logo
RunComfy
  • ComfyUI
  • Trainer
  • Models
  • MCPNew
  • Pricing
  • Seedance 2.5Hot
  • Seedream 5.5New

Workflows by Model

HotMiniMax H3Video with audio from text, images or referencesHotQwen Image 2.1Create images and edit photos with referencesWanVideo from text or images, motion transferFLUXImage generation, editing and character variationsLTXVideo with synced audio from text or imagesQwen Image EditPhoto editing with text and image referencesKrea 2Image creation, style transfer and reference editsZ-ImageFast portraits and concepts from text

Popular & New Workflows

NewMiniMax H3 Character Swap V1.5Swap video characters, keep the original audioNewP-H3-Image Reference EditEdit a photo guided by a reference imageHotMiniMax H3 Image-to-VideoOne image to cinematic video with synced audioHotLTX 2.5 Image-to-VideoOne frame to sharp video with synced audioHotMiniMax H3 Character Swap (SAM3)Swap video characters while following the motionQwen Image 2.1 Multi-Image EditingPrecise scenes from up to 10 reference imagesFLUX Klein Face SwapNatural, lifelike face swapsSeedVR2 Video UpscalerSharp, smooth video upscaling
View More Workflows

Train a Model

NewMOSS-Image BaseImage generation, newly supportedNewFLUX.3 KleinImage generation, newly supportedHotKrea 2The most-trained image modelHotKrea 2 TurboFew-step image generationHotQwen Image 2.1Image generation and editingZ-Image TurboFast portraits and concept imagesMiniMax H3Video with synchronized audio

Train & Deploy

Getting StartedYour first training job with Ostris AI ToolkitDatasetsUpload and manage training datasetsInferenceRun your trained models in a playground or via APIDeploymentsServe your trained models as dedicated endpoints
Train More Models

Image Models

NewGPT Image 2.65% OFF · Detailed text to image, GIF and SVG, up to 4KNewSeedream 5.510% OFF · Text to image up to 2K, with transparent PNGsNewMiniMax H3 Image10% OFF · Text or references to a still up to 4KNewFLUX 3 Image Klein10% OFF · Text or references to a still from 768 to 4KHotSeedream 5.0 Pro20% OFF · Reference edits with multilingual textHotSeedream 4.520% OFF · Photoreal edits with brand consistencyHotWan 2.6 ImageInstruction-based image editingNano Banana Pro77% OFF · Precise 2K to 4K visuals from sketches

Video Models

NewSeedance 2.5 Flash34% OFF · Text, image, or reference to videoNewKling 4.09% OFF · Animate a still into a 3 to 30s clipHotWan 3.0 Prime13% OFF · Fast clips from reference videosHotSeedance 2.535% OFF · Longer, more consistent cinematic videoHotWan 3.0Clips from image, video and audio referencesHotMiniMax H3Animate a first frame into a 5 to 15s clipWan 2.510% OFF · Fluid motion with native audioFLUX 3 MaxClips from text, a still, or keyframes
View More Models

API

Serverless (ComfyUI)Deploy ComfyUI workflows as serverless endpoints.Serverless (LoRA)Deploy LoRAs as serverless endpoints.Model APIRun hosted models on-demand with no deployment.Trainer APITrain, manage, and retrieve LoRAs via API.CLIRun RunComfy models from your terminal.
MODELS
Explore
All Models
LIBRARY
Generations
MODEL APIS
API Docs
API Keys
ACCOUNT
Usage

Wan 2.7 Image to Video: High-Fidelity Motion & Audio Generation on playground and API | RunComfy

wan-ai/wan-2.7/image-to-video

Turn static images into high-definition videos with precise start-end control, built-in audio, and seamless visual consistency. Ideal for product demos, character animation, and fast marketing content creation.

