AI video and image model specs and features
This table lists what each AI video and image model in Twistavo AI Studio accepts and what one reference output costs: 31 video models and 33 image generation models, with clip lengths, resolutions, aspect ratios, the sound setting, required inputs, video extend, motion control, video edit and credits, then 3 video editing and motion models with their inputs and features.
Updated . Download: CSV · JSON. License CC BY 4.0, attribution "Twistavo".
Which AI video model supports start and end frames, reference images, extend and motion control
| Seedance 2.5 | video | 4 | 30 | 4 to 30, every 1 s | 480p, 720p, 1080p | 16:9, 4:3, 1:1, 3:4, 9:16, 21:9 | sound setting: on or off | yes | yes | yes | up to 30 reference images, 30 images in total with frames | up to 10 videos | up to 10 audio tracks | 50 | no | no | no | 5 s clip | 301 | 6.67 | 3.20 |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Seedance 2.5 Extend | video | 4 | 30 | 4 to 30, every 1 s | 480p, 720p, 1080p | not published | sound setting: on or off | yes | no | no | up to 30 reference images | 1 video, required | up to 10 audio tracks | not published | yes, forward or backward | no | no | n/a | not published | not published | not published |
| Seedance 2.0 | video | 4 | 15 | 4 to 15, every 1 s | 480p, 720p, 1080p, 4k | 16:9, 4:3, 1:1, 3:4, 9:16, 21:9 | sound setting: on or off | yes | yes | yes | up to 9 reference images, 9 images in total with frames | up to 3 videos | up to 3 audio tracks, with an image or a video | 12 | no | no | no | 5 s clip | 193 | 4.28 | 2.05 |
| Seedance 2.0 Fast | video | 4 | 15 | 4 to 15, every 1 s | 480p, 720p | 16:9, 4:3, 1:1, 3:4, 9:16, 21:9 | sound setting: on or off | yes | yes | yes | up to 9 reference images, 9 images in total with frames | up to 3 videos | up to 3 audio tracks, with an image or a video | 12 | no | no | no | 5 s clip | 108 | 2.39 | 1.15 |
| Kling 4.0 | video | 3 | 30 | 3 to 30, every 1 s | 720p, 1080p | 16:9, 9:16, 1:1, 21:9 | not published | yes | yes | yes | up to 10 reference images, 10 images in total with frames | 1 video, 3 to 30 s each | no | not published | no | no | no | 5 s clip | 108 | 2.39 | 1.15 |
| Kling 4.0 Flash | video | 3 | 20 | 3 to 20, every 1 s | 720p | 16:9, 9:16, 1:1, 21:9 | not published | yes | yes | no | up to 10 reference images, 10 images in total with frames | 1 video, 3 to 30 s each | no | not published | no | no | no | 5 s clip | 129 | 2.86 | 1.37 |
| Kling 3.0 Turbo | video | 3 | 15 | 3 to 15, every 1 s | 720p, 1080p | 16:9, 9:16, 1:1 | not published | yes | yes | no | no | no | no | not published | no | no | no | 5 s clip | 65 | 1.44 | 0.69 |
| Kling 3.0 Standard | video | 3 | 15 | 3 to 15, every 1 s | not published | 16:9, 9:16, 1:1 | sound setting: on or off | yes | yes | yes | no | no | no | not published | no | no | no | 5 s clip | 76 | 1.68 | 0.81 |
| Kling 3.0 Pro | video | 3 | 15 | 3 to 15, every 1 s | not published | 16:9, 9:16, 1:1 | sound setting: on or off | yes | yes | yes | no | no | no | not published | no | no | no | 5 s clip | 86 | 1.91 | 0.91 |
