Video generation
Generate videos from text prompts or reference images. All models support text-to-video and image-to-video.Seedance 2
ByteDance’s flagship. Text/image/video editing/extension. 250 credits (preview) / 150 credits (fast).
Kling V3
Best overall model. Flexible 3-15s duration, keyframe control. 150 credits (pro) / 100 credits (standard).
Sora 2
OpenAI’s model. Cinematic quality, video remix. 100-300 credits.
Wan 2.5
Budget-friendly. Good character motion. 60-80 credits.
Minimax
Versatile alternative. 80 credits.
LTX
Cheapest and fastest. Native audio, keyframes. 50 credits.
Grok Imagine Video
xAI model. Native audio, video editing. 100 credits.
Kling Legacy
Previous Kling versions (V2.6, V2.5, V2.1, V2). 100-150 credits.
Image generation
Generate and edit images from text prompts and reference images.Nano Banana (Gemini)
Recommended default. Text-to-image + editing. 5 credits.
Flux
Three tiers: Schnell, Dev, Pro. 5-10 credits.
Phota
Identity-preserving generation with profiles. 9-13 credits.
Grok Imagine Image
Cheapest image model. 3 credits.
Recraft
Design-focused. Icons, logos, brand colors. 10 credits.
Qwen Image
Multi-angle + editing. Bilingual prompts. 8 credits.
Seedream
ByteDance image editing. 10 credits.
Soul
Character generation with 80+ styles. 15 credits.
Lipsync and talking heads
Animate faces and bodies with speech audio.VEED Fabric
Image + audio = talking head. Simplest pipeline. 100 credits.
Sync Lipsync
Apply speech to existing video. Pro + Standard tiers. 50-80 credits.
OmniHuman
Full-body animation from image + audio. 100 credits.
Upscale and enhance
Increase resolution of images and videos.Image Upscale
6 models from Topaz (best) to CCSR (cheapest). 5-15 credits.
Video Upscale
4 models from Topaz to Sima. 15-50 credits.
Speech, music, and transcription
ElevenLabs Speech
Industry-leading TTS. 7 model variants, 21+ voices. 20-25 credits.
Music Generation
AI music from text prompts. 30 credits.
Whisper Transcription
Audio-to-text. fal + Groq variants. 3-10 credits.
Quick reference
Recommended defaults
| Task | Model | Credits |
|---|---|---|
| Image (versatile) | nano-banana-pro | 5 |
| Image (cheapest) | grok-imagine-image | 3 |
| Video (best) | kling-v3 | 150 |
| Video (premium) | seedance-2-preview | 250 |
| Video (budget) | wan-2.5 | 80 |
| Video (cheapest) | ltx-2-19b-distilled | 50 |
| Lipsync (simple) | veed-fabric-1.0 | 100 |
| Lipsync (best) | sync-v2-pro | 80 |
| Speech | eleven_v3 | 25 |
| Music | music_v1 | 30 |
| Transcription | groq-whisper-large-v3-turbo | 3 |
| Image upscale | seedvr | 10 |
| Video upscale | sima-video-upscaler | 15 |