APIXO bills both modes at $0.04 per generated image. One completed image costs $0.04, while three completed images cost $0.12. The selected mode, reference count, and aspect ratio do not have separately listed surcharges.
Wan 2.6 Image is APIXO’s still-image route for prompt-based generation and reference-guided transformation. Create new visuals from text or guide an edit with one to three public images, then request up to three outputs with negative-prompt and optional seed controls for iterative creative workflows.
Workflows
Text / Image to Image
APIXO Price
$0.04 / Image
References
1–3 Images
Output Count
1–3 Images
Editing Output
Fixed 2K
Loading workspace...
Generate a new image from a required Chinese or English prompt describing subjects, environments, composition, lighting, materials, and visual treatment.
Transform existing imagery through natural-language instructions and one to three public references, while allowing for variation in composition, details, and source fidelity.
Combine visual information from several references for subject, scene, color, or style exploration. Clearly describe each image’s intended role in the prompt.
Add a negative prompt of up to 500 characters to discourage unwanted content, visual defects, objects, or stylistic characteristics.
Request one, two, or three outputs per task to compare different interpretations without assuming that every requested image will complete successfully.
Supply an optional numeric seed to improve repeatability across experiments. Because generation remains probabilistic, identical seeds do not guarantee identical images.
Start with a required, non-empty prompt and no source images. APIXO exposes 1:1, 3:4, 4:3, 9:16, and 16:9 aspect ratios, one to three requested outputs, an optional negative prompt, and an optional seed.
Submit one to three public source images with a required instruction for editing or fusion. Output is fixed at 2K through APIXO, and aspect ratio should be omitted because that control applies only to text-to-image.
Verified still-image inputs and output settings for Wan 2.6 Image.
2 Modes
Workflows
2,000 Characters
Prompt Limit
500 Characters
Negative Prompt
1–3 URLs
References
1–3
Requested Outputs
0–2,147,483,647
Seed Range
Turn creative briefs into several campaign directions for mood boards, presentations, and early art development. Compare composition, lighting, and visual tone before moving selected concepts into a conventional production pipeline.
Use approved product references to explore alternate settings, materials, lighting, and promotional treatments. Review proportions, construction details, labels, logos, and brand colors against the original assets.
Bring subject, scene, or stylistic cues from multiple references into one exploratory result. Specify the role of each source and expect some variation in identity, layout, and reference relationships.
Create poster concepts, social visuals, illustrations, and editorial treatments from text or source imagery. Add exact typography, logos, and final layout elements with dedicated design tools after generation.
This route produces still images only and includes no video, animation, audio, motion, or duration controls.
APIXO does not publicly confirm the precise upstream model or checkpoint mapped behind each product-facing mode.
Both modes require a non-empty Chinese or English prompt of up to 2,000 characters. Keep requests within the documented limit.
Each reference must be a public JPEG, JPG, non-alpha PNG, BMP, or WebP URL, with width and height between 240 and 8,000 pixels. Keep the URLs directly accessible while the task runs.
APIXO does not expose streaming, Base64 input, custom dimensions, interleaved text-image output, transparent output, or 4K generation on this route.
Review anatomy, hands, identity, product geometry, logos, typography, unwanted objects, composition, and reference fidelity before using an output.
APIXO bills both modes at $0.04 per generated image. One completed image costs $0.04, while three completed images cost $0.12. The selected mode, reference count, and aspect ratio do not have separately listed surcharges.
No. One image is the default, and num_images accepts one, two, or three. A task can succeed with fewer images than requested; only completed image URLs appear in resultJson.resultUrls.
No. APIXO documents aspect ratio as a text-to-image-only control. Image-to-image uses a fixed 2K output configuration, so developers should omit the aspect-ratio field in that mode.
No. References can guide editing and fusion, but exact faces, product proportions, typography, logos, layout, and stylistic relationships are not guaranteed. Multiple generations and downstream correction may be necessary.
Wan 2.6 Image runs asynchronously through APIXO. Developers can poll for completion or use callback delivery, which requires a reachable callback endpoint. Successful image URLs are returned in resultJson.resultUrls.
Discover more AI models for your next creative workflow
Wan 2.7 Image is available on APIXO for Image. The model page brings examples, creation controls, pricing, and results into one focused workspace.
Wan 2.5 Image is available on APIXO for Image. The model page brings examples, creation controls, pricing, and results into one focused workspace.
Seedream 5.0 is available on APIXO for Image. The model page brings examples, creation controls, pricing, and results into one focused workspace.
Seedream 5.0 Pro is available on APIXO for Image. The model page brings examples, creation controls, pricing, and results into one focused workspace.
Flux 2 is available on APIXO for Image. The model page brings examples, creation controls, pricing, and results into one focused workspace.
Image
