Pruna AI

GENERATION API CALLS

Video Generation

This page is auto-generated from model configurations. Last updated: 2026-11-02.

This reference lists all available Pruna AI video generation models and their parameters. Use these parameter names when calling the Generation API.

P-Video
P-Video 2
P-Video 2 Pro
P-Video 2 Pro Avatar
P-Video 2 Pro Reference
P-Video Animate
P-Video Edit
P-Video Replace
Pruna P-Avatar

P-Video

P-Video is a video generation model that uses a text prompt to generate a video.

Model ID: model_p-video

Capabilities: txt2video, img2video

LLM Markdown: https://app.scenario.com/api/models/model_p-video/markdown

Parameter	Type	Required	Default	Min	Max	Allowed Values	Description
`prompt`	string	Yes	-	-	-	-	Text prompt for video generation.
`image`	file	No	-	-	-	-	Input image to generate video from.
`lastFrameImage`	file	No	-	-	-	-	Input image to generate video from.
`audio`	file	No	-	-	-	-	Input audio to condition video generation.
`duration`	number	No	`5`	1	20	-	Duration of the video in seconds (1-20). Ignored when audio is provided.
`aspectRatio`	string	No	`16:9`	-	-	`16:9`, `4:3`, `3:2`, `1:1`, `2:3`, `3:4`, `9:16`	Aspect ratio of the video. Ignored when an input image is provided.
`resolution`	string	No	`720p`	-	-	`720p`, `1080p`	Resolution of the video.
`fps`	number	No	`24`	-	-	`24`, `48`	Frames per second of the video.
`draft`	boolean	No	`false`	-	-	-	Draft mode. Generates a lower-quality preview of the video.
`promptUpsampling`	boolean	No	`true`	-	-	-	Use prompt upsampling to enhance the prompt.
`saveAudio`	boolean	No	`true`	-	-	-	Save the video with audio.
`seed`	number	No	-	-	-	-	Random seed. Set for reproducible generation.

P-Video 2

P-Video 2 generates videos from a text prompt, an image or an audio track, with native audio (dialogue, music, sound effects), improved lip sync and sharper on-screen text.

Model ID: model_pruna-p-video-2

Capabilities: txt2video, img2video

LLM Markdown: https://app.scenario.com/api/models/model_pruna-p-video-2/markdown

Parameter	Type	Required	Default	Min	Max	Allowed Values	Description
`prompt`	string	Yes	-	-	-	-	Text prompt for video generation.
`image`	file	No	-	-	-	-	First frame of the generated video. When provided, the aspect ratio is taken from the image.
`lastFrameImage`	file	No	-	-	-	-	Last frame of the generated video.
`audio`	file	No	-	-	-	-	Audio track conditioning the generation. When provided, the video lasts as long as the audio and the duration is ignored.
`duration`	number	No	`5`	1	20	-	Duration of the video in seconds. Ignored when an audio track is provided.
`aspectRatio`	string	No	`16:9`	-	-	`16:9`, `4:3`, `3:2`, `1:1`, `2:3`, `3:4`, `9:16`	Aspect ratio of the video. Ignored when an input image is provided.
`resolution`	string	No	`720p`	-	-	`720p`, `1080p`	Resolution of the video.
`fps`	number	No	`24`	-	-	`24`, `48`	Frames per second of the video.
`draft`	boolean	No	`false`	-	-	-	Draft mode. Generates a lower-quality preview of the video.
`promptUpsampling`	boolean	No	`true`	-	-	-	Use prompt upsampling to enhance the prompt.
`saveAudio`	boolean	No	`true`	-	-	-	Save the video with its generated audio.
`seed`	number	No	-	0	4294967295	-	Random seed. Set for reproducible generation.

P-Video 2 Pro

P-Video 2 Pro generates videos from a text prompt, with optional first- and last-frame conditioning, at 480p or 768p with generated audio.

