Skip to main content
AI video model
HappyHorse

HappyHorse 1.1

HappyHorse 1.1 routes by image count: no image selects text mode, 1 image selects first-frame image-to-video, and 2–9 images select reference mode. All three modes share the same resolutions, durations, and per-second rates.

Workflow
Text / single image / multiple images
Output
720p / 1080p
Duration
3–15 seconds
Credits
68–435
30-second overview
  • Selects among three workflows from 0 / 1 / 2–9 images
  • Applies strict prompt limits to Chinese and other text
  • Prices 720p / 1080p by output second
  • Validates true image format and dimensions before reserving credits

Popular searches: How do I use HappyHorse 1.1? · How much does HappyHorse 1.1 cost? · How many reference images does HappyHorse 1.1 support?

Examples

Visual transformation

Editorial design

Cinematic scene

SEEDANCE 2.0 视频提示词 时长:15秒 画幅:9:16竖屏 参考:严格使用参考图中的成年女主角,保持清晰面部五官、发型、妆容、身材比例和整套穿搭完全一致,全程为同一人物,不更换服装。 整体风格: 高级网红时尚短片,冷艳、妩媚、自信,深灰摄影棚,黑色镜面地面,暗紫色与金色轮廓光,柔和美颜主光,肤质真实细腻,轻微胶片颗粒,节奏感强但动作自然。 SHOT 1|0—5秒|怼脸眼神展示 主体:参考图女主。 动作:开场就是女主的面部超近景。她先微微侧脸看向画面外,随后缓慢转动眼睛直视镜头,轻轻眨眼,略微挑眉,嘴角露出若有若无的妩媚笑意;一只手自然拨动耳边碎发,身体轻微靠近镜头,目光自信、有吸引力。 环境:背景虚化成柔和的暗紫色光斑。 摄影机:85mm人像镜头,眼睛清晰锐利,浅景深,镜头缓慢推近并小幅环绕面部约15度,捕捉眼神、高光和真实皮肤细节。 约束:面部不能变形,不要夸张嘟嘴,不做低俗暗示动作。 SHOT 2|5—10秒|拉远展示完整造型 动作:女主抬手从镜头前自然划过,形成流畅遮挡转场。镜头迅速而平稳地从面部拉远到全身,她踩着高跟鞋向前走两步,交叉步停下,一只手扶腰,轻轻转换重心;随后转成侧身姿态,展示整体身材比例与服装轮廓,再顺势转身,回头看向镜头。 摄影机:由85mm近景无缝衔接至35mm全身镜头,轻微低机位但保持端正高级,镜头跟随后退;动作停顿瞬间出现一次时尚摄影闪光灯效果。 声音:清晰的高跟鞋脚步声、相机快门声、低沉时尚电子节拍。 约束:始终完整保留参考图服装、丝袜、高跟鞋及其花纹细节;镜头展示整体造型,不长时间聚焦单一身体部位。 SHOT 3|10—15秒|环绕炫姿收尾 动作:女主连续完成正面、侧面、背面三个自然模特姿势,动作之间使用短促流畅的速度变化。摄影机围绕她旋转约270度,她的裙摆、发丝和耳边碎发产生真实轻微摆动;环绕结束时她快速转回正面,向镜头走近,微微俯身贴近镜头,轻轻挑眉并眨一下眼,露出俏皮又妩媚的半笑,最后用指尖轻点镜头,画面瞬间切黑。 摄影机:50mm镜头稳定环绕,镜面地面产生柔和倒影;最后快速推近至面部特写,准确对焦双眼。 风格:高级、冷艳、妩媚、有网红爆款展示感,动作丰富但不杂乱,人物始终拥有镜头掌控力。 负面限制: 禁止人物身份变化、换脸、服装变化、蕾丝花纹漂移、丝袜接缝移动、身材忽胖忽瘦、比例夸张、肢体扭曲、额外手脚、多余手指、手指融合、五官融化、塑料皮肤、过度磨皮、走路滑步、高跟鞋穿模、衣物异常透明、走光、低俗姿势、私密部位特写、裙底机位、镜头角度漂移、人物瞬移、背景突然变形、过度慢动作、闪烁、字幕、文字、Logo、水印。

