
AI Video Edit by Chat
Describe the campaign style you need, like "turn this into a luxury product ad," and transform ordinary footage into a polished marketing video. No editing skills required.
Our latest releases including brand new features, effects packs, templates & more!

Describe the campaign style you need, like "turn this into a luxury product ad," and transform ordinary footage into a polished marketing video. No editing skills required.

Generate campaign-ready ad visuals from a product photo or a simple description. Unlike typical generative image tools, text remains editable after generation so you can update copy and placement directly while preserving the original design.

Turn simple prompts into powerful edits. Upload your video, describe the changes you want, and let AI instantly transform your footage into a whole new look or style.

Now supporting pet photos! Upload an image of your dog or cat and instantly see them styled in a variety of fun outfits.

Describe a mood, theme, or story, or use your own lyrics, and AI creates original vocals and music in seconds for videos, podcasts, and more.
Transform images into high-motion videos with native audio sync using Happy Horse 1.0.
Generate high-quality videos from text prompts with superior motion quality and multilingual lip sync using Happy Horse 1.0.
Jump back into your workflow faster with the new Recent Tasks tab. Your latest projects and edits are just one click away.
Now supporting Panasonic LUMIX G9 Mark II (RW2) and Nikon Z6III (NEF) RAW formats, enabling smooth import, viewing, and editing of the latest high-quality camera files.
Make more precise edits using reference images. Select an area, add a reference, and let AI realistically replace and blend elements into your scene.
Transform images into videos with superior motion quality and native audio sync, now with expanded model support including Wan 2.7, PixVerse v6, and Happy Horse 1.0.
Transform ideas into high-detail visuals with precise prompt understanding, now powered by Seedream 5.0 Lite.
Now supports Polish for a more localized editing experience.
Choose from multiple AI models, including GPT Image-2, to generate higher-converting ad visuals with text that stays editable after generation.
Choose from multiple AI models, including GPT Image-2, Nano Banana 2, and Seedream 5.0, using a reference image to generate on-brand visuals that match your creative direction and campaign needs.
With Wan 2.7 support, generate smoother, more lifelike motion that helps your ads and social campaigns capture attention and drive engagement.
Move effortlessly between PC and mobile. Access and share your projects anytime, wherever you are.
Apply filters to video and image overlay elements for a unified visual style. Match color, tone, and mood across every layer to create polished, campaign-ready marketing visuals.
Updated to the Gemma 4 AI model for improved on-device AI creation on supported AI PCs.

Remove unwanted people or objects from your footage instantly, even in complex scenes. Keep every moment clean, natural, and distraction-free without disrupting the flow of your video.

Enhance your video quality with AI that understands your footage and applies the right adjustments to improve lighting, color, audio, and more for clean, natural, and polished results.

Get sticker suggestions instantly based on your scene, making it easy to find the perfect visual accents without manual searching.

Turn everyday moments into fun, shareable collages in seconds. Start with templates and let the AI mix and match your photos into polished layouts.

Create realistic try-on visuals and transform them into dynamic, fashion videos for richer content. Launch collections faster, without studio shoots, casting, or editing expertise.

Bring styled product visuals to life with motion. Generate professional videos that highlight products on models in realistic, lifestyle-driven scenes.
Discover a soundtrack in seconds. Describe your idea, and AI instantly recommends music that matches your vision.
Transform concepts into visuals with the latest AI models: Nano Banana 2, Seedream 5.0, and GPT Image 2.
Transform images into cinematic clips with the latest AI models, including Wan 2.7 and Pixverse 6.0.
Transform concepts into animated visuals with the latest AI models, including Wan 2.7, Seedance 2.0, and Pixverse 6.0.
Imported clothing now appears more natural and detailed on your photo, with improved fit, fabric realism, and overall visual quality.
Now supports Kling O3 for smoother motion, richer detail, and more cinematic video generation.
Now supports Nano Banana 2, Kling O3, and GPT Image 2 for improved detail and smarter prompt-based image generation.
Define your preferred color scheme and product placement before generating, so every ad is on-brand and ready to publish without additional adjustments.

Turn your product assets into a ready-to-use marketing video in minutes. Simply define your audience and key message, and AI builds scenes, voiceover, subtitles, and effects to help accelerate your marketing output.

