ModelFoldwan/2-7-text-to-video
Wan 2.7 Video API is Alibaba Tongyi Lab's AI video suite, covering four generation modes — Text-to-Video, Image-to-Video, Reference-to-Video, and Video Edit. It supports full-modality input (text, image, video, audio) and outputs 720P–1080P video. Access all four modes through a single API on ModelFold.
Pricing: From 20 credits / sec at 720p (100 credits for 5 seconds), billed on output seconds. Every resolution is in the rate card below.
Explore more Text to Video models
More AI models from Wan
Latest and popular AI models
Wan 2.7 Video API – T2V, I2V, R2V & Video Edit
Access Wan 2.7's full four-model suite on ModelFold — generate videos from text or images, replicate characters with voice references, and edit existing footage with a single instruction. One API key, all modes.
Wan 2.7 Video API Modes on ModelFold for AI Video Generation
Wan 2.7 T2V – Text to Video API for Instant Video Generation
Turn plain text prompts into 720P–1080P videos in seconds. Wan2.7-T2V supports the "thinking mode" to handle complex scene descriptions with better composition accuracy. Ideal for social content, ads, and rapid prototyping via the Wan 2.7 API. When your Wan 2.7 workflow moves beyond reference-to-video work and requires controlled revisions, continue with Wan 3.0 Video API for video editing.
Wan 2.7 I2V – Image to Video with First & Last Frame Control
Animate one image or a 9-grid multi-image set into fluid video. Wan2.7-I2V lets you specify both the first and last frame, then auto-infers the motion in between — keeping subject identity stable and reducing drift. Flexible duration and multi-angle reference support make it ideal for product showcases and multi-shot narratives via the Wan 2.7 API.
Wan 2.7 R2V – Multi-Reference Video with Voice Clone & Motion Replication
Pass up to five image, video, or audio references into Wan2.7-R2V and it locks appearance, voice tone, lip sync, camera movement, and special effects in a single API call. Even complex, high-motion actions are reproduced stably. It leads the industry in reference count, making it the go-to mode for AI avatars and character-consistent Wan 2.7 AI video at scale.
Wan 2.7 Video Edit – Natural Language Video Editing API
Edit existing videos with a single natural-language instruction. Wan2.7-VideoEdit handles local modifications, style transfer, colorization, and old footage restoration — all through the Wan 2.7 API. No re-generation required; just describe the change and the model executes it.
Key Features of Wan 2.7 Video API on ModelFold
Wan2.7 AI Video High Resolution Output up to 1080P
Wan 2.7 ai video delivers stable output from 720p to 1080p, with extended duration support for richer scenes. Wan 2.7 video api helps build production ready pipelines with consistent quality across different video generation tasks.
Wan 2.7 Video API Start and End Frame Control for Motion Consistency
Wan 2.7 video api supports start and end frame control, enabling predictable motion paths and smoother transitions. Wan 2.7 ai video generation becomes more controllable, improving narrative flow in multi scene video creation.
Wan 2.7 API 9 Grid Image Input for Complex Scene Composition
Wan 2.7 api introduces 9 grid image input to provide multi angle references for scene layout. Wan 2.7 ai video improves composition accuracy and reduces visual drift in complex generation workflows.
Wan2.7 AI Video Subject and Voice Reference for Character Consistency
Wan 2.7 ai video supports subject and voice reference inputs, enabling consistent character appearance, voice tone, and lip sync. Wan 2.7 video api is suitable for storytelling and identity driven video generation.
Wan 2.7 Video API Instruction Based Editing for Fast Iteration
Wan 2.7 video api enables prompt driven editing such as object changes, style updates, and scene adjustments. Wan 2.7 ai video workflows become more efficient, reducing need for full regeneration and speeding up iteration.
How to Use Wan 2.7 Video API on ModelFold
Step 1 Try Wan 2.7 Video API in ModelFold Playground
Start with wan 2.7 video api in ModelFold Playground to test wan2.7 capabilities. Upload image, add prompt, or use reference to preview wan video generation before integrating wan 2.7 ai video into production workflows.
Step 2 Get Wan 2.7 API Key and Review API Documentation
Access wan 2.7 api key from ModelFold console and review documentation. Understand endpoints, authentication, and parameters for wan 2.7 video api to support text to video, image to video, and wan video workflows.
Step 3 Generate Wan 2.7 AI Video and Integrate into Workflow
Use wan 2.7 video api to generate wan 2.7 ai video with prompts, images, or references. Integrate wan2.7 output into product workflows, content pipelines, or AI video tools for scalable video creation.
Wan 2.7 Video API Use Cases You Can Build on ModelFold
Generate Marketing & Product Videos with Wan 2.7 T2V API
Product videos no longer require a production crew. Use the Wan 2.7 T2V API to generate polished ad creatives and demo clips directly from text prompts — or feed in image references via I2V to lock in brand visuals across every output. Multi-angle grid input lets teams iterate on creative directions fast, cutting turnaround from days to minutes.
