AI Video Models

LightricksLTX-2.3 Distilled 1.1

2/1 day included

Modalities: text / image / video / audio → video / audio
Capabilities: Connected multi-scene stories · Keyframes · Multiple subject reference · Inpainting · HDR conversion · Reference video editing · Faster memory-efficient VAE decoding · Smearing-reduced LTX-2.3 sampling
References: Keyframes · multiple subjects · reference sheet
Resolution: 480p · 540p · 720p · 1080p
Duration: 1–20 sec

Fast LTX-2.3 audio-video generation for text, image, video, and audio-conditioned workflows with first/end-frame and keyframe controls.

WanWan 2.2 I2V 14B Fast

2/1 day included

Modalities: text / image → video
Capabilities: Reference-guided first frame · Auto-generated first frame · 4-step inference
Mode: I2V only · auto first frame
Resolution: 480p · 720p · square
Duration: 1–6 sec
References: First frame · image references

Four-step Wan 2.2 14B image-to-video generation with NVFP4 sparse attention for RTX 50-series GPUs. Uses an uploaded first frame or lets you generate and review one from a prompt and optional references.

Soul AISoulX FlashHead (Talking Head)

3/1 day included

Modalities: text / image / audio → video
Capabilities: Talking head · Lip sync · Voice cloning
Quality: Fast · High quality

Real-time talking-head model that animates a face image with speech and accurate lip sync.

PixVersePixVerse V6

Upgrade required

Modalities: text / image → video
Released: Mar 30, 2026
Capabilities: Edit
Keyframes: Up to 2 positioned frames
Resolution: 360p · 540p · 720p · 1080p
Duration: 1–15 sec

Multi-shot cinematic video generation with native audio, 20+ camera controls, and character consistency

MicrosoftTRELLIS.2 4B (3D Generation)

Upgrade required

Modalities: image → 3d
Released: Dec 17, 2025
Formats: GLB

High-fidelity image-to-3D generative model with compact structured latents

MiniMaxMiniMax Hailuo 2.3 Fast

Upgrade required

Modalities: text / image → video
Released: Oct 29, 2025
Formats: MP4 · WEBM · MOV

Fast MiniMax Hailuo 2.3 model for short cinematic video

ByteDanceSeedance 1 Pro Fast

Upgrade required

Modalities: text / image → video
Released: Oct 25, 2025
Resolution: 480p · 720p · 1080p
Duration: 1.2–12 sec
Formats: MP4 · WEBM · MOV

Fast Seedance 1.0 Pro video generation for dance content

Kling AIKling 2.5 Turbo

Upgrade required

Modalities: text / image → video
Released: Oct 23, 2025
Duration: 5s · 10s
Formats: MP4 · WEBM · MOV

Fast cinematic image to video generation for creators

GizAIVideo Upscale & Enhance

Upgrade required

Modalities: video → video
Capabilities: Upscale · Denoise · Deblur
Output: HD · FHD · 2K · 4K
Processing: AI enhancement

Upscale, clean up, sharpen, or resize an existing video with AI or standard processing.

GizAIVideo Interpolate

Upgrade required

Modalities: video → video
Capabilities: Frame interpolation · Motion smoothing
Frame rate: 2x · 3x · 4x
Quality: Fast · Balanced · Quality

Increase video frame rate with frame interpolation.

TME Lyra LabMuseTalk 1.5 (Video Lipsync)

Upgrade required

Modalities: text / video / audio → video
Capabilities: Lip sync · Speech synthesis · Voice cloning
Input: Video + speech

Lip-sync model that retimes mouth motion in an existing video to match a new audio track.