| Kling 3.0 4K | video | 3 | 15 | 3 to 15, every 1 s | not published | 16:9, 9:16, 1:1 | sound setting: on or off | yes | yes | yes | no | no | no | not published | no | no | no | 5 s clip | 258 | 5.72 | 2.74 |
| Wan 3.0 | video | 4 | 10 | 4 to 10, every 1 s | 720p, 1080p | 16:9, 9:16, 1:1 | not published | yes | yes | no | no | no | no | not published | no | no | no | 5 s clip | 65 | 1.44 | 0.69 |
| Wan 3.0 Prime | video | 4 | 10 | 4 to 10, every 1 s | 720p, 1080p | 16:9, 9:16, 1:1 | not published | yes | yes | no | no | no | no | not published | no | no | no | 5 s clip | 118 | 2.62 | 1.25 |
| Wan 2.7 | video | 4 | 10 | 4 to 10, every 1 s | 720p, 1080p | 16:9, 9:16, 1:1 | not published | yes | yes | no | no | no | no | not published | no | no | no | 5 s clip | 65 | 1.44 | 0.69 |
| Wan 2.6 | video | 5 | 10 | 5 to 10, every 5 s | 720p, 1080p | 16:9, 9:16, 1:1 | not published | yes | no | no | no | no | no | not published | no | no | no | 5 s clip | 65 | 1.44 | 0.69 |
| MiniMax H3 | video | 5 | 15 | 5 to 15, every 1 s | 2K | 16:9, 9:16, 1:1 | not published | yes | yes | no | no | no | no | not published | no | no | no | 5 s clip | 86 | 1.91 | 0.91 |
| MiniMax Hailuo 2.3 | video | 6 | 10 | 6 to 10, every 4 s | not published | not published | not published | yes | yes | no | no | no | no | not published | no | no | no | n/a | not published | not published | not published |
| Grok Imagine Video 1.5 | video | 4 | 10 | 4 to 10, every 1 s | not published | not published | not published | yes | no | no | 1 to 8 reference images, at least 1 required | no | no | not published | no | no | no | 5 s clip | 193 | 4.28 | 2.05 |
| FLUX 3 Video | video | 5 | 20 | 5 to 20, every 1 s | 720p, 1080p, 2k, 4k | 21:9, 2:1, 16:9, 4:3, 1:1, 3:4, 9:16 | sound setting: on or off | yes | yes | yes | up to 8 reference images | up to 3 videos | no | not published | no | no | no | 5 s clip | 258 | 5.72 | 2.74 |
| Gemini Omni Flash | video | 4 | 10 | 4 to 10, every 1 s | 720p | 16:9, 9:16 | not published | yes | no | no | up to 7 reference images | 1 video | no | not published | no | no | no | 5 s clip | 129 | 2.86 | 1.37 |
| Gemini Omni Flash 1.1 | video | 3 | 10 | 3 to 10, every 1 s | 360p, 720p, 1080p, 4k | 16:9, 9:16 | not published | yes | yes | yes | up to 8 reference images | up to 3 videos | no | not published | no | no | yes, edit mode | 5 s clip | 129 | 2.86 | 1.37 |
| Gemini Omni Flash 1.2 | video | 3 | 15 | 3 to 15, every 1 s | 360p, 720p, 1080p, 4k | 16:9, 9:16 | not published | yes | yes | yes | up to 8 reference images | up to 3 videos | no | not published | yes, extend mode | no | yes, edit mode | 5 s clip | 97 | 2.15 | 1.03 |
| Grok Video | video | 1 | 15 | 1 to 15, every 1 s | not published | 16:9, 9:16, 1:1 | not published | yes | yes | no | no | no | no | not published | no | no | no | 5 s clip | 65 | 1.44 | 0.69 |
| Grok Imagine Video 1.5 Lite | video | 1 | 15 | 1 to 15, every 1 s | 480p, 720p, 1080p | 16:9, 9:16, 4:3, 3:4, 1:1, 3:2, 2:3 | not published | yes | yes | no | no | no | no | not published | no | no | no | 5 s clip | 43 | 0.95 | 0.46 |
