• Picasso AI Logo
    Logo Picasso IA
  • Home
  • AI Image
    Nano Banana 2
  • AI Video
    Veo 3.1 Lite
  • AI Chat
    Gemini 3 Pro
  • Edit Images
  • Upscale Image
  • Remove Background
  • Text to Speech
  • Effects
  • AI Toolkit
    NEW
  • Generations
  • Billing
  • Support
  • Account
Unlimited Videos ARE HERE ยท Nano Banana 2 & GPT Image 2.0 UNLIMITED UNTIL June 30Upgrade
  1. Collection
  2. Text to Video
  3. Happyhorse 1.1

Happyhorse 1.1: Text or Image to Video Online

Happyhorse 1.1 is a video generation model that takes a text prompt, a single image, or a set of reference images and produces a short video up to 15 seconds long. Freelancers and content creators who need motion content without a camera or video editor will find it useful. You describe what you want, upload a photo if you have one, and the model renders the video at 720p or 1080p. The model supports three generation modes. In text-to-video mode, a written prompt is all you need, and the output covers five aspect ratios from widescreen 16:9 to vertical 9:16. In image-to-video mode, you supply one photo and the model animates it from that first frame. When you upload up to nine reference images, you can reference each one by position in your prompt and the model builds them into a coherent video. Happyhorse 1.1 fits naturally into social media production, product demos, and short-form ad creation. You pick duration in one-second increments from 3 to 15 seconds, set the resolution, choose an aspect ratio, and click generate. The whole process takes minutes rather than hours in a traditional editing suite.

Official

Alibaba

307 runs

Happyhorse 1.1

2026-06-22

Commercial Use

Table of contents

  • Overview
  • How It Works
  • Frequently Asked Questions
  • Credit Cost
  • Features
  • Use Cases
  • Examples
Get Nano Banana Pro

Overview

Happyhorse 1.1 is a video generation model that works three ways: write a text prompt and it builds a scene from scratch, upload a single photo and it animates that image into a clip, or add up to nine reference images and it weaves them into a cohesive video. The output is a short clip up to 15 seconds long, rendered at 720p or 1080p in the aspect ratio you choose. On Picasso IA, the whole process runs in a browser with no software to install. It suits anyone who needs moving visuals without a production budget or a video editing background.

How It Works

  • Choose your mode: type a text prompt for a fully generated scene, upload one photo to animate it, or upload multiple reference images to build a composite video
  • Write your prompt describing the action, setting, or mood. If you are using multiple reference images, mention them in the prompt as [Image 1], [Image 2], and so on
  • Set your resolution (720p or 1080p), pick a duration between 3 and 15 seconds, and select the aspect ratio that fits your output format
  • Click generate and wait while the model renders your video clip
  • Download the finished video file and drop it into your project

Frequently Asked Questions

Do I need programming skills or technical knowledge to use this? No, just open Happyhorse 1.1 on Picasso IA, adjust the settings you want, and hit generate.

Is it free to try? Picasso IA gives you access to Happyhorse 1.1 without requiring a paid subscription upfront. Check the current plan page for credit amounts and any limits that apply.

How long does it take to get results? A short clip at 720p typically renders in under a minute. Longer durations and 1080p resolution take more processing time, though most generations finish within a few minutes.

What aspect ratios are available? You can choose from 16:9, 9:16, 1:1, 4:3, and 3:4. When you animate a single image, the model automatically uses that image's own aspect ratio instead.

Can I reproduce the exact same result? Yes. Enter the same seed value with the same prompt and settings, and the model produces a consistent output. This is useful when you want to iterate on a clip without changing the core look.

What happens if the result does not match what I had in mind? Rewrite your prompt with more specific details about motion, timing, or visual style, then run again. Trying a different seed or shortening the duration can also shift the output in a different direction.

Credit Cost

The credit cost for this model varies based on the settings you choose. Below are the costs per configuration:

ConfigurationCredits
720p2.8per second
1080p3.6per second

Features

Everything this model can do for you

Three generation modes

Switch between text-to-video, single-image animation, and multi-image reference video in one tool.

1080p output

Export videos at full HD resolution suitable for professional presentations and ads.

Flexible durations

Set video length from 3 to 15 seconds in one-second steps to match your exact format.

Five aspect ratios

Choose 16:9, 9:16, 1:1, 4:3, or 3:4 to fit any platform without cropping.

Multi-image input

Reference up to nine source images in a single prompt for richer, more specific video output.

Reproducible results

Reuse a seed value to regenerate the exact same video when you want consistent output.

No watermarks

Download clean video files ready for client delivery or direct publishing.

Use Cases

Write a text prompt describing a landscape and generate a 15-second 1080p video without any footage

Upload a product photo and animate it into a short video clip for a social media post

Provide up to nine reference images and describe the scene using [Image 1], [Image 2] notation to produce a multi-reference video

Set the aspect ratio to 9:16 and generate vertical video content sized for short-form platforms

Create a 3-second looping clip from a single still image for use as a background or animated header

Generate a 4:3 video from a text description to match a presentation or broadcast format

Produce a 1080p product demo video from a written brief without filming or editing software

Examples

1080p
16:9
5s
2m 57s

The animal prances across the branch

Switch Category

Effects

Text To Image

Text To Video

Large Language Models

Text To Speech

Super Resolution

Lipsync

AI Music Generation

Video Editing

Speech To Text

AI Enhance Videos

Remove Backgrounds