HappyHorse Reference-to-Video 1.1: Image to Video Online
Bottom line
HappyHorse Reference-to-Video 1.1 builds a new 4-15 second scene around 1 to 9 reference photos, in nine aspect ratios at 720p or 1080p; 5 seconds costs 45 or 58 credits. Upload a starting frame, choose HappyHorse Reference-to-Video 1.1 in the Image to Video tool, and animate it on VdoBloom. The credit price appears before every generation.

HappyHorse Reference-to-Video 1.1 places a subject from your photos into a scene you describe. Upload 1 to 9 reference images of a person, product, mascot or style, write a prompt of up to 5,000 characters, and get a new 4 to 15 second clip at 720p or 1080p in any of nine frame shapes, including 21:9 and 9:21. A 5-second clip costs 45 credits at 720p or 58 at 1080p; 15 seconds costs 135 or 173. It is for series work, where the same character or product has to stay recognisable across several different shots.
The difference from image-to-video is what happens to the photos. Image-to-video keeps one photo as the opening frame and moves it. Reference-to-video uses the photos as a guide to identity and appearance, then composes a fresh scene, so the output does not have to look like any one of your uploads. Version 1.1 costs less than 1.0 at every setting and adds 4:5, 5:4, 21:9 and 9:21 to 1.0's five frames.
There is no sample clip for this mode on the page yet. Below: the spec table, the cost of every length, how to build a reference set, how all six HappyHorse pages differ, how 1.1 compares with WAN 2.7 and Seedance 2.5 reference workflows, and the limits.
HappyHorse Reference-to-Video 1.1 specs at a glance
Values enforced by VdoBloom's backend and shown in the dashboard for happyhorse-1-1/reference-to-video. The settings panel labels the upload slot Reference Images (1-9), and the server refuses a request with none or with more than nine.
| Spec | HappyHorse Reference-to-Video 1.1 on VdoBloom |
|---|---|
| Inputs | 1 to 9 reference images plus a text prompt (both required) |
| Prompt length | Up to 5,000 characters |
| Clip length | 4 to 15 seconds, any whole second |
| Resolutions | 720p or 1080p |
| Aspect ratios | 16:9, 9:16, 1:1, 4:3, 3:4, 4:5, 5:4, 21:9, 9:21 |
| Price per clip | 36-135 credits at 720p, 47-173 at 1080p; the number of reference images does not change it |
| Cheapest render | 36 credits: 4 seconds at 720p |
| Content label | MODERATE (standard filtering) |
| Where it runs | Image to Video tab; excluded from the effect-tab model lists |
| Failed jobs | Credits refunded automatically |
What a reference-to-video clip costs, and what a series costs
Reference-to-video on 1.1 is billed on the same list as the other two 1.1 modes, and uploading nine references costs the same as uploading one. Price depends only on length and resolution. Because this mode is usually used for several clips, it helps to price the series: three 8-second 720p clips are 216 credits, and the same three at 1080p are 279. On 1.0 those three 1080p clips would be 474.
Dollar values use the Lite plan rate ($15 for 300 credits, $0.05 a credit). A one-time 300-credit pack is $19.50 and never expires, which suits a one-off campaign; plan credits reset each billing cycle.
| Length | 720p | 1080p | Same length on 1.0 at 1080p |
|---|---|---|---|
| 4 s (minimum) | 36 cr ($1.80) | 47 cr ($2.35) | 79 cr |
| 5 s | 45 cr ($2.25) | 58 cr ($2.90) | 99 cr |
| 6 s | 54 cr ($2.70) | 70 cr ($3.50) | 119 cr |
| 7 s | 63 cr ($3.15) | 81 cr ($4.05) | 138 cr |
| 8 s | 72 cr ($3.60) | 93 cr ($4.65) | 158 cr |
| 9 s | 81 cr ($4.05) | 104 cr ($5.20) | 177 cr |
| 10 s | 90 cr ($4.50) | 116 cr ($5.80) | 197 cr |
| 11 s | 99 cr ($4.95) | 127 cr ($6.35) | 217 cr |
| 12 s | 108 cr ($5.40) | 139 cr ($6.95) | 236 cr |
| 13 s | 117 cr ($5.85) | 150 cr ($7.50) | 256 cr |
| 14 s | 126 cr ($6.30) | 162 cr ($8.10) | 275 cr |
| 15 s (maximum) | 135 cr ($6.75) | 173 cr ($8.65) | 295 cr |
Read more: HappyHorse 1.1 reference-to-video pricing in dollars · Credit packs and plans
Building a reference set that holds up
Most consistency problems come from the references, not the prompt. Pick images where the subject is clear, well lit and not partly hidden, and cover the angles the scenes will need: a front view, a three-quarter view and, if the subject will turn, a profile. For products, include the side with the logo or label you need visible. Several near-identical photos add little; three to five varied ones usually tell the model more than nine copies of the same angle.
