Image-to-video models turn a starting photo into motion rather than generating from a text prompt alone. The 20 models below all list image-to-video among their categories, ranked by the best position each holds on a Versely leaderboard.
Ranking method
Filtered to models with the image-to-video category, sorted by best leaderboard position (unranked models after, cheapest complete job first).
Full ranking
| # | Model | Provider | Credits | Starting image |
|---|---|---|---|---|
| 1 | Happy Horse 1.1 Image to Video | Alibaba | 34-216 credits | Required |
| 2 | Vidu Q3 Image to Video | Vidu | 14-93 credits | Required |
| 3 | Pixverse 5.6 Image to Video | Pixverse | 28-240 credits | Required |
| 4 | Kling O3 Pro Image to Video | Kling | 56-168 credits | Required |
| 5 | Cosmos 3 Super Image to Video | NVIDIA | 8-28 credits | Required |
| 6 | Runway Gen-4.5 | Runway | 200-400 credits | Optional |
| 7 | Kling Video V3 Standard Image to Video | Kling | 51-152 credits | Required |
| 8 | Kling O3 Standard Image to Video | Kling | 45-135 credits | Required |
| 9 | Wan 2.7 Image to Video | Wan | 16-180 credits | Required |
| 10 | Hailuo 2.3 Pro | Hailuo | 40-79 credits | Required |
| 11 | Hailuo 2.3 Fast | Hailuo | 12-23 credits | Required |
| 12 | Wan Video 2.5 Image to Video | Wan | 20-120 credits | Required |
| 13 | Seedance Image to Video | ByteDance | 3-84 credits | Required |
| 14 | Vidu Q2 Pro Image to Video | Vidu | 16-88 credits | Required |
| 15 | Wan 2.6 Image to Video | Wan | 20-90 credits | Required |
| 16 | LTX 2 Pro | LTX | 29-192 credits | Required |
| 17 | Pika 2.5 Image to Video | Pika | 12-80 credits | Required |
| 18 | Kling V2.1 | Kling | 56-112 credits | Required |
| 19 | Midjourney V7 Image to Video | Midjourney | 28-88 credits | Required |
| 20 | LTX 2.3 Image to Video Pro | LTX | 29-192 credits | Required |
The top 5, explained
#1 — Happy Horse 1.1 Image to Video (Alibaba) costs 34-216 credits and sits at #9 in image to video on Versely's live model rankings. It outputs up to 1080p. Starting image: Required.
#2 — Vidu Q3 Image to Video (Vidu) costs 14-93 credits, discounted from a headline 28 and sits at #12 in image to video on Versely's live model rankings. It outputs up to 1080p. Starting image: Required.
#3 — Pixverse 5.6 Image to Video (Pixverse) costs 28-240 credits and sits at #13 in image to video on Versely's live model rankings. It outputs up to 1080p. Starting image: Required.
#4 — Kling O3 Pro Image to Video (Kling) costs 56-168 credits and sits at #15 in image to video on Versely's live model rankings. Starting image: Required.
#5 — Cosmos 3 Super Image to Video (NVIDIA) costs 8-28 credits and sits at #18 in image to video on Versely's live model rankings. It outputs up to 720p. Starting image: Required.
Compare these models head-to-head
More capability rankings
Frequently asked questions
What is the best image-to-video AI model?+
Happy Horse 1.1 Image to Video by Alibaba tops this ranking. Filtered to models with the image-to-video category, sorted by best leaderboard position (unranked models after, cheapest complete job first). Happy Horse 1.1 Image to Video costs 34-216 credits and sits at #9 in image to video on Versely's live model rankings.
How is this ranking calculated?+
Filtered to models with the image-to-video category, sorted by best leaderboard position (unranked models after, cheapest complete job first).
How many models qualify for this ranking?+
20 models with a page on Versely meet the criteria for "Best image-to-video AI model", across 12 providers.
What's the cheapest option in this ranking?+
Seedance Image to Video is the cheapest at 3-84 credits, against 34-216 credits for Happy Horse 1.1 Image to Video, the top-ranked entry.
Do all of these models hold a Versely leaderboard position?+
Yes — all 20 models here hold a position on at least one Versely leaderboard. Versely ranks each capability separately, so the leaderboard a position was earned on is named alongside it.
Try Happy Horse 1.1 Image to Video inside Versely
The all-in-one AI studio for creators. 60+ models for video, image, voice, music and lipsync — in your browser or on your phone.
Free account. Works in your browser - no install needed. The same account signs in on your phone.
Guides
One model for image, video and audio?
FLUX 3, MiniMax H3, Wan 3.0 and Gemini Omni Flash train all three modalities at once. When one model beats a best-of-breed stack, and three jobs where it loses.
60+ AI Models, One App: The Complete Versely Model Guide
A practical map of every AI model inside Versely — what each one is best at, when to pick it, and how to route prompts across models for the best result.