Cinematic scene

Create an ultra-realistic cinematic lifestyle video featuring the same young East Asian woman throughout the entire sequence. Maintain identical facial features, long soft ash-brown wavy hair, glowing skin, body proportions, and outfit in every shot. She wears a white ribbed crop top, beige high-waisted shorts, white sneakers, and carries a cream canvas tote bag throughout the video. Bright modern apartment, warm golden morning sunlight, neutral interiors, wooden furniture, indoor plants, premium lifestyle aesthetic. The video opens with her naturally tying her hair into a loose ponytail while smiling softly in front of a mirror. She grabs her canvas tote bag, reusable shopping bags, sunglasses, and keys before leaving the apartment. She walks through a peaceful tree-lined neighborhood as morning sunlight filters through the leaves. Handheld tracking shots follow her while a gentle breeze moves her hair naturally. She arrives at a vibrant local farmers market where she carefully selects fresh strawberries, blueberries, oranges, tomatoes, leafy vegetables, fresh flowers, and artisan bread. She smiles warmly at friendly vendors, smells flowers, gently inspects fresh produce, and places everything neatly into her tote bag. After paying, she strolls home through quiet streets carrying her groceries. Warm sunlight creates beautiful highlights while the camera captures candid lifestyle moments. Back home, she neatly arranges the groceries on the kitchen counter, washes fresh berries under running water, slices fruit, pours sparkling water filled with ice into a glass, and prepares a simple healthy snack. Soft close-up shots capture water droplets, fresh fruit textures, and natural morning light. She sits beside a large window surrounded by plants, enjoying her snack while looking outside. She notices the camera, smiles warmly, gently raises her sparkling water toward the viewer in a friendly toast, then relaxes as the camera slowly pulls back to reveal the peaceful apartment filled with warm sunlight. Natural ambient audio only: birds chirping, gentle breeze, footsteps, grocery bags rustling, fruit handling, market ambience, cashier beeps, doors opening, running water, knife slicing fruit, sparkling water pouring, ice clinking softly, leaves rustling. No background music, no subtitles, no logos, no watermarks, no on-screen text. Premium commercial-quality cinematography, smooth handheld and gimbal camera movement, realistic skin texture, natural expressions, physically accurate lighting, shallow depth of field, warm golden morning atmosphere, 16:9 widescreen, 4K HDR.