Model ID: model_pruna-p-video-2-pro

Capabilities: txt2video, img2video

LLM Markdown: https://app.scenario.com/api/models/model_pruna-p-video-2-pro/markdown

Parameter	Type	Required	Default	Min	Max	Allowed Values	Description
`prompt`	string	Yes	-	-	-	-	Text prompt for video generation.
`image`	file	No	-	-	-	-	First frame of the generated video. When provided, the aspect ratio is taken from the image. Supports jpg, jpeg, png, webp.
`lastFrameImage`	file	No	-	-	-	-	Last frame of the generated video. When a reference image is provided, the aspect ratio is taken from the image. Supports jpg, jpeg, png, webp.
`duration`	number	No	`5`	5	15	-	Duration of the video in seconds.
`aspectRatio`	string	No	`16:9`	-	-	`16:9`, `4:3`, `3:2`, `1:1`, `2:3`, `3:4`, `9:16`	Aspect ratio of the video. Ignored when a reference image is provided.
`resolution`	string	No	`768p`	-	-	`480p`, `768p`	Resolution of the video.
`mode`	string	No	`speed`	-	-	`cost`, `speed`, `quality`	Generation recipe. Cost is the cheapest, speed is faster, quality gives the highest fidelity.
`promptUpsampler`	string	No	`turbo`	-	-	`off`, `turbo`, `max`	Expand the prompt before generation. Independent of mode.
`seed`	number	No	-	0	4294967295	-	Random seed. Set for reproducible generation.

P-Video 2 Pro Avatar

P-Video 2 Pro Avatar generates talking videos from a portrait with either a voice script or uploaded audio, at 480p or 768p.

Model ID: model_pruna-p-video-2-pro-avatar

Capabilities: img2video

LLM Markdown: https://app.scenario.com/api/models/model_pruna-p-video-2-pro-avatar/markdown

Parameter	Type	Required	Default	Min	Max	Allowed Values	Description
`image`	file	Yes	-	-	-	-	Portrait used as the first frame. Sets the aspect ratio. Supports jpg, jpeg, png, webp (max 20 MB).
`voiceScript`	string	No	-	-	-	-	Script for the avatar to speak when no audio is uploaded. The video lasts as long as the speech (up to 3 minutes).
`audio`	file	No	-	-	-	-	Uploaded speech audio (1s to 3 minutes, max 64 MB). Sets the video length. If both audio and voice script are provided, audio is used.
`prompt`	string	No	-	-	-	-	Optional description of what the video should show. Pruna defaults if omitted.
`voicePrompt`	string	No	-	-	-	-	Optional delivery instructions (tone, pacing, accent, emotion). Not spoken.
`voice`	string	No	`Zephyr (Female)`	-	-	`Zephyr (Female)`, `Puck (Male)`, `Charon (Male)`, `Kore (Female)`, `Fenrir (Male)`, `Leda (Female)`, `Orus (Male)`, `Aoede (Female)`, `Callirrhoe (Female)`, `Autonoe (Female)`, `Enceladus (Male)`, `Iapetus (Male)`, `Umbriel (Male)`, `Algenib (Male)`, `Despina (Female)`, `Erinome (Female)`, `Laomedeia (Female)`, `Achernar (Female)`, `Algieba (Male)`, `Schedar (Male)`, `Gacrux (Female)`, `Pulcherrima (Female)`, `Achird (Male)`, `Zubenelgenubi (Male)`, `Vindemiatrix (Female)`, `Sadachbia (Male)`, `Sadaltager (Male)`, `Sulafat (Female)`, `Alnilam (Male)`, `Rasalgethi (Male)`	Voice for generated speech.
`voiceLanguage`	string	No	`English (US)`	-	-	`English (US)`, `English (UK)`, `Spanish`, `French`, `German`, `Italian`, `Portuguese (Brazil)`, `Japanese`, `Korean`, `Hindi`	Output language for generated speech.
`resolution`	string	No	`768p`	-	-	`480p`, `768p`	Resolution of the generated video.
`seed`	number	No	-	0	4294967295	-	Random seed for reproducible generation.

P-Video 2 Pro Reference

P-Video 2 Pro Reference generates 5–15s videos from a text prompt guided by reference images, videos and audio, at 480p or 768p.