| Happy Horse Video | video | 3 | 15 | 3 to 15, every 1 s | 720p, 1080p | 16:9, 9:16, 1:1, 4:3, 3:4 | not published | yes | yes | no | no | no | no | not published | no | no | no | 5 s clip | 108 | 2.39 | 1.15 |
| Kling 3.0 Omni (Frames) | video | 3 | 15 | 3 to 15, every 1 s | not published | 16:9, 9:16, 1:1 | sound setting: on or off | yes | yes | yes | no | no | no | not published | no | no | no | 5 s clip | 54 | 1.20 | 0.57 |
| Kling 3.0 Omni | video | 3 | 15 | 3 to 15, every 1 s | not published | 16:9, 9:16, 1:1 | sound setting: on or off | yes | no | no | up to 8 reference images | no | no | not published | no | no | no | 5 s clip | 54 | 1.20 | 0.57 |
| Kling 2.6 Video | video | 5 | 10 | 5 to 10, every 5 s | not published | 16:9, 9:16, 1:1 | sound setting: on or off | yes | yes | no | no | no | no | not published | no | no | no | 5 s clip | 86 | 1.91 | 0.91 |
| MiniMax H3 Max | video | 5 | 15 | 5 to 15, every 1 s | 480p, 768p | 21:9, 16:9, 4:3, 1:1, 3:4, 9:16 | not published | yes | yes | yes | up to 8 reference images | up to 3 videos | up to 3 audio tracks | not published | no | no | no | 5 s clip | 108 | 2.39 | 1.15 |
| Seedance 2.0 Mini | video | 4 | 15 | 4 to 15, every 1 s | 480p, 720p | 16:9, 9:16, 4:3, 3:4, 1:1, 21:9 | sound setting: on or off | yes | yes | yes | up to 8 reference images | up to 3 videos | up to 3 audio tracks | not published | no | no | no | 5 s clip | 43 | 0.95 | 0.46 |
| Google Veo 3.1 | video | 4 | 8 | 4 to 8, every 2 s | not published | 16:9, 9:16 | not published | yes | yes | no | no | no | no | not published | no | no | no | n/a | not published | not published | not published |
| Google Veo 3.1 Lite | video | 4 | 8 | 4 to 8, every 2 s | not published | 16:9, 9:16 | sound setting: on or off | yes | yes | yes | no | no | no | not published | no | no | no | n/a | not published | not published | not published |
| Soul 2 | image | n/a | n/a | n/a | 720p, 1080p | 9:16, 16:9, 4:3, 3:4, 1:1, 2:3, 3:2 | n/a | yes | no | no | no | no | no | not published | n/a | n/a | n/a | 1 image | 2 | 0.04 | 0.02 |
| Grok Imagine 2.0 | image | n/a | n/a | n/a | 2k | 1:1, 4:3, 3:4, 16:9, 9:16 | n/a | yes | no | no | up to 8 reference images | no | no | not published | n/a | n/a | n/a | n/a | not published | not published | not published |
| Recraft 4.1 | image | n/a | n/a | n/a | 1k | 1:1, 4:3, 3:4, 16:9, 9:16 | n/a | yes | no | no | no | no | no | not published | n/a | n/a | n/a | 1 image | 11 | 0.24 | 0.12 |
| Z-Image Turbo | image | n/a | n/a | n/a | not published | 1:1, 4:3, 3:4, 16:9, 9:16 | n/a | yes | no | no | no | no | no | not published | n/a | n/a | n/a | 1 image | 2 | 0.04 | 0.02 |
| 3D Jutsu Angles | image | n/a | n/a | n/a | 1k, 1.5k, 2k | 1:1, 4:3, 3:4, 16:9, 9:16, 3:2, 2:3, 21:9 | n/a | yes | no | no | up to 10 reference images | no | no | not published | n/a | n/a | n/a | 1 image | 22 | 0.49 | 0.23 |
| FLUX.2 | image | n/a | n/a | n/a | 1k, 2k | 1:1, 4:3, 3:4, 16:9, 9:16 | n/a | yes | no | no | up to 8 reference images | no | no | not published | n/a | n/a | n/a | 1 image | 9 | 0.20 | 0.10 |