Cinematic scene

Cinematic scene

FORMAT: 15s / 145 BPM / 15 SHOTS / beat-synced routineSUBJECT: Young Indian woman, mid-20s. Long voluminous curly dark brown hair. Warm olive skin. Nose ring. Natural editorial makeup. Warm genuine smile. Gold hoop earrings. Minimal gold jewellery.[ATTACH REFERENCE: the Kellogg's shower gel image for exact face match]NARRATIVE ARC: A sharp young Indian woman using propert.shop to close her first crore-level deal — from pre-dawn app scroll to golden-hour triumph.WARDROBE: AT HOME — oversized white tee, navy lounge shorts, gold chain always visible, hair loose and curly.OUTSIDE — fitted navy blazer, white fitted top, cream tailored trousers, clean white sneakers, small gold hoops, minimal gold jewellery.ENVIRONMENT: Minimalist luxury apartment (white + navy tones, soft morning light), propert.shop office (open plan, city-view glass walls), luxury property site visit (Worli penthouse, marble lobby, glass elevator with Mumbai skyline), golden-hour rooftop.Everything feels premium, glossy, aspirational.MOOD: Pre-dawn obsession → sharp focused momentum → thrill of the deal → triumphant golden-hour exhale.MUSIC: Fast percussive electro-pop / propulsive beat-driven energyCOLOR LOGIC: Hyperreal Premium Look — Navy, Gold, Crisp White. Every frame feels like a propert.shop brand asset.STYLE: Ultra-Realistic. Premium founder documentary aesthetic.LOGIC RULE: Wardrobe consistency — home tee at home, blazer outside. propert.shop app visible on phone in every applicable scene. Gold jewellery always present. Curly hair consistent throughout.─────────────────────────────────────────────SHOT 1: ECU, 85mm push-in03:47 AM on the phone screen glowing against navy bedsheets. propert.shop app open — a ₹6.8 Cr Bandra West penthouse, price just dropped. Her hand visible, gold ring catching screen glow.SFX: notification ping, soft screen glow, quiet room.SHOT 2: WS, 35mm handheld joltRhythmic cut into her jolting upright through cool side light — phone already mid-scroll, sitting up in white oversized tee and navy lounge shorts, curly hair wild from sleep, eyes immediately sharp. One slow smile forms.SFX: mattress shift, sharp breath, quiet "finally."SHOT 3: MCU, 50mm slideCut on action — bathroom mirror, water cupped to face, droplets catching overhead light. Phone propped on counter, propert.shop listing glowing in mirror reflection behind her curly hair.SFX: faucet rush, water slap, distant notification tick.SHOT 4: Insert shot, 85mm rack focusMatch cut into her thumb flying across the screen — WhatsApp voice note recording: "Bandra West just dropped ₹40 lakh — send it to the Kapoors right now."propert.shop logo visible on phone screen.SFX: message whoosh, muffled voice, notification ping.SHOT 5: Interior view, 24mm wideObject pass — fridge snaps open, blue-white light flooding the frame. Her hand darts in for water, phone glowing in other hand. Listing now shows: "4 users viewing this property."SFX: fridge hum, bottle cap click, chime.SHOT 6: Insert shot, 50mm handheldRhythmic cut into laptop screen cracking open — propert.shop dashboard loading: "876 verified listings · 14 new AI matches · 2 deals pending."Coffee slides in beside the trackpad. Her gold-ringed hand wraps around the mug.SFX: laptop chime, ceramic clink, keyboard burst.SHOT 7: MCU, centered 50mm push-inMatch cut — one fast sip, sharp clock glance: 7:22 AM. She's already reaching for the navy blazer draped on the chair behind her.SFX: ceramic clink, chair scrape, blazer fabric snap.SHOT 8: Bird's-eye insert, 35mm overheadCut on action into clean white sneakers snapping onto marble floor. propert.shop access card and keys beside them. Her gold anklet visible above the shoe.SFX: sole thump, card jingle, lace pull.SHOT 9: MS, 35mm pivotCamera wipe — navy blazer goes on over white fitted top, curly hair tossed back once, phone, keys, propert.shop access card scooped in one sharp grab.SFX: fabric snap, card tap, key jingle, bag zip.SHOT 10: Insert shot, 50mm overheadMatch cut into her thumb confirming on the app: "Site Visit Confirmed — 10:00 AM — Raheja Imperia, Worli · ₹6.8 Cr"Uber notification arrives simultaneously beneath it.SFX: tap, confirmation chime, distant car horn.SHOT 11: WS, 24mm parallaxWhip pan into her striding through the building lobby into Mumbai morning light — blazer sharp, gold earrings catching the sun, curls moving with the stride, pace unhurried but electric.SFX: marble echo, glass door swing, city ambient rush.SHOT 12: MS to CU, 35mm glide into 85mm push-inSound bridge into the Worli tower glass elevator rising — Mumbai skyline smearing gold outside the glass. She stares out, one hand gripping the rail, other hand holding the phone with the 3:47 AM listing — now real and massive around her.SFX: elevator hum, city wind, her steady exhale.SHOT 13: Insert to MCU, 50mm snap zoomSmash cut — penthouse floor, site visit. She gestures at the floor-to-ceiling Mumbai skyline view, speaking to an off-screen client, curls caught in the breeze through the open slab. Mid-gesture — phone vibrates.She glances down: "OFFER ACCEPTED — ₹6.8 Cr · Raheja Imperia ✓"Expression: still. Then one slow, quiet exhale. Then the smile.SFX: phone buzz, confirmation tone, wind, her soft laugh.SHOT 14: OTS, 35mm handheldRhythmic cut — rooftop, golden hour. She's on a call, navy blazer caught in the warm breeze, Mumbai going amber-gold behind her curly silhouette. Laughing now — head thrown back slightly, the deal energy still live in every frame.SFX: wind, call audio murmur, city below, her laugh.SHOT 15: WS, 50mm pull-outL-cut — apartment re-entry. Blazer drops onto the chair. She's back in white oversized tee, gold chain, curly hair loose again. Falls back onto navy bedsheets — phone face-up on her chest, propert.shop app glowing.A new listing just pinged. ₹9.1 Cr. Juhu.Her thumb moves without hesitation.SFX: door shut, bag drop, blanket rustle, notification ping, room tone.─────────────────────────────────────────────END CARD (0.5s hold):propert.shop wordmark centered. White on navy.Tagline: "Find. Own. Belong."

At a glance

Is this model right for you?

Single-image mode requires both sides of the image to be at least 300 pixels, with an aspect ratio from 0.4–2.5. Reference mode requires a minimum short edge of 400 pixels. Signed upload metadata binds the true format and dimensions, and prompts or media outside the contract are rejected before credits are reserved.

What it does best
A short-video entry point whose three branches are selected by image count.
Who it is for
A good fit for animating one key frame or using multiple character, wardrobe, and setting images as references.
Why use it on Kyeo AI
Kyeo never silently truncates the prompt and validates image geometry, mode, and dynamic pricing before task creation.

Key facts

Quickly evaluate whether this model fits your business use case.

Single-image mode
Exactly 1 image
Reference mode
2–9 images
Image formats
JPEG / PNG / WebP
Prompt
Chinese and other text use different limits

Other names

The same model may have different names in official documentation, community discussions, and API integrations. This section brings them together for you.

HappyHorse V1.1
HappyHorse 1.1 image to video
HappyHorse 1.1 multi-image video

Common questions

These practical questions focus on the task, input conditions, and result requirements you should confirm before choosing.

How do I use HappyHorse 1.1?
How much does HappyHorse 1.1 cost?
How many reference images does HappyHorse 1.1 support?
Does HappyHorse 1.1 support Chinese prompts?
How do HappyHorse 1.1 720p and 1080p prices differ?

