Video Models
Spark Dance Series
| Model ID | Name | Input | Notes |
|---|
spark_dance_v2_0 | Seedance 2.0 | text / image / video / audio | Flagship, up to 15s, multimodal input |
spark_dance_v2_0_fast | Seedance 2.0 Fast | text / image / video / audio | Fast variant, ideal for draft iteration |
Kirin Series
| Model ID | Type | Input |
|---|
kirin_v2_6_t2v | T2V | text |
kirin_v2_6_i2v | I2V | text / image |
kirin_v3_t2v | T2V | text |
kirin_v3_i2v | I2V | image |
kirin_v3_omni_video | Omni | text / image / video |
kirin_video_o1 | O1 | text / image / video |
kirin_v3_motion_control | Motion Control | text / image / video |
kirin_duration_extension | Duration Extension | text / video |
kirin_identify_face | Face Recognition | video |
Vidu Series
| Model ID | Type | Input |
|---|
viduq3_pro_text2video | Q3 Pro T2V | text |
viduq3_pro_img2video | Q3 Pro I2V | text / image |
viduq3_turbo_text2video | Q3 Turbo T2V | text |
viduq3_turbo_img2video | Q3 Turbo I2V | text / image |
viduq2_pro_img2video | Q2 Pro I2V | text / image |
viduq2_pro_reference | Q2 Pro Reference | image / video |
viduq1_text2video | Q1 T2V | text |
viduq1_img2video | Q1 I2V | image |
Other Video Models
| Model ID | Provider | Input |
|---|
veo_3.1_generate_001 | Google | text / image |
pixverse_v6_t2v | Pixverse | text |
pixverse_v6_i2v | Pixverse | image |
pixverse_v6_transition | Pixverse | image |
Image Models
| Model ID | Name | Provider |
|---|
spark_dream_5_0 | Spark Dream 5.0 | Vtrix |
spark_dream_4_5 | Spark Dream 4.5 | Vtrix |
kirin_v3_image | Kirin V3 Image | Vtrix |
kirin_v3_omni_image | Kirin V3 Omni Image | Vtrix |
gpt_image_1_5 | GPT Image 1.5 | OpenAI |
gpt_image_1_5_edit | GPT Image 1.5 Edit | OpenAI |
nano_banana_2 | Nano Banana 2 | Google |
qwen_image_edit_plus | Qwen Image Edit Plus | Alibaba |
wan27_image_pro | Wan2.7 Image Pro | Wan |
Audio Models
| Model ID | Name | Description |
|---|
kirin_text_to_audio | Kirin Text2Audio | Text to sound effects, 3–10 seconds |
kirin_video_to_audio | Kirin Video2Audio | Video to audio, 3–20 seconds |
mureka_song_generator | Mureka Song Generator | AI song generation |
mureka_lyrics_generator | Mureka Lyrics Generator | AI lyrics generation |
Parameter Spec Example: Spark Dance 2.0
Using spark_dance_v2_0 as an example. Run vtrix models spec spark_dance_v2_0 to view the full spec.
| Parameter | Type | Required | Default | Description |
|---|
content | array | required | — | Multimodal input array (text / image_url / video_url / audio_url) |
resolution | string | optional | 720p | 480p / 720p / 1080p |
ratio | string | optional | adaptive | 16:9 / 9:16 / 1:1 / 4:3 / 3:4 / 21:9 / adaptive |
duration | integer | optional | 5 | Duration in seconds, range 4–15, -1 for auto |
seed | integer | optional | -1 | Random seed |
generate_audio | boolean | optional | true | Whether to generate synchronized audio |
return_last_frame | boolean | optional | false | Whether to return the last frame as an image |
service_tier | string | optional | default | flex = async inference, 50% off |
camera_fixed | boolean | optional | false | Fix the camera angle |
callback_url | string | optional | — | Callback URL on task completion |
safety_identifier | string | optional | — | End-user identifier (≤ 64 characters) |