Skip to main content
Kyeo AI
AI video model
HappyHorse

HappyHorse 1.0

HappyHorse 1.0 / Workflows — The currently available workflows are prompt-only video, one-image video, and reference video with 2 to 9 images. Editing an existing video is currently unavailable on this page.

Use this modelView credit pricingBack to Model Hub
Workflows
Text, single image, and 2–9 image reference
Credit cost
84–720 credits / request
Prompt limit
2,500 with Chinese; 5,000 otherwise; over-limit requests are rejected before charging
Upload limit
1 / 2–9 · JPG/PNG/WebP · 10 MB
30-second overview
  • HappyHorse 1.0 / Workflows — The currently available workflows are prompt-only video, one-image video, and reference video with 2 to 9 images.
  • HappyHorse 1.0 / Upload limit — Use exactly 1 image for image-to-video or 2 to 9 images for reference video. Images must be JPEG, PNG, or WebP and no larger than 10 MB; single-image mode requires both dimensions to be at least 300 px, while reference mode requires the shortest side to be at least 400 px.
  • HappyHorse 1.0 / Credit cost — 720p costs 28 credits per output second and 1080p costs 48 credits per output second. A 3 to 15 second request therefore costs 84 to 720 credits.
  • HappyHorse 1.0 / Upload limit / Asynchronous task — Editing an existing video is currently unavailable on this page.

Popular searches: How do I use HappyHorse 1.0? · How many credits does HappyHorse 1.0 cost? · How does HappyHorse 1.0 text-to-video work?

Examples

Cinematic scene

CAMERA: Handheld DV camcorder POV, shot by CHASE herself (selfie-style/propped on vanity mirror), never visible on screen. Natural shake, imperfect framing, delayed focus, clumsy zooms, occasional face-cropping. LOOK: DV tape aesthetic — soft/blurry, faint noise, blooming highlights, flickering auto-exposure, muted contrast, realistic skin tones. STYLE: Casual GRWM vlog narration, warm chatty pacing, camera alternates handheld/propped. CHARACTER: CHASE — Korean idol, 20s, long black hair, dewy skin, coral lips. Starts in oversized cardigan/robe over high-neck top → ends in turtleneck sweater + trousers (fully covered throughout). Adds stud earrings partway through. SETTING: Warm, bulb-lit vanity corner with skincare/makeup laid out, soft natural window light. STORYBOARD: (2s, propped, medium) Waves, settles in: "Hey guys, get ready with me for today!" (2s, handheld, close) Holds up skincare bottle: "Starting with this — my favorite lately." (2s, propped, medium) Pats product on face, smiles at camera: "Just letting that sink in for a sec." (1.5s, macro insert) Hands blending makeup, brush on cheek — no dialogue, ambient sound only. (2s, handheld, medium) Applies lip product, checks mirror: "This color's new — let's see." (2s, propped, wide) Pulls on turtleneck, adjusts sleeves: "Outfit's going on now." (1.5s, handheld, tight) Clips on earrings, tilts head: "Last detail — done!" (2s, arm's-length selfie) Spins to show outfit, leans in, waves: "That's my GRWM — see you soon!"

