AI models in ClickBait
ClickBait puts video and image models in one workspace. Kling, Seedance, Veo, WAN and MiniMax H3 make clips, while Nano Banana, GPT Image, Seedream and FLUX generate and edit images. The two tables below compare duration, resolution, references and sound for each model. Every version and the common questions live on the model page.
Updated:
Which models make video
| Model | Versions | Duration | Resolution | References | Sound | Price from |
|---|---|---|---|---|---|---|
| Kling | Kling 3.0, Kling 3.0 Omni, Kling Motion Control | 3-15 s; matches the source video | 720p, 1080p, 4K | up to 7 images, up to 1 videos | on/off switch (Kling 3.0, Kling 3.0 Omni); no switch (Kling Motion Control) | from 20 tokens |
| Seedance | Seedance 2, Seedance 2 Fast, Seedance 2 Mini, Seedance 2.5 | 4-30 s | 480p, 720p, 1080p, 4K | up to 30 images, up to 10 videos | on by default | from 12 tokens |
| Veo | Veo 3.1 Fast, Veo 3.1 Lite, Veo 3.1 Quality | 8 s | 720p, 1080p, 4K | up to 1 images | no switch | from 32 tokens |
| WAN | WAN 3.0, WAN 3.0 Prime | 2-30 s | 480p, 720p, 1080p | up to 10 images, up to 5 videos | on by default | from 8 tokens |
| MiniMax H3 | MiniMax H3 | 5-15 s | 768p, 2K | up to 9 images, up to 3 videos | no switch | from 24 tokens |
Which models make images
| Model | Versions | Resolution | References | Aspect ratios | Price from |
|---|---|---|---|---|---|
| Kling | Kling O3 Image, Kling O1 Image | 1K, 2K, 4K | up to 10 images | 1:1, 9:16, 16:9, 21:9, 2:3, 3:2, 3:4, 4:3 | from 2 tokens |
| Nano Banana | Nano Banana 2, Nano Banana Pro, Nano Banana | 1K, 2K, 4K | up to 14 images | 1:1, 9:16, 16:9, 21:9, 2:3, 3:2, 3:4, 4:3, 4:5, 5:4 | from 4 tokens |
| GPT Image | GPT Image 2.5 Flare, GPT Image 2.5 Sunburst, GPT Image 2, GPT Image 1.5, GPT-4o Image | 1K, 2K, 4K, custom size | up to 16 images | 1:1, 9:16, 16:9, 3:4, 4:3, 2:3, 3:2, 4:5, 5:4, 21:9 | from 2 tokens |
| Seedream | Seedream 5.0 Pro, Seedream 5.0 Lite, Seedream 4.5, Seedream 4 | 2K, 4K, custom size | up to 10 images | 1:1, 9:16, 16:9, 3:4, 4:3, 3:2, 2:3, 21:9 | from 3 tokens |
| FLUX | FLUX.2, Flux Kontext | 1K, 2K | up to 8 images | 1:1, 9:16, 16:9, 3:4, 4:3, 3:2, 2:3, 21:9, 9:21 | from 3 tokens |
| WAN | Wan 2.7 Image | up to 4 images | 1:1, 9:16, 16:9, 3:4, 4:3 | from 2 tokens |
Model pages
Kling
video 3-15 s; matches the source video, up to 4K
images up to 4K
up to 10 references
from 2 tokens
Kling Motion Control
video matches the source video, up to 1080p
Seedance
video 4-30 s, up to 4K
from 12 tokens
Veo
video 8 s, up to 4K
from 32 tokens
Nano Banana
images up to 4K
up to 14 references
from 4 tokens
GPT Image
images up to 4K
up to 16 references
from 2 tokens
Seedream
images up to 4K
up to 10 references
from 3 tokens
FLUX
images up to 2K
up to 8 references
from 3 tokens
WAN
video 2-30 s, up to 1080p
up to 4 references
from 2 tokens
MiniMax H3
video 5-15 s, up to 2K
from 24 tokens
Suno
songs up to 8 min, two tracks per run
from 5 tokens
ElevenLabs
text to speech up to 5,000 characters, 19 voices
from 2 tokens
How to pick a model
For long clips look at Seedance 2.5 and WAN 3.0, which render up to 30 seconds in one go. If you want sound straight from the generation, use Kling 3.0 with its audio switch or WAN 3.0, where audio is on from the start. 4K output comes from Kling 3.0, Seedance 2, Veo 3.1 Fast and Veo 3.1 Quality.
For images the deciding factors are usually the number of references and the frame size. GPT Image 2 and 2.5 take up to 16 photos and a custom size, Nano Banana 2 up to 14 photos and 4K. Seedream 4.5 is the default image model in ClickBait, with 2K or 4K output and a custom size as well.
Model comparisons
Frequently asked questions
Which model makes the longest videos?
Seedance 2.5 and WAN 3.0, with up to 30 seconds per run. Kling 3.0 tops out at 15 seconds, and Veo 3.1 always renders 8-second clips.
Which models can generate sound?
Kling 3.0 and Kling 3.0 Omni add audio when you turn the switch on, and WAN 3.0 and WAN 3.0 Prime have audio on by default. The other video models in ClickBait have no audio switch.
Which models make 4K images?
Nano Banana 2 and Nano Banana Pro, GPT Image 2 and both GPT Image 2.5 versions, Kling O3 Image, Seedream 4.5 and Seedream 4. Seedream 5.0 outputs 2K, FLUX.2 1K or 2K.
Can I upload my own photos as references?
Yes. GPT Image 2 and 2.5 accept up to 16 photos, Nano Banana 2 up to 14, Seedream 5.0 Pro and Kling O3 Image up to 10. For video, Seedance 2.5 takes the most: up to 30 images and up to 10 video references.
How do I see the price before I run a model?
Prices are in tokens and depend on the model, duration, resolution and other settings. The total shows on the run button before you start, and the lowest price per model is listed on the pricing page.