AI Videoer
Generate text-to-video and image-to-video clips with Kling, Veo, Wan, Seedance and Hailuo in one workspace. Choose a model for your task and review its credit estimate before submitting.
Generation requires enough credits for the selected model. One-time packs and subscriptions are available.
Choose a model for your next clip
Current AI Videoer settings, not a quality ranking. Costs may change; review the generator's estimate before submitting.
| Model | Inputs on AI Videoer | Sound controls | Credit estimate |
|---|---|---|---|
| Veo 3.1 Fast | Text, image or reference images | Native audio; no separate audio switch | 10 per generation |
| Veo 3.1 Quality | Text or image | Native audio; no separate audio switch | 70 per generation |
| Kling 3.0 | Image-to-video | Sound toggle; required for multi-shot | 5s Standard: 50 silent / 75 with sound |
Kling 3.0: Animate an image with shot and sound controls
Start from a reference image, describe its motion, and choose Standard or Professional mode. Enable sound when needed; multi-shot mode requires it. Inspect the output for subject drift and dialogue errors.
15-Second Continuous Videos
Configure a single shot or a multi-shot sequence within the current 15-second total limit.
Optional Sound
Enable Sound and include short dialogue or effects in your prompt. Accurate wording, voice assignment and lip-sync are not guaranteed.
Image References
Use clear reference images to guide a subject. Logos, small text and fine details can still change during generation.
Credits Based on Settings
Mode, sound and duration determine the cost. A 5-second Standard clip currently costs 50 points without sound or 75 with sound.
Veo 3.1: Text, image and native-audio clips
Choose Fast for lower-credit iteration or Quality for another model option. Both accept text and image input; Fast also offers reference-image mode. Neither page exposes a separate audio switch or a 4K export setting.
Landscape and Portrait
Select the aspect ratio supported by your input mode; 9:16 is useful for vertical social clips.
Rich Audio Generation
Describe dialogue, ambience or effects in the prompt. Listen to the result before publishing; speech and synchronization can vary.
Reference Inputs
Use image-to-video for a starting image; select Fast's reference mode when working with multiple reference images.
Compare Credit Costs
Fast currently costs 10 credits per generation and Quality costs 70. Output quality and completion time are not guaranteed.
Wan 2.6: Affordable AI Video Creator with Native Audio Sync
Explore Wan 2.6 for text, image and reference-video workflows. Choose the supported duration and resolution in its generator, and review the result before using it in an ad or a social post.
15s 1080p Video Capabilities
Choose supported duration and resolution settings. Dialogue and scene accuracy can vary between generations.
'Starring' Reference System
Reference-video input can guide a subject; it does not guarantee unchanged appearance or voice across scenes.
Smart Multi-Shot Mode
Describe camera movement and scene changes in the prompt. Review whether the generated clip follows them.
Model-Specific Pricing
Duration and resolution affect credit costs. Check the displayed estimate before submitting a task.
Seedance 2: Multimodal AI Video Creator with Director-Level Control
Explore Seedance's supported reference inputs and output settings. Available controls vary by version; check each generator rather than assuming every model has the same features.
True Multimodal Input
Use the image, video and audio inputs available in the selected version; upload limits are shown in the generator.
Audio-Video Joint Generation
Audio-video generation with controls for reference media, duration, resolution, and sound where supported.
Director-Level Adjustments
Describe camera movement, lighting and action. Prompt instructions guide a result but do not guarantee exact execution.
Output Settings
Choose the resolution and duration supported by the selected model, then check the credit estimate.
Hailuo 2.3: Expressive AI Video Creator for Realistic Micro-Expressions
Explore Hailuo 2.3 for short character and motion studies. Review the available input mode, duration and resolution before generating; results and queue times vary.
Ultra-Realistic Micro-Expressions
Capture ultra-realistic micro-expressions and natural facial performances that sincerely convey real emotion.
Superior Physics Engine
Experience superior visual physics and dynamic motion control tailored for complex character actions.
Fast Generation Mode
Compare the available settings in the Hailuo generator. Completion time depends on the upstream queue and task.
Enhanced Stylization Support
Extensive enhanced stylization support including specialized anime, illustration, and unique art profiles.
AI Videoer: Frequently Asked Questions
Inputs, credits and limits for your first video.
Create your first clip
Choose a model, add your input and review the credit estimate before generating.