

Wan2.5 Image and Wan2.2 Image side by side: specs, capabilities, parameters, and live pricing from the EmpirioLabs catalog.
Wan2.5 Image and Wan2.2 Image are both Alibaba Cloud models in the Image Generation category, available through the EmpirioLabs API.
| Spec | Wan2.5 Image | Wan2.2 Image |
|---|---|---|
| Model ID | wan2-5-image | wan2-2-image |
| Author | Alibaba Cloud | Alibaba Cloud |
| Released | Sep 24, 2025 | Jul 28, 2025 |
| Input | Text Image | Text |
| Output | Image | Image |
| Region | Singapore | Singapore |
| Endpoints | POST /v1/images/generations | POST /v1/images/generations |
| Capabilities |
Live rates from the EmpirioLabs catalog for both models. Each rate card always matches what the API charges.
Request parameters each model lists on EmpirioLabs, with the allowed values or range where one applies. A dash marks a parameter the model does not list.
| Parameter | Wan2.5 Image | Wan2.2 Image |
|---|---|---|
| prompt | string | string |
| aspect_ratio | 1:1, 16:9, 9:16, 4:3, 3:4, 3:2, 2:3 Default: 1:1 | 1:1, 16:9, 9:16, 4:3, 3:4, 3:2, 2:3 Default: 1:1 |
| image | array | - |
| num_images | 1 to 4 Default: 1 | 1 to 4 Default: 1 |
| negative_prompt | string | string |
| prompt_extend | boolean Default: true | boolean Default: true |
| watermark | boolean Default: false | boolean Default: false |
| seed | 0 to 2147483647 | 0 to 2147483647 |
| response_format | url, b64_json Default: url | url, b64_json Default: url |
| model_tier | - | plus, flash Default: plus |
Text-to-image renders about 1.7 megapixels at the chosen aspect ratio; attach 1 to 3 images for editing and fusion at about 1 megapixel. Prompts up to 2000 characters.
Text-to-image only. Plus is the higher-fidelity tier; flash is faster and cheaper. Each aspect ratio has one output size, up to 1280 pixels on the long side (1024x1024 at 1:1), with prompts up to 500 characters.
Wan2.5 Image runs through POST /v1/images/generations. The request returns a job_id right away; poll GET /v1/jobs/{job_id} until the job completes and read the output URLs from the result. Or add "sync": true to skip polling: the request stays open and returns the finished OpenAI-style image response directly, so OpenAI SDKs work as-is. Both models are called through the same endpoint. Set model to wan2-5-image or wan2-2-image. Get an API key from the EmpirioLabs dashboard.
curl https://api.empiriolabs.ai/v1/images/generations \
-H "Authorization: Bearer $EMPIRIOLABS_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "wan2-5-image",
"prompt": "Describe what you want Wan2.5 Image to generate."
}'Wan2.5 Image is the newer release (Sep 24, 2025); Wan2.2 Image was released on Jul 28, 2025. Input types only Wan2.5 Image accepts: Image. Capabilities listed only for Wan2.5 Image: image editing. The specs, rate cards, and parameters on this page come from the live EmpirioLabs catalog.
Wan2.5 Image is the newer release (Sep 24, 2025); Wan2.2 Image was released on Jul 28, 2025.
The two models are priced on different units or tiers, so compare the live rate cards on this page. They always match what the API charges.
Yes. Both models use POST /v1/images/generations with the same EmpirioLabs API key, so most integrations switch by changing the model value. Check the parameters table on this page first if you rely on a model-specific parameter.
Yes. Open each model in the EmpirioLabs playground and run the same prompt on both, with the parameters the API exposes.
Check out our pricing or reach out if you want your own model deployed on our stack.