use https://api.tokenlab.sh/v1/images/generations for ImagineArt 2.0. The request example below shows the matching code shape.
Which operations does ImagineArt 2.0 support?
ImagineArt 2.0 supports Image editing, Text to image. Select an operation above to see its endpoint and request example.
Compare ImagineArt 2.0
Sources
Reviewed Oct 2, 2026