Then keep the set fixed. Reuse exactly the same images for every clip in a series and change only the prompt, which should describe the new setting, action and camera rather than the subject's appearance. If you describe the subject in words as well, keep that description short and identical in every prompt so it does not pull the look in different directions. Choose the aspect ratio per clip; the references work the same in 21:9 as in 9:16.
- Clear, well-lit, unobstructed photos of the subject.
- Varied angles over duplicate shots; 3-5 images is a practical start.
- Same reference set for every clip in a series.
- Prompt the scene, action and camera; keep any subject description identical across prompts.
- Use only images of people you have the right to depict.
Read more: How to use HappyHorse 1.1 reference-to-video for consistent characters · Reference-to-video prompt workflows
All six HappyHorse pages compared
Of the six HappyHorse entries, the two reference modes are the only ones that take more than one image, and the 1.1 reference mode is the only one that combines multiple references with the nine-ratio frame set. Every entry shares the 4-15 second range, 720p/1080p and the MODERATE label; the price list follows the version.
| Page | You start from | Images | Prompt | Aspect ratios | 4 s at 720p | 15 s at 1080p |
|---|---|---|---|---|---|---|
| Text-to-Video 1.1 | A text prompt | None | Required, up to 5,000 characters | 9: 16:9, 9:16, 1:1, 4:3, 3:4, 4:5, 5:4, 21:9, 9:21 | 36 cr | 173 cr |
| Image-to-Video 1.1 | One photo | Exactly 1 | Optional, up to 5,000 characters | No setting; frame the photo | 36 cr | 173 cr |
| Reference-to-Video 1.1 | Reference photos plus a prompt | 1 to 9 | Required, up to 5,000 characters | 9, same set as Text-to-Video 1.1 | 36 cr | 173 cr |
| Text-to-Video 1.0 | A text prompt | None | Required, up to 5,000 characters | 5: 16:9, 9:16, 1:1, 4:3, 3:4 | 46 cr | 295 cr |
| Image-to-Video 1.0 | One photo | Exactly 1 | Optional, up to 5,000 characters | No setting; frame the photo | 46 cr | 295 cr |
| Reference-to-Video 1.0 | Reference photos plus a prompt | 1 to 9 | Required, up to 5,000 characters | 5, same set as Text-to-Video 1.0 | 46 cr | 295 cr |
Read more: HappyHorse Text-to-Video 1.1 · HappyHorse Image-to-Video 1.1 · HappyHorse Text-to-Video 1.0 · HappyHorse Image-to-Video 1.0 · HappyHorse Reference-to-Video 1.0
HappyHorse 1.1 vs WAN 2.7 vs Seedance 2.5 for reference-driven video
Three reference workflows on VdoBloom take different approaches. WAN 2.7 Reference-to-Video is the cheapest per clip but offers only 5 or 10 seconds and no ratio setting; it can also take reference videos. Seedance 2.5 accepts up to nine photos that you tag in the prompt as @Image1, @Image2 and so on, runs up to 30 seconds and generates audio, at a higher per-second rate. HappyHorse 1.1 sits between them on price, allows any length from 4 to 15 seconds, and has the widest frame choice of the three. Vidu Q4 Reference is a fourth option in the same tab, using the same 1-9 image panel with five aspect ratios; its price is shown before you generate.
| Model | Lengths | Aspect ratios | References | 5 s at 720p | Longest clip at 720p |
|---|---|---|---|---|---|
| HappyHorse Reference-to-Video 1.1 | 4-15 s, every second | 9, incl. 21:9 and 9:21 | 1-9 images | 45 cr | 135 cr (15 s) |
| HappyHorse Reference-to-Video 1.0 | 4-15 s, every second | 5 | 1-9 images | 58 cr | 173 cr (15 s) |
| WAN 2.7 Reference-to-Video | 5 or 10 s | No ratio setting | Reference images or videos | 32 cr | 64 cr (10 s) |
| Seedance 2.5 (reference photos) | 4-30 s, every second | 6, incl. 21:9 | Up to 9 photos tagged @Image1, @Image2 | 126 cr | 756 cr (30 s) |
Read more: WAN 2.7 Reference-to-Video model page · Seedance 2.5 model page · Vidu Q4 Reference model page
Where it runs, and where it does not
Open the Image to Video tab, choose HappyHorse and then Reference-to-Video 1.1, upload your references in the Reference Images (1-9) panel, write the prompt and set length, resolution and ratio. The credit total updates before you generate.