| FLUX 3 Image | image | n/a | n/a | n/a | 768sq, 1k, 1.5k, 2k, 4k | 21:9, 2:1, 16:9, 3:2, 7:5, 4:3, 5:4, 1:1, 4:5, 3:4, 5:7, 2:3, 9:16, 1:2 | n/a | yes | no | no | up to 8 reference images | no | no | not published | n/a | n/a | n/a | 1 image | 18 | 0.40 | 0.19 |
| Flux Kontext | image | n/a | n/a | n/a | not published | 1:1, 4:3, 3:4, 16:9, 9:16 | n/a | yes | no | no | up to 4 reference images | no | no | not published | n/a | n/a | n/a | 1 image | 13 | 0.29 | 0.14 |
| GPT Image 2 | image | n/a | n/a | n/a | 1k, 2k, 4k | 1:1, 4:3, 3:4, 16:9, 21:9, 9:16, 3:2, 2:3, 4:5, 5:4 | n/a | yes | no | no | up to 8 reference images | no | no | not published | n/a | n/a | n/a | 1 image | 61 | 1.35 | 0.65 |
| GPT Image 2.5 | image | n/a | n/a | n/a | 1k, 2k, 4k | 1:1, 3:2, 2:3, 4:3, 3:4, 16:9, 9:16, 21:9, 27:16, 16:27, 9:8, 8:9, 4:5, 5:4 | n/a | yes | no | no | up to 8 reference images | no | no | not published | n/a | n/a | n/a | 1 image | 3 | 0.07 | 0.03 |
| GPT Image 2.6 | image | n/a | n/a | n/a | 1k, 2k, 4k | 1:1, 3:2, 2:3, 4:3, 3:4, 16:9, 9:16, 21:9, 27:16, 16:27, 9:8, 8:9, 4:5, 5:4 | n/a | yes | no | no | up to 8 reference images | no | no | not published | n/a | n/a | n/a | 1 image | 7 | 0.16 | 0.07 |
| GPT Image 2.6 Flare | image | n/a | n/a | n/a | 1k, 2k, 4k | 1:1, 3:2, 2:3, 4:3, 3:4, 16:9, 9:16, 21:9, 27:16, 16:27, 9:8, 8:9, 4:5, 5:4 | n/a | yes | no | no | up to 8 reference images | no | no | not published | n/a | n/a | n/a | 1 image | 7 | 0.16 | 0.07 |
| Grok Image | image | n/a | n/a | n/a | 1k, 2k | 1:1, 1:2, 2:1, 3:2, 2:3, 4:3, 3:4, 16:9, 9:16 | n/a | yes | no | no | up to 8 reference images | no | no | not published | n/a | n/a | n/a | 1 image | 9 | 0.20 | 0.10 |
| Ideogram 4.5 | image | n/a | n/a | n/a | 1k, 2k | 1:1, 1:2, 2:1, 2:3, 3:2, 4:5, 5:4, 9:16, 16:9, 5:8, 8:5, 3:4, 4:3, 9:22, 22:9, 9:23, 23:9, 3:8, 8:3, 5:12, 12:5, 1:3, 3:1 | n/a | yes | no | no | up to 8 reference images | no | no | not published | n/a | n/a | n/a | 1 image | 54 | 1.20 | 0.57 |
| Ideogram 4.6 | image | n/a | n/a | n/a | 2k, 4k | 1:1, 1:2, 2:1, 2:3, 3:2, 4:5, 5:4, 9:16, 16:9, 5:8, 8:5, 3:4, 4:3, 9:21, 21:9, 9:22, 22:9, 9:23, 23:9, 3:8, 8:3, 5:12, 12:5, 1:3, 3:1 | n/a | yes | no | no | up to 8 reference images | no | no | not published | n/a | n/a | n/a | 1 image | 18 | 0.40 | 0.19 |
| Image Auto | image | n/a | n/a | n/a | not published | 1:1, 4:3, 3:4, 16:9, 9:16 | n/a | yes | no | no | up to 14 reference images | no | no | not published | n/a | n/a | n/a | 1 image | 18 | 0.40 | 0.19 |
| Kling Image 4.0 | image | n/a | n/a | n/a | 2k, 4k, 8k | 16:9, 9:16, 1:1, 4:3, 3:4, 3:2, 2:3, 21:9 | n/a | yes | no | no | up to 8 reference images | no | no | not published | n/a | n/a | n/a | 1 image | 18 | 0.40 | 0.19 |
| Kling O1 Image | image | n/a | n/a | n/a | 1k, 2k | 1:1, 16:9, 9:16, 4:3, 3:4, 3:2, 2:3, 21:9 | n/a | yes | no | no | up to 10 reference images | no | no | not published | n/a | n/a | n/a | 1 image | 5 | 0.11 | 0.05 |
| MiniMax H3 Image | image | n/a | n/a | n/a | 1k, 2k, 4k | not published | n/a | yes | no | no | up to 8 reference images | no | no | not published | n/a | n/a | n/a | 1 image | 35 | 0.78 | 0.37 |