Scale Social Media Content Using Wan 2.7 AI Video
Short-form platforms demand volume and consistency. With Wan 2.7 AI video generation on ModelFold, content teams can produce lifestyle clips, hook videos, and scene transitions at scale — then use the VideoEdit API to swap backgrounds, shift tone, or localize content for different markets via a single natural-language instruction. One API call replaces hours of post-production.
Film Pre-Production & Storyboarding with Wan 2.7 API
Translate scripts into visual storyboards before a single frame is shot. Wan 2.7 API supports multi-shot narrative sequencing and camera movement control, letting directors and writers preview scenes with real motion — not static sketches. R2V mode keeps character appearance consistent across shots, making it practical for animatics and pitch decks alike.
Video Restoration & Style Transfer via Wan 2.7 Video Edit API
Repurpose archival or low-quality footage without reshooting. The Wan 2.7 VideoEdit API handles black-and-white colorization, degraded footage restoration, and full style transfers — all triggered by plain-language instructions. Studios and archivists can modernize entire video libraries through batch API calls on ModelFold, with the original motion structure preserved throughout.
Why Choose Wan 2.7 Video API on ModelFold
Free Credits and Flexible Plans for Wan 2.7 Video API Users
Wan 2.7 video api on ModelFold offers free credits for new users to test wan 2.7 ai video without upfront cost. Flexible plans and entry level options make wan 2.7 api accessible for different budgets and usage needs.
Affordable Wan 2.7 API Pricing for Scalable Wan AI Video Workflows
Wan 2.7 ai video on ModelFold comes with affordable pricing designed for scaling. Wan 2.7 video api helps reduce cost per generation, making wan2.7 suitable for startups, creators, and production level video workflows.
Wan 2.7 Video API and Wan 2.7-Image API in One Place
ModelFold provides wan 2.7 video api and wan 2.7 image api in one place, simplifying integration and management. Wan 2.7 ai video and image workflows can run together without switching platforms, improving efficiency and consistency.
Frequently Asked Questions
What Is Wan 2.7 Video API?⌄
Wan 2.7 Video API is a suite of AI video generation models released by Alibaba's Tongyi Lab in April 2026. It includes four sub-models — T2V, I2V, R2V, and VideoEdit — covering the full creative pipeline from text-to-video generation to instruction-based editing. On ModelFold, all four modes are accessible via a unified API endpoint.
What Video Generation Modes Does Wan 2.7 API Support?⌄
Wan 2.7 API supports four modes: Text-to-Video (T2V) for prompt-driven generation, Image-to-Video (I2V) for animating static images, Reference-to-Video (R2V) for multi-reference character and voice replication, and VideoEdit for natural-language instruction-based editing of existing footage. Each mode targets a distinct stage of the video production workflow.
What Input Formats Does Wan 2.7 AI Video API Accept?⌄
Wan 2.7 AI video API accepts text prompts, single images, 9-grid multi-image sets, existing video clips (2–10 seconds for VideoEdit), and audio files for voice reference in R2V mode. This full-modality input support — text, image, video, and audio — makes it one of the most flexible video generation APIs available on ModelFold.
What Can Wan 2.7 Video Edit API Do?⌄
Wan 2.7 VideoEdit takes an existing 2–10 second video and edits it based on a natural-language instruction. Supported operations include local element swaps, background changes, style transfer, and black-and-white colorization — all while preserving the original motion structure. No re-generation is required.
What Is the Difference Between Wan 2.7 T2V and I2V?⌄
T2V generates video from a text prompt alone — no image input needed. I2V takes one image or a 9-grid multi-image set as input, with optional first and last frame control so the model auto-infers motion in between. I2V is better suited when visual consistency and subject identity matter more than creative freedom.
How Is Wan 2.7 API Different from Wan 2.6?⌄
Wan 2.7 introduces several capabilities not available in Wan 2.6: first and last frame control, 9-grid multi-image input, up to five simultaneous references in R2V, and the full VideoEdit instruction mode. Overall video quality, temporal consistency, and style range have also been significantly improved.
How to Access Wan 2.7 API on ModelFold?⌄
Wan 2.7 api can be accessed through ModelFold with an API key. Developers can test wan 2.7 video api in playground, review documentation, and integrate wan 2.7 ai video into applications using standard API requests.
For reference-to-video workflows, how does Wan 2.7 Video compare with the newer MiniMax H3 (Hailuo-03)?⌄
The key capability to test is multimodal referencing for more consistent visual guidance from references; try MiniMax H3 (Hailuo-03) on ModelFold for that workflow.
| 720p | 100 credits per 5 seconds |
| 1080p | 150 credits per 5 seconds |
Billed per second. The price above is for a 5-second clip at each resolution — longer clips cost proportionally more, and the Playground charges the exact same way.
curl https://ai.modelfold.online/v1/videos/generations \
-H "Authorization: Bearer $MODELFOLD_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"wan/2-7-text-to-video","prompt":"...","resolution":"720p","duration":5}'