Image format must be JPEG, JPG, PNG, BMP, WEBP.
Image format must be JPEG, JPG, PNG, BMP, WEBP.
Audio format must be WAV, MP3. The duration of this audio must be between 2 and 30 seconds.
Content to avoid in the video.
Enable intelligent prompt rewriting.
Idle
The rate is $0.09 per second for 720p, $0.13 per second for 1080p.

Introduction To Wan 2.7 Image To Video

Developed by Wan AI in collaboration with Together AI, Wan 2.7 Image to Video transforms static images into dynamic, high-definition clips with precise start-end control, built-in audio, and seamless visual consistency. Designed for e-commerce teams, creative agencies, and product marketers, it streamlines content production by turning complex video workflows into a fast, controllable process for continuous iteration. For developers, Wan 2.7 Image to Video on RunComfy can be used both in the browser and via an HTTP API, so you don’t need to host or scale the model yourself.

Ideal for: Product Showcases | Character Animations | Marketing Demo Videos

What makes Wan 2.7 Image to Video stand out#

Wan 2.7 Image to Video is built for turning a single still image, or a defined start and end frame, into a coherent short video with stable subject identity and scene continuity. Image-to-video serves as the mechanism for converting static visual intent into timed motion, allowing users to generate structured movement, transitions, and presentation-ready clips without rebuilding the scene frame by frame. Wan 2.7 Image to Video emphasizes high-definition output, controllable duration, and optional audio attachment for compact production workflows.


Key capabilities:

  • Start-frame generation from one source image with consistent visual structure.
  • Start-to-end control using an end image to guide motion progression.
  • HD output options at 720p and 1080p.
  • Short-form duration control from 2 to 15 seconds.
  • Prompt and negative prompt support for motion and content steering.
  • Optional prompt expansion for clearer instruction interpretation.
  • Seed-based repeatability for more consistent reruns.

Prompting guide for Wan 2.7 Image to Video#

Start Wan 2.7 Image to Video with a clear source image and a prompt that describes motion, camera behavior, subject continuity, and scene mood. If you need directed progression, provide both image_url and end_image_url so Wan 2.7 Image to Video can interpolate toward a defined visual outcome. Keep the prompt focused on visible motion rather than backstory. For product clips, specify rotation, push-in, or lighting change. For character shots, describe pose transition, facial restraint, and background stability. Wan 2.7 Image to Video also supports resolution selection, duration control, optional audio, negative_prompt filtering, prompt expansion, and seed tuning.


  • "Animate the product photo into a slow cinematic turntable shot, soft reflections, clean studio background, steady framing"
  • "Create a 5-second character motion clip from the portrait, subtle head turn, natural blinking, hair moving slightly in the wind"
  • "Use the first and end image to generate a smooth transformation from closed box packaging to opened product presentation"
  • "Animate the food image with a gentle top-down camera drift, steam rising, realistic texture retention, premium ad style"
  • "Generate a short architectural reveal from the exterior still, slow forward dolly, stable lines, realistic sunlight shift"

Pro tips:

  • Describe motion with camera and subject terms: pan, dolly, tilt, rotate, blink, drift, reveal.
  • State what must remain fixed, such as identity, layout, packaging shape, or background geometry.
  • Use end_image_url when precise final framing or pose matters.
  • Keep negative_prompt concise and practical, such as "flicker, warping, extra limbs, unstable background".

Related Playgrounds

sam-3/video-to-video

Empowers precise tracking and seamless object edits across video scenes.

seedance-2.5-flash/image-to-video

Seedance 2.5 Flash animates a start image into a 4-30 second 480p or 720p clip.

wan-3.0/reference-to-video

Wan 3.0 Reference To Video builds clips from image, video, audio refs

kling-2-6/motion-control-standard

AI-driven motion conversion tool enabling precise, stable animation creation

kling-video-o3/standard/video-to-video

Prompt-driven video editing at $0.126 per second of output.

wan-2-6/flash/image-to-video

Craft lifelike video scenes from stills with motion, dialogue sync, and flexible creative control.

Frequently Asked Questions

What is Wan 2.7 Image to Video and what does the image-to-video feature do?