| Nano Banana | image | n/a | n/a | n/a | not published | 1:1, 3:2, 2:3, 4:3, 3:4, 4:5, 5:4, 9:16, 16:9, 21:9 | n/a | yes | no | no | up to 8 reference images | no | no | not published | n/a | n/a | n/a | 1 image | 9 | 0.20 | 0.10 |
| Nano Banana 2.1 | image | n/a | n/a | n/a | 1k, 2k, 4k | 1:1, 3:2, 2:3, 4:3, 3:4, 4:5, 5:4, 9:16, 16:9, 21:9, 4:1, 1:4, 8:1, 1:8 | n/a | yes | no | no | up to 8 reference images | up to 3 videos | no | not published | n/a | n/a | n/a | 1 image | 13 | 0.29 | 0.14 |
| Nano Banana 2 Lite | image | n/a | n/a | n/a | 1k | 1:1, 3:2, 2:3, 4:3, 3:4, 4:5, 5:4, 9:16, 16:9, 21:9 | n/a | yes | no | no | up to 14 reference images | no | no | not published | n/a | n/a | n/a | 1 image | 9 | 0.20 | 0.10 |
| Nano Banana 2 | image | n/a | n/a | n/a | 1k, 2k, 4k | 1:1, 3:2, 2:3, 4:3, 3:4, 4:5, 5:4, 9:16, 16:9, 21:9 | n/a | yes | no | no | up to 8 reference images | no | no | not published | n/a | n/a | n/a | 1 image | 13 | 0.29 | 0.14 |
| Nano Banana Pro | image | n/a | n/a | n/a | 1k, 2k, 4k | 1:1, 3:2, 2:3, 4:3, 3:4, 4:5, 5:4, 9:16, 16:9, 21:9 | n/a | yes | no | no | up to 14 reference images | no | no | not published | n/a | n/a | n/a | 1 image | 18 | 0.40 | 0.19 |
| OpenAI Hazel | image | n/a | n/a | n/a | not published | 1:1, 3:2, 2:3 | n/a | yes | no | no | up to 16 reference images | no | no | not published | n/a | n/a | n/a | 1 image | 35 | 0.78 | 0.37 |
| Seedream 5.0 Flash | image | n/a | n/a | n/a | 1k, 1.5k, 2k | 1:1, 4:3, 3:4, 16:9, 9:16, 3:2, 2:3, 21:9 | n/a | yes | no | no | up to 10 reference images | no | no | not published | n/a | n/a | n/a | 1 image | 5 | 0.11 | 0.05 |
| Seedream 5.5 | image | n/a | n/a | n/a | 1k, 1.5k, 2k | 1:1, 4:3, 3:4, 16:9, 9:16, 3:2, 2:3, 21:9 | n/a | yes | no | no | up to 10 reference images | no | no | not published | n/a | n/a | n/a | 1 image | 31 | 0.69 | 0.33 |
| Seedream 4.5 | image | n/a | n/a | n/a | not published | 1:1, 4:3, 16:9, 3:2, 21:9, 3:4, 9:16, 2:3 | n/a | yes | no | no | up to 14 reference images | no | no | not published | n/a | n/a | n/a | 1 image | 9 | 0.20 | 0.10 |
| Seedream 5.0 Lite | image | n/a | n/a | n/a | not published | 1:1, 4:3, 3:4, 16:9, 9:16, 21:9 | n/a | yes | no | no | up to 8 reference images | no | no | not published | n/a | n/a | n/a | 1 image | 9 | 0.20 | 0.10 |
| Seedream 5.0 Pro | image | n/a | n/a | n/a | 1k, 1.5k, 2k | 1:1, 4:3, 3:4, 16:9, 9:16, 3:2, 2:3, 21:9 | n/a | yes | no | no | up to 10 reference images | no | no | not published | n/a | n/a | n/a | 1 image | 22 | 0.49 | 0.23 |
| Soul Cast | image | n/a | n/a | n/a | not published | 16:9 | n/a | optional | no | no | no | no | no | not published | n/a | n/a | n/a | 1 image | 2 | 0.04 | 0.02 |
| Soul Cinematic | image | n/a | n/a | n/a | not published | 1:1, 16:9, 9:16, 4:3, 3:4, 3:2, 2:3, 21:9 | n/a | yes | no | no | 1 reference image | no | no | not published | n/a | n/a | n/a | 1 image | 2 | 0.04 | 0.02 |
| Soul Location | image | n/a | n/a | n/a | not published | 1:1, 16:9, 9:16, 4:3, 3:4, 3:2, 2:3, 21:9, 9:21 | n/a | yes | no | no | no | no | no | not published | n/a | n/a | n/a | 1 image | 2 | 0.04 | 0.02 |
Editing, extend and motion control models