Decision guide

Still deciding? Start with these key decision points.

1
Use one image for first-frame guidance

With only one primary visual, the system selects single-image mode and does not send the reference-mode aspect-ratio field.

2
Use two or more images as element references

In reference mode, identify the roles of people, clothing, and settings by image order in the prompt.

3
Switch models for video or audio references

HappyHorse 1.1 does not currently accept reference video or audio. Compare MiniMax H3 or Seedance when those media types are required.

Popular comparisons

Compare common alternatives on the same task to clarify differences in inputs, controls, and cost.

How do the reference-media types of HappyHorse 1.1 and MiniMax H3 differ?
How do the image-to-video limits of HappyHorse 1.1 and Kling 3.0 Turbo compare?

Model comparison table

Not sure which model to choose? Compare the key differences between this model and its alternatives at a glance.

Input options
HappyHorse 1.1
Text, 1 first-frame image, or 2–9 reference images
Kling 3.0 Turbo
Text or 1 image
MiniMax H3
Text, first/last frames, or multimodal references

Real-world experience

Practical guidance based on public sources, current on-site limits, and representative tasks.

No silent truncation produces a controlled failure

Prompts over the language-specific limit are rejected before task creation, so users are not led to believe that the entire input was sent.

Reference-image count does not change the current rate

The three branches share a per-second rate, though additional media can still increase conflicts and iteration cost.

Capabilities

Text-to-video

Create a video from text using nine aspect ratios, a resolution, and a duration.

Single-image-to-video

Use one valid image as the first-frame visual input.

Multi-image reference

Use 2–9 images to define characters, objects, and settings.

Use cases

Character showcase clip

Generate motion and camera changes from one character image.

Wardrobe and setting combination

Use separate images for the person, clothing, and environment.

Multi-format ad draft

Compare landscape, portrait, and square composition in text or reference mode.

Prompt tips

Refer to images by order

Use labels such as “image 1” and “image 2” to give every reference a distinct role.

Keep Chinese prompts within 2,500 characters

Do not rely on public source truncation; manually shorten overlong content before submission.

Name what must stay fixed in single-image mode

List the appearance, product branding, and compositional elements that should not change.

Why choose it

Image count makes the three input modes intuitive.
Supports up to 9 reference images.
Offers nine common output aspect ratios.
Kyeo does not silently truncate prompts.

What to know first

No reference video or reference audio.
Single-image mode does not expose a separate aspect-ratio field.
Chinese prompts have a lower limit than other text.
More reference images do not guarantee better consistency.

Adjustable settings

Quickly evaluate whether this model fits your business use case.

Resolution
Optional
Parameter type: Select
Default: 1080p
720p
1080p
Video duration
Optional
Parameter type: Integer
Default: 5 seconds
3–15 seconds
Text / reference-mode aspect ratio
Optional
Parameter type: Select
Default: 16:9
16:9
9:16
1:1
4:3
3:4
4:5
5:4
9:21
21:9

Credit cost

68–435 credits

Text, single-image, and multi-image-reference modes share the same rates: 720p costs 22.5 credits per output second, while 1080p costs 29. Kyeo rounds the request total up and settles against actual consumption after completion.

Credit-saving tip

Before generating images or videos in bulk, run an A/B test with the same input on this model and similar alternatives. Confirm the result first to avoid wasting credits.

Frequently asked questions

Related models

Still deciding? Take a quick look at these similar alternatives.

Kling 3.0 Turbo

Kling 3.0 Turbo targets 3–15-second video generation. It uses text mode when no image is uploaded and switches to image-to-video when one valid image is supplied. Resolution and duration directly determine the preauthorization amount.

AI video model
54–338 credits

MiniMax H3

MiniMax H3 offers 768P and 2K output with text, first/last-frame, and image/video/audio reference scenes. Reference-video duration and every input image from image 6 onward affect pre-task authorization.

AI video model
32–406 credits

Seedance 2.0 Mini

Seedance 2.0 Mini combines text, first/last-frame, and multimodal-reference generation in one entry point. Reference video enters the pre-task pricing formula, so both media duration and output duration must be verified before task creation.

AI video model
15–150 credits

Sources

This page is based on vendor materials, model-family documentation, and Kyeo AI integration settings.

Source note

Explore HappyHorse 1.1: 720p or 1080p, 3–15 seconds, text, single-image, or 2–9-image reference generation, 68–435 credits, and image limits. Text, single-image, and multi-image-reference modes share the same rates: 720p costs 22.5 credits per output second, while 1080p costs 29. Kyeo rounds the request total up and settles against actual consumption after completion.

Last updated: 2026-08-28
HappyHorse V1.1 current interface notes
Integration

Used to check the input modes, visible controls, media limits, and availability of the version currently connected to this site. The page and workbench show the actual options.