Bring your stories to life with voice cloning now available across AI Storytelling, Talking Avatar, and Text to Speech for truly personal, on-brand narration.
Bring your characters to life with natural, full-body movement and lifelike gestures synced seamlessly with speech. With voice cloning, your avatar can deliver your message in your voice across multiple languages for a more consistent and engaging global presence.
Find the perfect sticker instantly with natural language search. AI understands what you’re looking for and provides the most relevant stickers every time.
Preview transitions with your own footage in real time before applying them, making it easier to choose the effect that fits best.
Create images your way with new AI models: Flux.2 Pro, GPT Image1.5, and Z-Image. Each offers unique strengths in realism, style, and detail.
Generate compelling videos from text using expanded AI models, including Kling 3.
Image to Video now supports Kling 3.
Generate compelling videos from text or images with expanded AI models including Vidu Q3.
Text to Image now supports reference images with certain integrated AI models, giving you greater control over style, composition, and visual direction.
Run wire removal directly on your PC with Intel or AMD CPUs for faster performance and enhanced privacy.
Facial detection now identifies smaller faces more accurately, reducing misidentification and enabling more precise, reliable edits.
Edit faster and more intuitively by selecting objects directly, with no need to activate the Pick Tool first.
Image to Video now supports Kling 3 and Vidu Q3 for enhanced motion quality and creative options.
Access AI Agent from Guided or GenAI Studio for quicker guidance and smoother editing.
Edit HEVC 10-bit 4:2:2 footage with full hardware and software decode support for smoother playback, improved color accuracy, and a more stable editing workflow.
Transform text into story-driven videos with expanded AI model support, including Kling 2.6, Vidu Q2, and Sora-2, all from a single interface.
Image to Video now supports Kling 2.6 and Vidu Q2, enabling smoother motion, clearer subject movement, and more coherent video generation.
Boost video quality with enhanced frame interpolation and super-resolution upscaling for smoother, clearer results.
Now supports Kling 2.6 and Kling O1 models, delivering smoother motion and higher-quality results in Image to Video.
Text to Image now supports Flux.2 Pro, GPT-1.5, Kling O1, and Z-Image models, enabling more accurate, higher-quality images from text prompts.

Virtually try on outfits using images or generated looks and instantly visualize styles. Explore aesthetics, refine your look, and turn fashion ideas into shareable, creative visuals.

Show multiple products with a single virtual model in one workflow, creating immersive visuals that connect with buyers and highlight collections across markets. Experiment with styling and drive confident purchasing at scale.

Apply multiple outfits to one model, or one look across multiple models, in a single workflow, helping shoppers envision every option. With ready-to-use model presets, fashion resellers can launch listings faster, cut costs, and boost conversions.

Generate images from text using leading AI models like Nano Banana, GPT Image, FLUX, and more. Choose the AI model that delivers the exact look, detail, or style you need without leaving your workflow.

Create videos through text-driven storytelling. Define structure and pacing, while AI transforms your direction into an expressive video, complete with AI voiceover.

Access the latest third-party AI models in one centralized hub. Experiment with new AI-powered features as soon as they’re released and stay current as AI models continue to evolve.

Trim long clips into shorter reference clips before generation to target precise gestures, improve accuracy, accelerate processing, and reduce unnecessary compute costs.

Generate images from text using leading AI models like Nano Banana, GPT Image, FLUX, and more. Choose the AI model that delivers the exact look, detail, or style you need without leaving your workflow.

Editing just got more intuitive. Tell Edit by Chat what you want to change, or pick from smart suggestions, then keep refining your photo until it feels right, all in one continuous flow.

Access the latest third-party AI models in one centralized hub. Experiment with new AI-powered features as soon as they’re released and stay current as AI models continue to evolve.

Create realistic try-on images with AI-generated virtual models from flat garment photos. Sellers can showcase consistent, catalog-ready visuals for fast fashion refreshes without coordinating studio shoots or hiring professional models.

Enhanced prompt understanding and product awareness, delivers cleaner, product-forward layouts, on-brand backgrounds, and benefit-led copy.

Integrate stickers, slogans, and callouts across entire image sets at once to maintain consistent branding and reduce editing time to minutes, resulting in unified, eCommerce-ready visuals.

Access to the latest third-party AI partner tools in one centralized hub. Experiment with new AI-powered features as soon as they’re released and stay current as AI tools continue to evolve.

Now with upgraded face detection. Smarter AI analyzes your portrait, auto-centers the subject, and provides cleaner cutouts with balanced composition and smoother skin texture, producing polished, professional headshots with minimal editing.

Showcase accessories and lifestyle products in realistic, on-model settings. Turn standalone items into styled visuals that highlight fit, function, and fashion appeal.
Turn still images into dynamic motion with advanced AI models such as Runway Gen-4 and Sora-2. Pick the model that matches your creative goal directly from a single control in your editing window, and watch your ideas move effortlessly.
Achieve cleaner edges and more precise details, especially around hair, contours, and detailed elements, for a more natural result.
Turn still images into dynamic motion. Pick the AI model that best matches your creative goal directly from a single control in your editing window, and watch your ideas move effortlessly.
Bring out richer colors and deeper contrast with HEVC (H.265) 10-bit 4:2:0 HDR editing. Supports Rec. 2100 HLG/PQ and iPhone HDR images for stunning lifelike results.

Animate a photo by applying motion and lip-sync from a reference clip. Use “Keep Photo Background” to bring portraits or virtual hosts to life, and “Keep Video Background” to replace characters inside a scene for business demos or story-driven clips.

Transform text or images into cinematic clips with upgraded AI generation. Add expressive motion, realistic atmosphere, and mood-matched audio, including optional spoken dialogue, for immersive, film-quality storytelling.

Animate a photo by applying motion and lip-sync from a reference clip. Use “Keep Photo Background” to bring portraits or virtual hosts to life, and “Keep Video Background” to replace characters inside a scene for business demos or story-driven clips.

Create film-like clips from images in seconds. Master Mode generates realistic lighting, motion, and mood with tailored sound for truly cinematic results.

Upgraded facial detection now recognizes more faces, including smaller or angled ones that were previously missed for natural and professional retouching.