Skip to main content

P-Video: Text & Image to Video Online

Text & Image to VideoFrom 7 credits★ 4.6 / 5Flexible content filterUpdated October 2026
Generate with P-Video

Bottom line

Pruna AI's P-Video makes 4-10 second clips from text or a photo at 720p or 1080p in seven aspect ratios; 5 seconds at 720p is 8 credits. Start from a prompt or a still image in the Text to Video tool; VdoBloom shows the exact credit cost before each P-Video run, with no separate P-Video account.

P-Video sample clips

Every clip below is a real render made on VdoBloom. Each caption names the model that produced it and gives its length and size.

P-Video — model preview

A 5-second square clip generated on VdoBloom with P-Video: the preview shown when choosing this model in the VdoBloom picker.

5 s · 720×720

Preview clip, generated on VdoBloom with P-Video

Make one like this →

P-Video is Pruna AI's text- and image-to-video model, described in VdoBloom's picker as real-time text and image to video and served through Runware. Pruna's specialty is making models run leaner, and P-Video is built for volume: it turns a prompt or a photo into a 4 to 10 second clip at 720p or 1080p, in seven aspect ratios (16:9, 9:16, 1:1, 4:3, 3:4, 3:2, 2:3), at a per-second price low enough that repeated attempts stay cheap.

On VdoBloom a 5-second 720p clip is 8 credits and 10 seconds is 16; at 1080p those are 16 and 32 credits. The shortest render, 4 seconds at 720p, is 7 credits, so a new account's 10 free credits cover one clip with credits to spare. Paid credits need no subscription: a one-time 300-credit pack is $19.50 and never expires, or the Lite plan is $15 a month for 300 credits. The cost is shown before every generation and a failed job is refunded automatically.

The clip above was generated on VdoBloom with P-Video. Below: the spec table, every price P-Video can bill, how it compares with its successor P-Video 2 and with Seedance 2 Fast, where it runs, prompting notes and its limits. If you need sound, a last frame or clips past 10 seconds, P-Video 2 is the newer model in the same family.

P-Video specs at a glance

These are the options VdoBloom's picker offers for prunaai:p-video@0 and the limits its endpoint enforces. The picker offers 4 to 10 seconds; the price list below covers exactly those settings.

SpecP-Video on VdoBloom
Developer / routePruna AI, served through Runware (model prunaai:p-video@0)
InputsText prompt (text to video) or a photo as the first frame (image to video)
Clip length4, 5, 6, 7, 8, 9 or 10 seconds
Resolution720p or 1080p
Aspect ratios16:9, 9:16, 1:1, 4:3, 3:4, 3:2, 2:3 (text to video); image to video uses the photo with a resolution preset
Output sizes (text to video)720p: 1280x720 (16:9), 720x1280 (9:16), 720x720 (1:1). 1080p: 1920x1080, 1080x1920, 1080x1080
Prompt lengthUp to 2,000 characters
Price per secondAbout 1.6 credits at 720p and 3.2 at 1080p (8 and 16 credits for 5 seconds)
Cheapest render7 credits: 4 seconds at 720p
Where it runsText to Video and Image to Video tabs, P-Video family in the model picker

What P-Video costs: every setting

P-Video has a fixed credit price for each length and resolution, so this table is the complete list for the settings the picker offers. Dollar figures use the Lite plan rate ($15 for 300 credits, $0.05 a credit). One-time pack credits never expire; subscription credits reset each billing cycle.

Length720p1080p
4 s7 cr ($0.35)13 cr ($0.65)
5 s8 cr ($0.40)16 cr ($0.80)
6 s10 cr ($0.50)20 cr ($1.00)
7 s12 cr ($0.60)23 cr ($1.15)
8 s13 cr ($0.65)26 cr ($1.30)
9 s15 cr ($0.75)29 cr ($1.45)
10 s16 cr ($0.80)32 cr ($1.60)

Read more: Per-second rates across VdoBloom's video models · Credit packs and plans

P-Video vs P-Video 2 vs Seedance 2 Fast

P-Video is the lowest-priced of these three at every setting they share. Its successor P-Video 2 adds native audio, a last-frame slot, a Draft tier and lengths up to 20 seconds for a few credits more per clip. Seedance 2 Fast, ByteDance's quick Seedance 2 tier, adds 480p, the 21:9 frame, sound and lengths to 15 seconds, at a higher per-second price and a 720p ceiling.

P-VideoP-Video 2Seedance 2 Fast
Clip length4-10 s1-20 s4-15 s
Resolutions720p, 1080p720p, 1080p (+ Draft)480p, 720p
Aspect ratios7, incl. 3:2 and 2:37 (text to video)6, incl. 21:9
AudioNo audio setting in the pickerAlways on, includedGenerated by default, included
Last frameNoOptionalSeedance family frame/reference inputs
5 s at 720p8 cr11 cr50 cr
10 s at 720p16 cr21 cr100 cr
10 s at 1080p32 cr41 crNot offered (720p max)

Read more: P-Video 2 model page · Seedance 2 Fast model page · What changed from P-Video to P-Video 2

Where to run P-Video on VdoBloom

P-Video sits in the P-Video family of the model picker, next to P-Video 2. Same price and options on both tabs.