Wan 2.7 Image to Video is an AI-powered model designed to transform static images into short, realistic video clips. The image-to-video function lets users control the beginning and ending frames, add motion dynamics, and even include built-in audio, allowing creators to bring still visuals to life quickly.

How does Wan 2.7 Image to Video improve upon earlier versions for image-to-video generation?

Wan 2.7 Image to Video builds on the 2.6 version by adding first and last-frame control, enhanced identity preservation, improved motion consistency, and support for 9-grid image-to-video inputs. These upgrades ensure more stable animations and smoother transitions, especially for realistic subject movements.

Is Wan 2.7 Image to Video free to use, or does it require credits?

Access to Wan 2.7 Image to Video operates on a credit system through Runcomfy’s AI Model. New users receive free trial credits upon registration, after which additional credits can be spent per image-to-video generation, depending on duration and resolution settings.

What kind of outputs can I expect from Wan 2.7 Image to Video?

Outputs from Wan 2.7 Image to Video are high-definition 1080p video clips with durations ranging from 2 to 15 seconds. Each image-to-video clip can include built-in audio, realistic subject motion, and enhanced visual consistency suited for professional use.

Who should use Wan 2.7 Image to Video and its image-to-video tools?

Wan 2.7 Image to Video is ideal for content creators, marketers, and creative professionals needing to generate quick, high-quality videos from static imagery. The image-to-video features streamline workflows for product demos, storytelling, and avatar-driven content creation.

Can I use multiple reference inputs in Wan 2.7 Image to Video for better image-to-video results?

Yes, Wan 2.7 Image to Video allows up to five reference inputs — including images, video, or audio. This flexibility enhances the image-to-video process by supporting consistent identity, color tone, and voice matching for multi-modal creative projects.

Does Wan 2.7 Image to Video support audio in the image-to-video creation process?

Yes. Wan 2.7 Image to Video includes built-in audio generation capabilities, enabling users to embed realistic background sounds or voices alongside their image-to-video creations. This helps produce cohesive and ready-to-share video content.

What are the main limitations of Wan 2.7 Image to Video when using the image-to-video feature?

While Wan 2.7 Image to Video delivers high-quality results, users should avoid conflicting reference images or overly complex prompts. Image-to-video clips work best with consistent lighting and clear motion direction; excessive edits or mismatched references may cause drift or artifacts.

On what platforms can I access Wan 2.7 Image to Video and its image-to-video tools?

Wan 2.7 Image to Video is accessible through the Runcomfy AI Model on desktop and mobile browsers. The online platform supports smooth operation of image-to-video generation without needing local installations or heavy system requirements.

Follow us
  • LinkedIn
  • Facebook
  • Instagram
  • Twitter
Support
  • Discord
  • Email
  • System Status
  • Affiliate
Video Models
  • Seedance 2.5 Flash Text To Video
  • Seedance 2.5 Flash
  • Seedance 2.5 Flash Reference to Video
  • Wan 3.0
  • MiniMax H3 Fast
  • Wan 2.5
  • View All Models →
Image Models
  • Seedream 5.5
  • Seedream 5.5 Edit
  • Seedream 5.5 Layer Decomposition
  • Wan 2.6 Image to Image
  • Nano Banana Pro
  • Seedream 5.0 Pro
  • View All Models →
Legal
  • Terms of Service
  • Privacy Policy
  • Cookie Policy
RunComfy
Copyright 2026 RunComfy. All Rights Reserved.

RunComfy is the premier ComfyUI platform, offering ComfyUI online environment and services, along with ComfyUI workflows featuring stunning visuals. RunComfy also provides AI Models, enabling artists to harness the latest AI tools to create incredible art.

Wan 2.7 Image To Video Examples

Video thumbnail
Loading...
Video thumbnail
Loading...
Video thumbnail
Loading...
Video thumbnail
Loading...
Video thumbnail
Loading...
Video thumbnail
Loading...