These video models have no generation duration and no reference cost in the catalogue, so only their inputs are listed.
| Seedance 2.5 Edit | yes | no | no | up to 30 reference images | 1 video, required | up to 10 audio tracks | not published | no | no | yes, edits 1 uploaded video |
|---|---|---|---|---|---|---|---|---|---|---|
| Kling 3.0 Motion Control | yes | yes, required | no | no | 1 video, required | no | not published | no | yes, 1 character image and 1 motion video | no |
| Kling 3.0 Motion Control Pro | yes | yes, required | no | no | 1 video, required | no | not published | no | yes, 1 character image and 1 motion video | no |
Feature definitions
- Start and end frames
- You upload the first image of the clip, and on some models the last one; the model animates from the first to the last.
- Reference images
- Images of a character, product or style that the model keeps in the clip without using them as the first frame. "Required" means the job does not run without them.
- Video input
- A video you upload for the model to follow, edit or extend. The cell gives the number of videos and, where the catalogue sets one, their length.
- Audio input
- An audio track you upload, which a speaking or singing clip follows. "No" means the model takes no audio track.
- Sound setting
- The AI Studio picker offers a sound setting for the model, on or off or always on. "Not published" means the catalogue has no sound setting for it.
- Video extend
- The model continues an uploaded video, adding seconds after it (forward) or before it (backward).
- Motion control
- The job requires a character image and a motion video; the model moves the character the way the person in the video moves.
- Video edit
- The model changes an uploaded video from a prompt, for example a background or an object, instead of generating a new clip.
How this table is produced
Durations, resolutions, aspect ratios, the sound setting, inputs and features are what the AI Studio picker offers for each model, read from the model catalogue: durations are the range the model's generation job accepts, narrowed by the per-job cost cap. The reference cost is the live AI Studio quote of a 5 s clip at the model's default resolution, sound on when the model has a sound setting and no reference media (the basis of the clip cost table), or of one image at default settings. Dollars convert credits at the $3.99 entry price. The best-plan column uses the Agency rate ($499/mo), the plan with the lowest price per credit. Inputs and features read the catalogue fields only (media roles and counts, required media, media limits, settings, the extension direction setting), never a model name; motion control is a job that requires both a character image and a motion video, and "no" means the field exists and offers nothing. Editing and motion models (video models with no generation duration and no reference cost) are listed apart, with their inputs only. "not published" marks a value the catalogue or the quote does not give; "n/a" a value that does not apply.
Cost of the same clip on every model · Every model's price · Open AI Studio