vidgen-i2v
PortraitJPG / PNG
vidgen-i2v
SpokespersonVideo output
E-commerce
Product spokesperson videos
Animate any portrait into a natural talking video. Pass an image URL — receive a production-ready clip. No studio, no shoot.
VidModel API Platform
Video & Image Generation Models. One API.
Access production-ready video and image models — from industry-known names to high-performance specialists — through a single, credit-based API.
Featured
Popular Models
Most popular models across all categories
FeaturedPopular
Popular
Models
Most popular video generation, character, and image AI models across all categories
VIDEO GEN
VidGen
View all modelsSpecialized for human subjects — exceptional body structure and portrait fidelity, complex action scenes, and background audio
VIDEO GEN
VidGen 1.0 Image to Video
Animate images into video with accurate human body structure and natural movement — strong in complex action scenes with background audio support.
VidGen 1.0 Video Extend
Extend VidGen-generated video up to 20 seconds while preserving body structure, character consistency, and scene continuity.
VIDEO GEN
VidGen 1.0 Text to Video
Generate video from text prompts with exceptional human body structure and portrait accuracy — ideal for complex action scenes and audio-rich content.
VIDEO GEN
VIDEO GEN
VidVox
View all modelsFast generation, lifelike realism — talking-character video and 15-second HD output in one API request
VIDEO GEN
VidVox 1.0 Reference to Video
Blend multiple images into a video, replace characters, or change actions in video.
VidVox 1.0 Image to Video
Animate a single portrait image into realistic talking-character video — up to 15s HD per generation, with fast output and lifelike results.
VIDEO GEN
VidVox 1.0 Flash Image to Video
The fastest VidVox variant — generate talking-character video with lifelike realism at significantly reduced generation time.
VIDEO GEN
CHARACTER
AI Character
Create AI characters from text prompts with optional face image references
CHARACTER
FaceSync Character Generator
Generate AI characters with high facial identity preservation — up to 95%+ similarity to the uploaded reference face.
StyleSync Character Generator
Generate AI characters that preserve the reference face's original style and hairstyle with strong face similarity (~85%).
CHARACTER
SkinReal Character Generator
Generate full-body AI character images with natural skin texture — less smoothing for a more realistic, photographic result.
CHARACTER
PortraitLive Character Generator
Generate detailed half-body portrait images with vivid expressions and high facial clarity.
CHARACTER
IMAGE EDIT
Image Edit
Prompt-driven image editing powered by VidGen and VidVox model pipelines
IMAGE EDIT
VidGen Image Edit
Prompt-driven image editing powered by VidGen — best for removing objects or subjects from complex, layered scenes.
VidVox Image Edit
Prompt-driven image editing powered by VidVox — best for preserving fine details and rendering sharp, legible text in the output.
IMAGE EDIT
VidVox Pro Image Edit
The Pro tier of VidVox image editing — enhanced detail rendering, sharper text, and higher-fidelity edits for production-quality output.
IMAGE EDIT
SEEDANCE
Seedance 2.0
Cinematic video generation by ByteDance — image-to-video, text-to-video, and reference-to-video with native audio sync and up to 4K output
SEEDANCE
Seedance 2.0 Image to Video
Animate still images into cinematic video with physics-accurate motion, native audio sync, and up to 4K resolution — powered by ByteDance.
Seedance 2.0 Text to Video
Generate cinematic video from text prompts with automatic camera planning, multimodal reference support, and native audio sync — up to 4K.
SEEDANCE
Seedance 2.0 Reference to Video
Multi-reference video generation with strong character and style consistency — supply images, video clips, and audio to anchor identity across shots.
SEEDANCE
Seedance 2.0 Fast Reference to Video
Speed-optimized Seedance R2V for rapid iteration — same multimodal reference inputs at significantly faster generation time and lower cost.
SEEDANCE
KLING
Kling
Kuaishou's Kling video models — physics-accurate motion, native audio, multi-shot generation, and up to 1080p output across image-to-video and text-to-video modes
KLING
Kling v3-pro Image to Video
Kuaishou's flagship I2V model — up to 15s at 1080p with physics-aware motion, optional start/end frame guidance, and native audio generation.
Kling v3 Image to Video
Cost-effective Kling V3 image-to-video — structural fidelity to the source image, native audio, and up to 15s output at 1080p.
KLING
Kling v3 Text to Video
Physics-accurate text-to-video with multi-shot generation up to 15s, native multilingual audio, and up to 1080p — no source image required.