Editorial design

Visual transformation

Visual transformation

Cinematic scene

Cinematic anime short film clip, 15 seconds. Miami-style nightclub, neon pink and blue lights, palm silhouettes through windows, bass-heavy dance floor, bottle service tables. Vibrant saturated colors. Fully original characters, not based on any existing movie or franchise. CHARACTER 1 — RYDER: Athletic young male, sharp confident smirk, fitted black suit no tie, sunglasses pushed up. Smooth precise hand-to-hand strikes, always the clean effortless takedown. CHARACTER 2 — DESHAWN: Stockier young male, wide panicked eyes, Hawaiian shirt untucked. Shouts constantly, flailing defensive swings, terrified but somehow always survives, occasionally lucky. CRIMINALS: All-black tactical vests over club shirts, gold jewelry. Clearly distinct from Ryder's suit and DeShawn's Hawaiian shirt. AUDIO: High energy Miami bass hip hop beat loud from frame one, every beat synced to the action, club music underneath, crashes and shattering glass throughout, never dropping. 0:00–0:01 — Already mid-action, strobing nightclub, both moving forward through the crowd, tactical-vested criminals closing in. 0:01–0:03 — Ryder slides across the bar landing two clean strikes, both drop. DeShawn screams "WHY IS THIS HAPPENING TO ME" swinging a bar stool wildly, hits a champagne bottle above a criminal's head, glass showers him, DeShawn swings again by accident, connects. 0:03–0:06 — Both advancing through the dance floor. Ryder flips over a couch smoothly, clean strike on the other side. DeShawn tries the same, faceplants into the couch, accidentally headbutts a criminal hiding behind it. 0:06–0:09 — Both running forward, criminals chasing through the strobe lights. DeShawn swings backward eyes closed screaming, connects with a disco ball cable that swings and clips a chaser. DeShawn opens his eyes, sees the result, screams louder in disbelief. 0:09–0:12 — Last three criminals block the club exit. Ryder drops two with clean strikes. DeShawn grabs a bottle from the bar, hurls it, knocks the last one out cold. 0:12–0:15 — Both walking out into the night. Ryder calm, sunglasses back down, smooth exit. DeShawn still shaking, Hawaiian shirt torn, breathing hard. Both nod. Hero moment. Done. Cinematic cel-shaded 3D anime, semi-realistic CGI, hand-painted textures, Unreal Engine quality, colorful nightclub strobe lights throughout, bold flat color blocking, chunky simplified forms, hard edge shadows, thick black outlines, vibrant saturated colors, not cartoon not Disney not Pixar, film grain, Miami bass beat dominant throughout, camera angles switching rapidly every action, Ryder always smooth and precise, DeShawn always panicked but effective, criminals always in black tactical vests.

Fashion portrait

At a glance

Is this model right for you?

Choose 720p or 1080p and a 3 to 15 second duration. Aspect ratio is available for text-to-video and multi-image reference video; the prompt is optional only in single-image mode. Use exactly 1 image for image-to-video or 2 to 9 images for reference video. Images must be JPEG, PNG, or WebP and no larger than 10 MB; single-image mode requires both dimensions to be at least 300 px, while reference mode requires the shortest side to be at least 400 px.

What it does best
HappyHorse 1.0 / Workflows — HappyHorse 1.0 on Kyeo supports text-to-video, single-image animation, and multi-image reference video from one model page.
Who it is for
HappyHorse 1.0 — The currently available workflows are prompt-only video, one-image video, and reference video with 2 to 9 images.
Why use it on Kyeo AI
HappyHorse 1.0 / Resolution / Video duration — Choose 720p or 1080p and a 3 to 15 second duration. Aspect ratio is available for text-to-video and multi-image reference video; the prompt is optional only in single-image mode.

Key facts

Quickly evaluate whether this model fits your business use case.

Category
AI video model
Vendor
HappyHorse
Model family
HappyHorse
Workflows
Text, single image, and 2–9 image reference
Runtime
Asynchronous task
Prompt limit
Chinese present: 2,500; otherwise: 5,000; rejected before charge
Upload limit
1 image or 2–9 images; video upload unavailable

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 1 0

Common questions

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

How do I use HappyHorse 1.0?
How many credits does HappyHorse 1.0 cost?
How does HappyHorse 1.0 text-to-video work?
How can I animate one image with HappyHorse 1.0?
How do multi-image references work in HappyHorse 1.0?

Decision guide

Still deciding? Start with these key decision points.

1
Choose it when the asset strategy is still open

Choose it when the asset strategy is still open — HappyHorse 1.0 on Kyeo supports text-to-video, single-image animation, and multi-image reference video from one model page.

2
Compare specialist models for deeper control

Compare specialist models for deeper control — Choose 720p or 1080p and a 3 to 15 second duration. Aspect ratio is available for text-to-video and multi-image reference video; the prompt is optional only in single-image mode.

3
Workflows

Workflows — The currently available workflows are prompt-only video, one-image video, and reference video with 2 to 9 images. 720p costs 28 credits per output second and 1080p costs 48 credits per output second. A 3 to 15 second request therefore costs 84 to 720 credits.