Model ID: model_pruna-p-video-2-pro-reference

Capabilities: img2video, video2video

LLM Markdown: https://app.scenario.com/api/models/model_pruna-p-video-2-pro-reference/markdown

Parameter	Type	Required	Default	Min	Max	Allowed Values	Description
`prompt`	string	Yes	-	-	-	-	Describe the video. Refer to references by order: Image 1, Video 1, Audio 1, and so on.
`referenceImages`	file_array	No	-	-	-	-	Images to guide subjects or style (up to 9 including first and last frames, max 20 MB each). Refer to them as Image 1, Image 2, and so on. At least one reference image, video, or frame is required.
`referenceVideos`	file_array	No	-	-	-	-	Videos to guide motion (up to 3, each 2–15s and 15s in total, max 1920×1080, 60 fps and 100 MB each). Refer to them as Video 1, Video 2, and so on. Billed per second, up to the output duration.
`referenceAudio`	file_array	No	-	-	-	-	Audio to guide the video (up to 3, 15s in total, max 50 MB each). Refer to them as Audio 1, Audio 2, and so on. Requires at least one reference image or video.
`keepAudio`	boolean	No	`false`	-	-	-	Use the reference audio as the video’s soundtrack and generate the video to match it. Requires exactly one reference audio. Shorter audio plays first and the model generates the rest; longer audio is cut to the duration.
`image`	file	No	-	-	-	-	Soft opening keyframe. Counts as a reference image.
`lastFrameImage`	file	No	-	-	-	-	Soft closing keyframe. Counts as a reference image.
`duration`	number	No	`5`	5	15	-	Duration of the video in seconds.
`aspectRatio`	string	No	`adaptive`	-	-	`adaptive`, `16:9`, `4:3`, `3:2`, `1:1`, `2:3`, `3:4`, `9:16`	Aspect ratio of the video. Auto follows the references.
`resolution`	string	No	`768p`	-	-	`480p`, `768p`	Resolution of the video. Reference video billing depends on this value.
`mode`	string	No	`speed`	-	-	`cost`, `speed`	Generation recipe. Cost is the cheapest, speed is faster.
`promptUpsampler`	string	No	`turbo`	-	-	`off`, `turbo`, `max`	Expand the prompt before generation. A first or last frame forces turbo even when off.
`seed`	number	No	-	0	4294967295	-	Random seed. Set for reproducible generation.

P-Video Animate

Animate a reference subject image using the motion from a source video.

Model ID: model_pruna-p-video-animate

Capabilities: video2video

LLM Markdown: https://app.scenario.com/api/models/model_pruna-p-video-animate/markdown

Parameter	Type	Required	Default	Min	Max	Allowed Values	Description
`video`	file	Yes	-	-	-	-	Source RGB video used for motion. Supports mp4.
`image`	file	Yes	-	-	-	-	Reference subject image to animate.
`instructionPrompt`	string	No	-	-	-	-	Instructions for animating the reference subject from the source motion.
`resolution`	string	No	`1080p`	-	-	`720p`, `1080p`	Target resolution of the output video.
`saveAudio`	boolean	No	`true`	-	-	-	Save the generated video with audio.
`targetFps`	string	No	`original`	-	-	`original`, `24`, `48`	Target FPS for the working video.
`seed`	number	No	-	0	4294967295	-	Random seed for reproducible generation.

P-Video Edit

Edit a source video from a text prompt, optionally guided by up to four reference images.

Model ID: model_pruna-p-video-edit

Capabilities: video2video

LLM Markdown: https://app.scenario.com/api/models/model_pruna-p-video-edit/markdown

Parameter	Type	Required	Default	Min	Max	Allowed Values	Description
`video`	file	Yes	-	-	-	-	Source video to edit. Supports mp4. Maximum length: 15 seconds.
`prompt`	string	Yes	-	-	-	-	Text prompt describing the edit.
`images`	file_array	No	-	-	-	-	Optional reference images for identity or style. Up to four. Supports jpg, jpeg, png, webp.
`promptUpsampling`	boolean	No	`true`	-	-	-	Use prompt upsampling to enhance the edit prompt.
`draft`	boolean	No	`false`	-	-	-	Draft mode. Faster, lower-quality preview billed at a lower rate.
`saveAudio`	boolean	No	`true`	-	-	-	Save the generated video with audio.
`seed`	number	No	-	0	2147483647	-	Random seed for reproducible generation.