KLING
Kling v2.5-turbo Image to Video
Speed-optimized Kling I2V for high-throughput pipelines — fast generation, 720p output, 5 or 10s clips, and first/last frame control at reduced cost.
KLING
WAN
Wan
Alibaba's Wan video models — open-source DiT architecture with 86%+ VBench scores, covering image-to-video, text-to-video, reference-to-video, and instruction-based video editing across Wan 2.6 and 2.7
WAN
Wan 2.7 Image to Video
Alibaba's flagship I2V model — up to 15s at 1080p with 9-grid multi-angle input, first+last frame guidance, and physics-accurate motion from a single source image.
Wan 2.7 Text to Video
Alibaba's 2.7 T2V model — up to 15s at 1080p from text prompts with multi-shot storytelling, automatic prompt expansion, and multi-character interaction support.
WAN
Wan 2.7 Reference to Video
Reference-driven video generation accepting up to 5 reference videos — preserves character identity, visual style, and motion patterns across up to 15s of 1080p output.
WAN
Wan 2.7 Edit
Instruction-based video editing — describe the change in plain text and Wan 2.7 Edit modifies the video while preserving the original motion, timing, and temporal structure.
WAN
Wan 2.7 Pro Edit
Professional-tier image editing with instruction-guided precision — 20+ points above standard Wan 2.7 Edit on benchmarks, supporting up to 9 reference images and 12-language prompts.
WAN
Wan 2.6 Image to Video
Proven open-source I2V foundation — up to 15s at 1080p from a single source image, with broad aspect ratio support, optional audio sync, and reproducible generation via seed.
WAN
Wan 2.6 Text to Video
Scene-aware T2V with multi-shot segmentation enabled by default — up to 15s at 1080p from text, with native audio sync and character consistency across narrative cuts.
WAN
Wan 2.6 Reference to Video
Proven reference-to-video foundation — up to 3 reference videos, 5 or 10s output at 1080p, with character identity and visual style preserved across generated clips.
WAN
QuickstartShip in minutes,
Ship in minutes,
not days.
Two endpoints, one API key. POST to create a task, GET to retrieve the result — the same pattern across every model type.
One key, every model
Your API key works across video generation, characters, face swap, and image editing — no separate accounts per provider.
Async task lifecycle
POST to create a task, GET to poll the result. The same two-step pattern works for every model type.
Predictable response shape
Every task returns taskId, taskStatus, and a videoUrl or imageUrls on success. No undocumented fields.
const BASE = "https://api.vidmodel.ai"
const HEADERS = {
"Authorization": `Bearer ${process.env.VIDMODEL_API_KEY}`,
"Content-Type": "application/json",
}
// 1. Create task
const { taskId } = await fetch(
`${BASE}/openapi/v1/aigc/video-generation/tasks`,
{
method: "POST",
headers: HEADERS,
body: JSON.stringify({
model: "vidgen1.0-t2v",
prompt: "A cinematic shot of a girl walking in the rain",
promptEnhance: true,
outputAudio: false,
}),
}
).then((r) => r.json())
// 2. Query result
const { videoUrl } = await fetch(
`${BASE}/openapi/v1/tasks/${taskId}`,
{ headers: HEADERS }
).then((r) => r.json())Use Cases
What teams ship with VidModel
Three production workflows, each handled by a single API call.
vidvox-flash
Text PromptCharacter brief
vidvox-flash
Batch OutputHigh volume
Creator Tools
Personalized content at scale
Generate character video in parallel across thousands of users. Flash mode delivers full throughput without sacrificing visual realism.
vidvox-r2v
References2–4 photos
vidvox-r2v
Character SceneHD video
Marketing
Multi-reference character scenes
Blend subjects from separate photos into one coherent scene. R2V reads all references and synthesizes them into high-fidelity video.
Why choose usOne API for every
One API for every
video and image model
VidModel aggregates the best video and image models — from well-known names to high-performance specialists — under a single API key. No separate contracts, no mismatched task lifecycles.
Curated model selection
Access flagship names and high-performing specialists — all production-tested and available under a single API key, with no separate contracts per provider.
Organized by use case
Models are grouped by what you build — video generation, talking characters, AI personas, image editing, and face swap — not just by vendor name.
Granular output controls
Set resolution, duration, aspect ratio, reference faces, and style per request without managing separate vendor integrations.
Production-grade reliability
Typed responses, consistent output shapes, and usage visibility designed for teams shipping media features at scale.
Platform signals
Ship media features with fewer moving parts.