Popular comparisons

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

How does HappyHorse 1.0 differ from Wan 2.7 Video?
HappyHorse 1.0 vs Wan 2.7 Video for reference-driven clips
How does HappyHorse 1.0 compare with Kling 3.0?
HappyHorse 1.0 vs Kling 3.0 for camera control
What separates HappyHorse 1.0 from Seedance 2.0?
HappyHorse 1.0 vs Seedance 2.0 for multi-asset workflows

Model comparison table

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

Workflows
HappyHorse 1.0
Workflows — Text, single image, and 2–9 image reference
Wan 2.7 Video
Text / first or first-last frame / continuation / video edit
Kling 3.0
Text / 1-2 images
Output duration
HappyHorse 1.0
Output duration — 3-15 seconds, integer
Wan 2.7 Video
5 / 10 / 15 seconds; video edit up to 10
Kling 3.0
3-15 seconds
Output tiers
HappyHorse 1.0
Output tiers — 720p / 1080p
Wan 2.7 Video
720p / 1080p
Kling 3.0
std 720p / pro 1080p
Kyeo billing
HappyHorse 1.0
Kyeo billing — 28 / 48 credits per second at 720p / 1080p
Wan 2.7 Video
Resolution and duration based
Kling 3.0
Mode, audio, and per-second based
Distinct controls
HappyHorse 1.0
Distinct controls — Choose 720p or 1080p and a 3 to 15 second duration. Aspect ratio is available for text-to-video and multi-image reference video; the prompt is optional only in single-image mode.
Wan 2.7 Video
Negative prompt, prompt expansion, watermark, and edit audio
Kling 3.0
Single/multi-shot control and generated-audio toggle

Real-world experience

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

Workflows

Workflows / HappyHorse 1.0 — The currently available workflows are prompt-only video, one-image video, and reference video with 2 to 9 images.

Upload limit

Upload limit / HappyHorse 1.0 — Use exactly 1 image for image-to-video or 2 to 9 images for reference video. Images must be JPEG, PNG, or WebP and no larger than 10 MB; single-image mode requires both dimensions to be at least 300 px, while reference mode requires the shortest side to be at least 400 px.

Capabilities

Workflows

Workflows — The currently available workflows are prompt-only video, one-image video, and reference video with 2 to 9 images.

Resolution / Video duration

Resolution / Video duration — Choose 720p or 1080p and a 3 to 15 second duration. Aspect ratio is available for text-to-video and multi-image reference video; the prompt is optional only in single-image mode.

Credit cost

Credit cost — 720p costs 28 credits per output second and 1080p costs 48 credits per output second. A 3 to 15 second request therefore costs 84 to 720 credits.

Use cases

Text-first short-film drafts

Text-first short-film drafts — HappyHorse 1.0 on Kyeo supports text-to-video, single-image animation, and multi-image reference video from one model page.

Still-image animation

Still-image animation — Use exactly 1 image for image-to-video or 2 to 9 images for reference video. Images must be JPEG, PNG, or WebP and no larger than 10 MB; single-image mode requires both dimensions to be at least 300 px, while reference mode requires the shortest side to be at least 400 px.

Reference-led generation and clip variants

Reference-led generation and clip variants — The currently available workflows are prompt-only video, one-image video, and reference video with 2 to 9 images.

Prompt tips

Assign each asset a clear role

Assign each asset a clear role / HappyHorse 1.0 — Choose 720p or 1080p and a 3 to 15 second duration. Aspect ratio is available for text-to-video and multi-image reference video; the prompt is optional only in single-image mode.

Reference images by order

Reference images by order / HappyHorse 1.0 — Use exactly 1 image for image-to-video or 2 to 9 images for reference video. Images must be JPEG, PNG, or WebP and no larger than 10 MB; single-image mode requires both dimensions to be at least 300 px, while reference mode requires the shortest side to be at least 400 px.

Resolution / Video duration

Resolution / Video duration / HappyHorse 1.0 — Choose 720p or 1080p and a 3 to 15 second duration. Aspect ratio is available for text-to-video and multi-image reference video; the prompt is optional only in single-image mode.

