HappyHorse Reference-to-Video 1.1: Image to Video Online
Bottom line
Builds new scenes around your reference images, keeping subjects consistent across 4-15s clips in 9 ratios. 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.
Reference-to-video solves a different problem than ordinary image animation, and HappyHorse Reference-to-Video 1.1 is built around that distinction. Instead of treating your upload as a first frame to set in motion, it treats reference images as a guide — who the subject is, what the product looks like, what style to hold — and generates a new scene from your prompt around them. The payoff is consistency: the same character or object appearing across multiple clips without drifting into a stranger by the third shot.
Specs match the strongest of the HappyHorse line: 4 to 15 second durations at any whole second, 720p or 1080p output, and the full nine-ratio framing set (16:9, 9:16, 1:1, 4:3, 3:4, 4:5, 5:4, 21:9, 9:21). A character established once can appear in an ultrawide establishing shot and a 9:16 vertical cut generated from the same references. Pricing runs about 9 credits/second at 720p and 11.75 at 1080p, cheaper than the 1.0 version's reference-to-video pricing.
Content filtering is MODERATE, the standard tier. Because this workflow generates new scenes around a recognizable subject, reference images of real people should be ones you have the right to use.
What it costs on VdoBloom
About 9 credits/second at 720p, 11.75 at 1080p, across the 4-15 second range. A 4-second 720p clip is 36 credits; a 15-second 1080p clip is 173 credits — versus 295 credits for the equivalent on HappyHorse Reference-to-Video 1.0, making 1.1 the cheaper choice for the same result.
Keeping a subject consistent across clips
The practical workflow is to gather two or three clean reference images of the subject — consistent lighting and angle help — and reuse that same reference set across every prompt in a series. Because reference-to-video generates a new scene each time rather than animating one fixed frame, you can move the same subject through an ultrawide 21:9 establishing shot and a 9:16 vertical cut without re-shooting or re-uploading anything beyond the original references.
What creators use HappyHorse Reference-to-Video 1.1 for
- Keeping a brand mascot or recurring character consistent across an episodic series of clips.
- Placing one product into multiple generated settings — lifestyle, studio, outdoor — from a single reference set.
- Producing matched ultrawide and vertical cuts of the same subject for different ad placements.
- Building a multi-shot campaign around one character without a new reference photoshoot per scene.
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
How is reference-to-video different from regular image-to-video?
Image-to-video animates your upload as the literal opening frame. HappyHorse Reference-to-Video 1.1 instead uses your images as a guide to the subject's identity and look, then generates an entirely new prompted scene around that subject.
What does HappyHorse Reference-to-Video 1.1 cost?
About 9 credits/second at 720p, 11.75 at 1080p — the same rate as HappyHorse 1.1's other modes, and cheaper than the 1.0 version's roughly 11.5/19.7. An 8-second 720p clip is 72 credits; a 12-second 1080p clip is 139 credits.
What framing and length options do I get?
Nine aspect ratios — including 21:9 ultrawide and 9:21 vertical — with durations from 4 to 15 seconds in one-second steps, rendered at 720p or 1080p.
What is it best at keeping consistent?
Recurring characters, products, and visual styles across multiple clips. Because the same reference images can drive many generations, a subject stays recognizable from shot to shot instead of morphing between runs.
Is there a free way to test HappyHorse Reference-to-Video 1.1?
New VdoBloom accounts start with 10 free credits, short of the 36-credit floor for a 4-second 720p clip here — useful for reviewing the reference-upload workflow and pricing before topping up.
What's the content policy on HappyHorse Reference-to-Video 1.1?
MODERATE, the standard filtering tier. Reference workflows involving real people should respect likeness rights on top of whatever the content filter itself blocks.
Happy Horse 1.1 vs Seedance 2 — which handles multi-subject scenes better?
Both support keeping more than one subject in frame: HappyHorse 1.1's reference-to-video mode is purpose-built for it across nine aspect ratios, while Seedance 2's family handles two reference photos via @Image1/@Image2 prompt tags. Neither is objectively better — HappyHorse's reference workflow is a dedicated mode with no duration/input tradeoffs, while Seedance's two-image approach is bundled into its regular per-second pricing. Test both on the same reference set if consistency is the priority.
Is HappyHorse Reference-to-Video 1.1 open source?
Not established, so no claim either way — treat it as a proprietary model accessible only through VdoBloom.
How does 1.1 compare with the 1.0 version of Reference-to-Video?
1.1 costs less per second (about 9/11.75 credits/second at 720p/1080p versus 1.0's roughly 11.5/19.7) and adds four extra aspect ratios (4:5, 5:4, 21:9, 9:21) on top of 1.0's five. Duration range and resolution tiers are otherwise identical.