Type
Spec
Rate
480p Video
per second
$0.057
720p Video
per second
$0.17
T2V Fast
additional fee
$0.065
T2V Quality
additional fee
$0.13
SVI 2.0 Pro and Hunyuan Video 1.5 side by side: specs, capabilities, parameters, and live pricing from the EmpirioLabs catalog.
VITA-Group / EPFL 
Tencent Video GenerationSVI 2.0 Pro from VITA-Group / EPFL and Hunyuan Video 1.5 from Tencent are both in the Video Generation category, available through the EmpirioLabs API.
| Spec | SVI 2.0 Pro | Hunyuan Video 1.5 |
|---|---|---|
| Model ID | svi-2-0-pro | hunyuan-video-1-5 |
| Author | VITA-Group / EPFL | Tencent |
| Released | Dec 26, 2025 | Nov 20, 2025 |
| Input | Text Image | Text Image |
| Output | Video | Video |
| Endpoints | POST /v1/videos/generations | POST /v1/videos/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 | SVI 2.0 Pro | Hunyuan Video 1.5 |
|---|---|---|
| resolution | 832x480, 480x832, 720x1280, 1280x720 Default: 832x480 | 480p, 720p, 1080p Default: 480p |
| duration | 18 to 121.5 Default: 18 | 1 to 10 Default: 5 |
| cfg | 1 to 2 Default: 1 | - |
| negative_prompt | string Default: vibrant tone, overexposed, static, blurry details, subtitles, style, artwork, painting, picture, still, overall gray, worst quality, low quality, JPEG compression residue, ugly, incomplete, extra fingers, poorly drawn hands, poorly drawn face, deformed, disfigured, malformed limbs, fused fingers, still picture, messy background, three legs, background crowd, walking backwards | string |
| t2v_quality | fast, quality Default: quality | - |
| prompt | - | string |
| mode | - | auto, t2v, i2v Default: auto |
| aspect_ratio | - | 16:9, 9:16, 1:1, 4:3, 3:4 Default: 16:9 |
| cfg_scale | - | 1 to 20 Default: 6 |
| steps | - | 10 to 50 Default: 25 |
| image | - | string |
| seed | - | min 0 |
Videos up to 121.5 seconds at 480p and 40.5 seconds at 720p, with a consistent character identity. Image-to-Video typically yields superior results to text-to-video.
8.3B-parameter Mixture-of-Experts model with strong motion coherence and bilingual prompt understanding.
SVI 2.0 Pro runs through POST /v1/videos/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. Both models are called through the same endpoint. Set model to svi-2-0-pro or hunyuan-video-1-5. Get an API key from the EmpirioLabs dashboard.
curl https://api.empiriolabs.ai/v1/videos/generations \
-H "Authorization: Bearer $EMPIRIOLABS_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "svi-2-0-pro",
"prompt": "Describe what you want SVI 2.0 Pro to generate."
}'SVI 2.0 Pro is the newer release (Dec 26, 2025); Hunyuan Video 1.5 was released on Nov 20, 2025. Capabilities listed only for SVI 2.0 Pro: infinite length, character consistency. Capabilities listed only for Hunyuan Video 1.5: 1080p upscale, bilingual. The specs, rate cards, and parameters on this page come from the live EmpirioLabs catalog.
SVI 2.0 Pro is the newer release (Dec 26, 2025); Hunyuan Video 1.5 was released on Nov 20, 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/videos/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.