P-Video Replace

Place one to four reference identities into a source video scene.

Model ID: model_pruna-p-video-replace

Capabilities: video2video

LLM Markdown: https://app.scenario.com/api/models/model_pruna-p-video-replace/markdown

Parameter	Type	Required	Default	Min	Max	Allowed Values	Description
`video`	file	Yes	-	-	-	-	Source RGB video scene. Supports mp4.
`images`	file_array	Yes	-	-	-	-	One to four identity reference images to place into the video.
`instructionPrompt`	string	No	-	-	-	-	Instructions for placing reference identities into the source scene.
`resolution`	string	No	`1080p`	-	-	`720p`, `1080p`	Target resolution of the output video.
`saveAudio`	boolean	No	`true`	-	-	-	Save the generated video with audio.
`targetFps`	string	No	`original`	-	-	`original`, `24`, `48`	Target FPS for the working video.
`seed`	number	No	-	0	4294967295	-	Random seed for reproducible generation.

Pruna P-Avatar

Generate talking-avatar videos from a portrait image with either a voice script or uploaded audio.

Model ID: model_pruna-p-avatar

Capabilities: img2video

LLM Markdown: https://app.scenario.com/api/models/model_pruna-p-avatar/markdown

Parameter	Type	Required	Default	Min	Max	Allowed Values	Description
`image`	file	Yes	-	-	-	-	Portrait image URI (URL, S3, or data URI). Supports jpg, jpeg, png, webp.
`voiceScript`	string	No	-	-	-	-	Script for the avatar to speak when no audio is uploaded.
`audio`	file	No	-	-	-	-	Uploaded audio used for speech. If both audio and voice script are provided, audio is used.
`videoPrompt`	string	No	-	-	-	-	Optional prompt for the video. Pruna defaults if omitted.
`voicePrompt`	string	No	-	-	-	-	Optional speaking style, tone, pacing, and emotion instructions.
`negativePrompt`	string	No	-	-	-	-	Optional description of what to avoid in the video. Pruna defaults if omitted.
`voice`	string	No	`Zephyr (Female)`	-	-	`Zephyr (Female)`, `Puck (Male)`, `Charon (Male)`, `Kore (Female)`, `Fenrir (Male)`, `Leda (Female)`, `Orus (Male)`, `Aoede (Female)`, `Callirrhoe (Female)`, `Autonoe (Female)`, `Enceladus (Male)`, `Iapetus (Male)`, `Umbriel (Male)`, `Algenib (Male)`, `Despina (Female)`, `Erinome (Female)`, `Laomedeia (Female)`, `Achernar (Female)`, `Algieba (Male)`, `Schedar (Male)`, `Gacrux (Female)`, `Pulcherrima (Female)`, `Achird (Male)`, `Zubenelgenubi (Male)`, `Vindemiatrix (Female)`, `Sadachbia (Male)`, `Sadaltager (Male)`, `Sulafat (Female)`, `Alnilam (Male)`, `Rasalgethi (Male)`	Voice for generated speech.
`voiceLanguage`	string	No	`English (US)`	-	-	`English (US)`, `English (UK)`, `Spanish`, `French`, `German`, `Italian`, `Portuguese (Brazil)`, `Japanese`, `Korean`, `Hindi`	Output language for generated speech.
`resolution`	string	No	`720p`	-	-	`720p`, `1080p`	Resolution of the generated video. Please note that 1080p portrait videos may experience color artifacts. For optimal quality in portrait mode, we recommend selecting 720p.
`disablePromptUpsampling`	boolean	No	`false`	-	-	-	Disable Prompt Upsampling
`strengthNegativePrompt`	number	No	`15`	0	100	-	Strength of the negative prompt on a 0-100 scale. Pruna defaults if omitted.
`seed`	number	No	-	0	4294967295	-	Random seed for reproducible generation.