  • Text to Video: write the prompt (up to 2,000 characters), pick P-Video, choose 4-10 seconds, 720p or 1080p and one of seven aspect ratios.
  • Image to Video: upload a photo as the first frame and describe the motion; the photo is sent with a resolution preset, so crop it to the shape you want first.
  • There is no last-frame slot and no Draft switch for P-Video in the picker; both are P-Video 2 features.

Read more: Best AI model for image to video

P-Video output sizes for every aspect ratio

On text to video, VdoBloom sends P-Video an exact width and height for the aspect ratio and resolution you pick. These are the frame sizes you get, which matters when the clip has to drop into an edit or a platform slot without re-scaling. Image to video does not use this table: the photo is sent with a 720p or 1080p preset, so crop it to the target shape before uploading.

Aspect ratioTypical use720p frame1080p frame
16:9YouTube, landing pages, presentations1280x7201920x1080
9:16Reels, Shorts, TikTok, Stories720x12801080x1920
1:1Feed posts, product tiles720x7201080x1080
4:3Classic frame, slides960x7201440x1080
3:4Portrait feed posts720x9601080x1440
3:2Photo-style landscape1080x7201620x1080
2:3Pinterest-style portrait720x10801080x1620

Prompting P-Video

Write one subject, one action and one camera move per clip; at 4-10 seconds there is room for a single beat, not a sequence. Lead with the subject and the action ('a red kite climbs over a grey beach, slow upward tilt'), then add light and style. On image to video, do not re-describe the photo; spend the words on what moves and how the camera behaves. Because a 4-second 720p try is 7 credits, the efficient loop is several short 720p variations, then one 1080p render of the winner at the length you need.

Limits and honest caveats

The ceiling is 10 seconds and 1080p, with no 4K and no 21:9 frame. The picker exposes no audio control and no last frame; if the clip needs speech, sound effects or an end image, use P-Video 2. Lengths below 4 seconds are not offered in the picker. VdoBloom does not publish render times, so treat 'real-time' as the vendor's positioning, not a guarantee. Prompts are screened before generation, and a failed job is refunded automatically.

VdoBloom does not score models on subjective look; the 7-credit minimum is the quickest way to see whether P-Video suits a shot.

What creators use P-Video for

  • Rapid previsualization: blocking out shot ideas from text before committing credits to a premium model.
  • Animating a still photo and a text-only version of the same concept side by side on one model.
  • Cheap draft variants across all seven aspect ratios before choosing the framing to finish.
  • Short 4-10 second inserts and social clips where a longer, pricier render is not needed.

How to use P-Video on VdoBloom

  1. 1Open the Text to Video tool and select P-Video from the model picker.
  2. 2Write your prompt, or upload a starting image for image-to-video.
  3. 3Choose your duration (4–10s), quality (720p/1080p), aspect ratio, review the credit cost, and generate.

Frequently asked questions

What is Pruna AI P-Video?

P-Video is a text- and image-to-video model from Pruna AI, a company focused on making AI models run faster and leaner. On VdoBloom it makes 4-10 second clips at 720p or 1080p in seven aspect ratios, served through Runware, with no Pruna account needed.

How much does P-Video cost on VdoBloom?

8 credits for 5 seconds at 720p and 16 for 10 seconds; at 1080p, 16 and 32 credits. The full range is 7 credits (4 s, 720p) to 32 credits (10 s, 1080p), and the exact price is shown before you generate.

Do my 10 free signup credits cover a P-Video render?

Yes. A 4-second 720p clip is 7 credits and a 5-second one is 8, both within a new account's 10 free credits. Further credits come as a one-time 300-credit pack ($19.50, never expires) or the $15-a-month Lite plan.

Does P-Video do both text-to-video and image-to-video?

Yes. Pick it on the Text to Video tab to generate from a prompt, or on the Image to Video tab to animate a photo used as the first frame. Length, resolution and price are the same in both modes.

What lengths and sizes does P-Video support?

4 to 10 seconds in whole-second steps, at 720p or 1080p, in 16:9, 9:16, 1:1, 4:3, 3:4, 3:2 or 2:3. At 720p, 16:9 is 1280x720 and 9:16 is 720x1280.

How fast is P-Video?

Pruna positions it as real-time text and image to video. VdoBloom does not publish render times, so take that as the vendor's positioning; the job runs in the background and the clip saves to My Creations.

Does P-Video generate sound?

VdoBloom's picker has no audio setting for P-Video. If you need dialogue, music or sound effects generated with the picture, P-Video 2 in the same family has audio always on, from 11 credits for 5 seconds at 720p.

P-Video or P-Video 2?

P-Video is a few credits cheaper (8 against 11 for 5 seconds at 720p) and fine for quick, simple shots up to 10 seconds. P-Video 2 adds native audio, a last frame, a Draft tier and lengths up to 20 seconds.

P-Video or Seedance 2 Fast?

P-Video costs less at every setting both offer (16 against 100 credits for 10 seconds at 720p) and reaches 1080p. Seedance 2 Fast adds 480p, the 21:9 frame, sound and lengths to 15 seconds.

P-Video guides, prices and comparisons

This page is the P-Video hub. Each guide below goes deeper on one question and links back here.

Related models