Black Forest LabsFLUX 3 Video

≈ $0.044–0.594/sec

Modalities: text / image / video → video
Released: Aug 4, 2026
Price: ≈ $0.044–0.594/sec
Keyframes: Up to 10 positioned frames
Resolution: 720p · 1080p
Formats: MP4 · WEBM · MOV

Multimodal video generation with native synchronized audio across styles and modes

MiniMaxMiniMax H3

≈ $0.0785–0.153/sec

Modalities: text / image / video / audio → video
Released: Jul 30, 2026
Price: ≈ $0.0785–0.153/sec
Capabilities: Edit
References: Up to 9 images
Keyframes: Up to 2 positioned frames

Multimodal video generation with native synced audio, multi-reference consistency, and continuation workflows

GoogleGemini Omni Flash

$1.65 in · $9.9 out / 1M

Modalities: text / image / video → video
Released: Jun 30, 2026
In / out price: $1.65 in · $9.9 out / 1M
Capabilities: Edit
References: Up to 7 images
Duration: 3–10 sec

Multimodal video generation and editing with native audio, multi-turn control, and photo-to-video references

ByteDanceSeedance 2.0 Mini

≈ $0.0396–0.0891/sec

Modalities: text / image / video / audio → video
Released: Jun 23, 2026
Price: ≈ $0.0396–0.0891/sec
References: Up to 9 images
Keyframes: Up to 2 positioned frames
Resolution: 480p · 720p

Compact Seedance 2.0 variant for faster, lighter multimodal video generation workflows

AlibabaHappyHorse 1.1

≈ $0.115–0.237/sec

Modalities: text / image → video
Released: Jun 22, 2026
Price: ≈ $0.115–0.237/sec
References: Up to 9 images
Resolution: 720p · 1080p
Duration: 3–15 sec

Multimodal video generation with stronger motion expressiveness, multi-image reference consistency, and improved audio-visual sync

Kling AIKling VIDEO 3.0 Turbo

≈ $0.123–0.154/sec

Modalities: text / image → video
Released: Jun 17, 2026
Price: ≈ $0.123–0.154/sec
Resolution: 720p · 1080p
Duration: 3–15 sec
Formats: MP4 · WEBM · MOV

Faster multimodal video generation with stronger prompt adherence, multi-shot consistency, and improved lip sync

Pruna AIP-Video-Replace

≈ $0.033–0.066/sec

Modalities: text / image / video → video
Released: Jun 4, 2026
Price: ≈ $0.033–0.066/sec
Capabilities: Edit
References: Up to 3 images
Resolution: 720p · 1080p

Character replacement for existing video using a reference image while preserving motion, timing, camera, and scene

RunwayRunway Aleph 2.0

≈ $0.308–0.325/sec

Modalities: text / image / video → video
Released: Jun 2, 2026
Price: ≈ $0.308–0.325/sec
Capabilities: Edit
Keyframes: Up to 5 positioned frames
Formats: MP4 · WEBM · MOV

Localized video editing with single-frame guidance, multi-shot consistency, and stronger preservation of the original clip

xAIGrok Imagine Video 1.5

≈ $0.00935–0.286/use

Modalities: text / image / audio → video
Released: May 30, 2026
Price: ≈ $0.00935–0.286/use
References: Up to 7 images
Resolution: 480p · 720p · 1080p
Duration: 1–15 sec

Higher-tier Grok image-to-video generation from a single starting frame with longer durations and stronger output quality

xAIGrok Imagine Video 1.5 Preview

≈ $0.0911–0.285/sec

Modalities: text → video
Released: May 30, 2026
Price: ≈ $0.0911–0.285/sec

Grok Imagine Video 1.5 Preview generates and edits video from text and visual inputs with native motion and scene control.

Pruna AIP-Video-Animate

≈ $0.033–0.066/sec

Modalities: text / image / video → video
Released: May 28, 2026
Price: ≈ $0.033–0.066/sec
Resolution: 720p · 1080p
Formats: MP4 · WEBM · MOV

Reference-image animation driven by the motion, timing, and camera movement of a source video

HeyGenHeyGen Avatar V

≈ $0.11/sec

Modalities: text / audio → video
Released: May 4, 2026
Price: ≈ $0.11/sec
Resolution: 720p · 1080p · 4K
Formats: MP4 · WEBM · MOV

High-fidelity avatar video generation with stronger identity consistency and lip sync

Pruna AIP-Video-Avatar

≈ $0.0275–0.0495/sec

Modalities: text / image / audio → video
Released: Apr 30, 2026
Price: ≈ $0.0275–0.0495/sec
Resolution: 720p · 1080p
Formats: MP4 · WEBM · MOV

High-fidelity talking avatar video generation from a portrait with script or audio control