Character elements vs frame-level control — which image animation approach fits?
WAN v2.2 is no longer offered on Melies. Kling v3 Standard is available today. The specs below are kept for reference.
Kling v3 Standard from Kuaishou and WAN v2.2 from Alibaba represent two different approaches to AI video generation. Kling's image-to-video model with custom character elements and end-frame control. On the other side, alibaba's image-to-video model with granular frame and interpolation controls.
Both models cost 60 credits per generation, so the decision comes down to capabilities rather than budget. Kling v3 Standard excels at image animation, character-driven video, controlled start/end frames, while WAN v2.2 is better suited for frame-precise animation, interpolation workflows, technical control.
Updated November 2026
WAN v2.2 is no longer offered on Melies, so Kling v3 Standard is the one you can use here. At 60 credits, it is a fit for image animation. For other options, compare the current video models and their credit costs on the pricing page.
| Provider | Kuaishou | Alibaba |
| Released | Feb 2026 | Jul 2025 |
| Cost | 60 | 60 |
| Speed | Medium | Medium |
| Max duration | 15 seconds | ~5 seconds at defaults (81 frames / 16fps) |
| Image input | ||
| Audio | ||
| Resolutions | Standard | 480p, 580p, 720p |
Both models cost the same. Here's how credits add up at scale.
| Volume | Kling v3 Standard | WAN v2.2 |
|---|---|---|
| 5 videos | 300 | 300 |
| 10 videos | 600 | 600 |
| 25 videos | 1,500 | 1,500 |
Kling v3 Standard generates native audio alongside the video — no need to add sound in post-production.
At 60 credits per video, Kling v3 Standard lets you generate more clips and pick the best ones.
Practical answers before you start creating.





Compare Kling v3 Standard with the other video models on Melies in one workspace. Switch models freely, same credits.
Start Creating Videos