One API key covers every model type. Teams get a unified task lifecycle, consistent output shapes, and a single billing surface — so the focus stays on building, not integrating.
5media pipelines
20smax video output
1 keyall model types
Customer stories
Teams shipping creative AI features faster
From creator tools to production media pipelines, teams use VidModel to consolidate video generation, character creation, and image editing into a single integration.
"
Switching to VidModel unified our entire media pipeline — video generation, face swap, and character creation now run through a single integration.
AR
Ari Renn
Head of Product · ClipForge
VIDEO PLATFORM
We cut our provider count from four to one. VidGen's human-optimized output is the only video generation model our team needs.
MP
Mina Park
VP Engineering
CREATOR STUDIO
The model catalog makes it easy for non-ML teammates to pick the right pipeline for each content type.
TW
Theo Walsh
Creative Lead
EDTECH APP
Talking character generation and face swap now share one workflow. A feature that used to take months shipped in a week.
LC
Leila Chen
Founder
3.8×faster time to ship
60%less integration work
99.9%API availability
Pricing
Pay per generation. No subscriptions.
Buy credits once, spend them across any model. Every generation shows the exact cost before you run it — no surprises.
FASTEST
VidVox Flash
VidVox's realism at the highest generation speed — built for rapid iteration and high-volume pipelines.
$0.25/ 5s
720p$0.25 / 5s
1080p$0.38 / 5s
PORTRAIT SPECIALIST
VidGen 1.0
Near-perfect human body structure and facial accuracy — the go-to for portrait and character video.
$0.50/ 5s
Audio off$0.50 / 5s
Audio on+$0.10 / 5s
SPEED + REALISM
VidVox 1.0
Fast generation paired with high visual realism — a rare combination across both standard and R2V modes.
$0.50/ 5s
720p$0.50 / 5s
1080p$0.75 / 5s
R2V 720p$0.50 + $0.50 ref
See full pricing →Face Swap, Image Edit & AI Character models — all credit-based, full rates on pricing page
All Models
Browse all video generation, character, image editing, and face swap models in one compact index.
VidGen 1.0 Image to Video
Animate images into video with accurate human body structure and natural movement — strong in complex action scenes with background audio support.
VIDEO GENVidGen 1.0 Video Extend
Extend VidGen-generated video up to 20 seconds while preserving body structure, character consistency, and scene continuity.
VIDEO GENVidGen 1.0 Text to Video
Generate video from text prompts with exceptional human body structure and portrait accuracy — ideal for complex action scenes and audio-rich content.
VIDEO GENVidVox 1.0 Reference to Video
Blend multiple images into a video, replace characters, or change actions in video.
VIDEO GENVidVox 1.0 Image to Video
Animate a single portrait image into realistic talking-character video — up to 15s HD per generation, with fast output and lifelike results.
VIDEO GENVidVox 1.0 Flash Image to Video
The fastest VidVox variant — generate talking-character video with lifelike realism at significantly reduced generation time.
VIDEO GENFaceSync Character Generator
Generate AI characters with high facial identity preservation — up to 95%+ similarity to the uploaded reference face.
CHARACTERStyleSync Character Generator
Generate AI characters that preserve the reference face's original style and hairstyle with strong face similarity (~85%).
CHARACTERSkinReal Character Generator
Generate full-body AI character images with natural skin texture — less smoothing for a more realistic, photographic result.
CHARACTERPortraitLive Character Generator
Generate detailed half-body portrait images with vivid expressions and high facial clarity.
CHARACTERVidGen Image Edit
Prompt-driven image editing powered by VidGen — best for removing objects or subjects from complex, layered scenes.
IMAGE EDITVidVox Image Edit
Prompt-driven image editing powered by VidVox — best for preserving fine details and rendering sharp, legible text in the output.
IMAGE EDITVidVox Pro Image Edit
The Pro tier of VidVox image editing — enhanced detail rendering, sharper text, and higher-fidelity edits for production-quality output.
IMAGE EDITSeedance 2.0 Image to Video
Animate still images into cinematic video with physics-accurate motion, native audio sync, and up to 4K resolution — powered by ByteDance.
SEEDANCESeedance 2.0 Text to Video
Generate cinematic video from text prompts with automatic camera planning, multimodal reference support, and native audio sync — up to 4K.
SEEDANCESeedance 2.0 Reference to Video
Multi-reference video generation with strong character and style consistency — supply images, video clips, and audio to anchor identity across shots.
SEEDANCELoading more…