Reference models are deliberately left out of the effect tabs' model lists, because those tabs animate a single photo and a multi-image reference model is the wrong fit there. To use this mode, select it yourself.
Limits and honest caveats
Consistency is guided by the references, not guaranteed: busy scenes, extreme angles the references never showed, or several similar-looking people in one frame make drift more likely. Text such as small logos can change between clips, so check it on every render. The ceiling is 15 seconds and 1080p; for longer takes, Seedance 2.5 reaches 30 seconds. There is no audio setting. The content filter blocks prohibited categories but does not check whether you have the right to use someone's likeness; that responsibility is yours. And the 10 free signup credits are below the 36-credit minimum.
What creators use HappyHorse Reference-to-Video 1.1 for
- A recurring mascot or presenter appearing in an office, a street and a studio across a three-clip series, from one reference set.
- One product placed into lifestyle, studio and outdoor scenes for an ad set, each rendered at its own placement's aspect ratio.
- Matched 21:9 and 9:21 cuts of the same character for a widescreen site header and a tall vertical banner.
- Short episodic content where a character needs to look the same in every episode without a new photoshoot.
- Style references: a few frames of an illustration style used to keep a look consistent across generated clips.
How to use HappyHorse Reference-to-Video 1.1 on VdoBloom
- 1Open the Image to Video tool and select HappyHorse Reference-to-Video 1.1 from the model picker.
- 2Upload your starting image and describe the motion you want in the prompt.
- 3Choose your duration (4–15s), quality (720p/1080p), aspect ratio, review the credit cost, and generate.
Frequently asked questions
What is HappyHorse Reference-to-Video 1.1?
It is the HappyHorse 1.1 mode that takes 1 to 9 photos of a subject plus a prompt and generates a new scene with that subject in it, 4 to 15 seconds long at 720p or 1080p, in nine aspect ratios. Unlike image-to-video, none of your photos is used as the literal first frame.
How many reference images can I use?
From 1 to 9 per generation. The dashboard panel is labelled Reference Images (1-9) and the server refuses requests outside that range. Price does not change with the number of images.
How much does it cost?
Same as every HappyHorse 1.1 mode: 36 credits for 4 seconds at 720p up to 135 for 15 seconds; 47 to 173 at 1080p. A 5-second 1080p clip is 58 credits, about $2.90 at the Lite plan rate.
Which aspect ratios can I use?
Nine: 16:9, 9:16, 1:1, 4:3, 3:4, 4:5, 5:4, 21:9 and 9:21. Version 1.0 of this mode has the first five.
Is a prompt required?
Yes. Reference-to-video needs a prompt (up to 5,000 characters) because the scene is built from it; the references only tell the model who or what should appear.
Can I use reference-to-video on the effect tabs?
No. VdoBloom leaves the reference models out of the effect tabs because those tabs animate one photo. On effect tabs that list HappyHorse, use Image-to-Video 1.1 instead, or run reference-to-video from the Image to Video tab.
HappyHorse 1.1 or WAN 2.7 Reference-to-Video?
WAN 2.7 is cheaper (32 credits for 5 seconds at 720p vs 45) and can take reference videos, but offers only 5 or 10 seconds and no ratio setting. HappyHorse 1.1 allows any length from 4 to 15 seconds and nine ratios. Pick WAN 2.7 for short, cheap clips and HappyHorse 1.1 when length or framing matters.
Can I use photos of real people?
Only people you have the right to depict, such as yourself or someone who has agreed. The MODERATE filter blocks prohibited content, but likeness rights are your responsibility.
How does 1.1 compare with HappyHorse Reference-to-Video 1.0?
Same 1-9 references, same 4-15 seconds, same resolutions. 1.1 adds 4:5, 5:4, 21:9 and 9:21 and costs less: 45 vs 58 credits for 5 seconds at 720p, 173 vs 295 for 15 seconds at 1080p.
Can I try it for free?
New accounts get 10 credits, below the 36-credit minimum, so you need a top-up. A one-time 300-credit pack is $19.50 with no subscription; that covers a three-clip 8-second series at 1080p (279 credits).
HappyHorse Reference-to-Video 1.1 guides, prices and comparisons
This page is the HappyHorse Reference-to-Video 1.1 hub. Each guide below goes deeper on one question and links back here.
HappyHorse 1.1 reference-to-video pricing
Every credit tier in dollars.
How to use HappyHorse 1.1 reference-to-video
Consistent characters, step by step.
1.1 image-to-video vs reference-to-video
Animate this photo, or put this subject somewhere new.
1.1 reference-to-video vs text-to-video
When adding photos to a prompt is worth it.
Reference-to-video prompt workflows
Prompt patterns for keeping a subject consistent.
Best AI model for image to video
Where multi-reference models fit among photo animators.