Why choose it

Workflows — HappyHorse 1.0 on Kyeo supports text-to-video, single-image animation, and multi-image reference video from one model page.
HappyHorse 1.0 · Resolution / Video duration — Choose 720p or 1080p and a 3 to 15 second duration. Aspect ratio is available for text-to-video and multi-image reference video; the prompt is optional only in single-image mode.
Credit cost / HappyHorse 1.0 — 720p costs 28 credits per output second and 1080p costs 48 credits per output second. A 3 to 15 second request therefore costs 84 to 720 credits.

What to know first

HappyHorse 1.0 / Asynchronous task — Editing an existing video is currently unavailable on this page.
HappyHorse 1.0 / Prompt limit — Chinese present: 2,500; otherwise: 5,000; rejected before charge
HappyHorse 1.0 / Upload limit / Asynchronous task — Use exactly 1 image for image-to-video or 2 to 9 images for reference video. Images must be JPEG, PNG, or WebP and no larger than 10 MB; single-image mode requires both dimensions to be at least 300 px, while reference mode requires the shortest side to be at least 400 px.

Adjustable settings

Quickly evaluate whether this model fits your business use case.

Resolution
Optional
Parameter type: select
Default: 1080p
720p
1080p
Aspect ratio
Optional
Parameter type: select
Default: 16:9
16:9
9:16
1:1
4:3
3:4
Video duration
Optional
Parameter type: number
Default: 5
Range 3 - 15
Random seed
Optional
Parameter type: number
Default: 0
Range 0 - 2147483647

Credit cost

28 / 48 credits per output second

720p costs 28 credits per output second and 1080p costs 48 credits per output second. A 3 to 15 second request therefore costs 84 to 720 credits.

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.

Wan 2.7 Video

Wan 2.7 supports text-to-video, first-frame or first-and-last-frame image-to-video, and video editing. It currently offers 720p and 1080p, so compare media requirements, duration, framing, and estimated credits together.

AI video model
16 credits/second at 720p; 24 credits/second at 1080p
View detailsUse now

Kling 3.0

Review Kling 3.0 on Kyeo AI: 3–15 seconds, single-shot or up to 5 multi-shots, first/last frames, sound, and std/pro/4k per-second rates. A fit for specifying first and last frames or splitting a 3–15-second concept into up to 5 short shots. Character consistency, lip sync, text, sound, and shot continuity still require review of the actual result.

AI video model
42–1005 credits / request
View detailsUse now

Seedance 2.0

Seedance 2.0 / Capabilities — Text accepts no media; frames requires a first frame and allows a last frame; reference requires a prompt and at least one image, video, or audio reference. Reference media cannot be sent with endpoint-frame fields. Seedance 2.0 supports three mutually exclusive text, frame, and multimodal-reference scenes. The current callable output set is 720p, 1080p, and 4K for 4–15 seconds; video-reference requests are available only at 1080p or 4K because those are the current priced combinations. 164–3,840 credits per request

AI video model
164–3,840 credits per request
View detailsUse now

Sources

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

Source note

HappyHorse 1.0 on Kyeo supports text-to-video, single-image animation, and multi-image reference video from one model page. The currently available workflows are prompt-only video, one-image video, and reference video with 2 to 9 images. Use exactly 1 image for image-to-video or 2 to 9 images for reference video. Images must be JPEG, PNG, or WebP and no larger than 10 MB; single-image mode requires both dimensions to be at least 300 px, while reference mode requires the shortest side to be at least 400 px. Choose 720p or 1080p and a 3 to 15 second duration. Aspect ratio is available for text-to-video and multi-image reference video; the prompt is optional only in single-image mode. Chinese present: 2,500; otherwise: 5,000; rejected before charge. 720p costs 28 credits per output second and 1080p costs 48 credits per output second. A 3 to 15 second request therefore costs 84 to 720 credits. Editing an existing video is currently unavailable on this page.

Last updated: 2026-08-27
HappyHorse 1.0 — Kyeo AI capability and pricing review
Editorial review