AI Models

Explore the Best AI Models
Video and Image Generators in One Studio

Browse 96 AI models — 53 for video and 36 for images. See the modes each one runs and its starting price, then open its page to learn more and create.

All AI Models

Every model page on Vidofy AI, the newest first.

NEW Wan 2.7 Create with Wan 2.7, where Wan2.7-Video turns one prompt into a multi-shot storyboard and Wan2.7-Image holds exact colors. Make 1080P clips or 4K Pro stills. Text to Video Image to Video Text to Image +3 Video From 11 credits NEW Recraft V4 Recraft V4 was tuned with designers to balance composition, color and typography as one layout. Write a prompt, pick a ratio and generate design-ready images. Text to Image Image From 18 credits NEW Flux 2 Flux 2 Pro, Flex and Max follow exact hex color codes and render legible typography. Generate on-brand posters, packaging and ad creatives from one prompt. Text to Image Image to Image Image From 11 credits NEW Kokoro 1.0 Kokoro 1.0 packs quality comparable to larger TTS models into 82M open weights. Turn scripts up to 7,000 characters into natural narration with 40 voices. Text to Speech From 9 credits NEW Minimax Speech 2.6 MiniMax Speech 2.6 reads URLs, emails, phone numbers, dates and prices correctly in multiple languages. Paste a raw script and get a natural, human-like voiceover. Text to Speech From 5 credits NEW Nano Banana 2 Lite Use Nano Banana 2 Lite, Google's fastest Nano Banana image model, for legible in-image text and consistent characters—generate or edit images from a prompt. Text to Image Image to Image Image From 7 credits NEW MiniMax Speech 2.8 MiniMax Speech 2.8 voices perform (laughs), (sighs) and (breath) tags exactly where you type them. Turn scripts into voiceovers with real human reactions. Text to Speech From 5 credits NEW Seedream 5.0 Pro Seedream 5.0 Pro builds complex, text-dense infographics with native text in 14 additional languages. Turn a brief into an explainer graphic at 1K or 2K. Text to Image Image to Image Image From 16 credits Gemini AI Gemini AI includes Gemini Nano Banana 2.1, using Gemini 3.6 Flash reasoning for labeled diagrams, multilingual designs and precisely directed visual concepts. Text to Video Image to Video Reference to Video +3 Video From 5 credits Gemini Omni Gemini Omni Flash reasons about what should happen next, drawing on real-world physics, history and science. Create 4–10 s clips up to 4K from text or photos. Text to Video Image to Video Video From 118 credits Qwen3 TTS Qwen3 TTS adapts tone, pace and emotion to what your script means. Create narration and voiceovers in Chinese, English, Japanese, Korean and 6 more languages. Text to Speech From 5 credits Gemini 3.1 Flash TTS Gemini 3.1 Flash TTS lets you steer whispers, laughs and pacing with 200+ inline audio tags. Pick from 30 voices and turn scripts into directed voiceovers. Text to Speech From 5 credits Grok TTS Grok TTS turns tags like [laugh], [sigh] and [breath] into real vocal sounds right where you type them. Pick Eve, Ara, Rex, Sal or Leo and generate a voiceover. Text to Speech From 5 credits ElevenLabs v3 Direct ElevenLabs v3 with audio tags like [whispers], [sighs] and [laughs] and turn your script into an acted, emotional voiceover in 70+ languages. Text to Speech From 5 credits Seedream 5.0 Flash Seedream 5.0 Flash brings native multilingual generation to ByteDance's fast Seedream 5.0 tier: prompt in Arabic, Thai or Japanese and get 2K images, even 21:9. Text to Image Image to Image Image From 6 credits Qwen Image 2.1 Qwen Image 2.1 generates images with a real alpha channel straight from your prompt. Create transparent stickers, logos and lettered posters in 2K. Text to Image Image to Image Image From 9 credits Nano Banana 2.1 Nano Banana 2.1 renders 8:1 panoramas and 1:8 vertical frames at up to 4K, with enhanced text and infographic layouts. Generate banners, posters and ads. Text to Image Image to Image Image From 4 credits PixVerse V6 PixVerse V6 cuts multi-shot video with native audio from one prompt. Set 3–15 seconds, up to 1080p and 2:3 or 3:2 framing, then generate cinematic clips. Text to Video Image to Video Reference to Video +1 Video From 14 credits Grok Imagine 2.0 Grok Imagine 2.0 plans typography and layout like a designer, so posters, infographics and UI mockups keep small text sharp. Render at 2K or phone-tall 9:19.5. Text to Image Image to Image Image From 12 credits Vidu Q4 Vidu Q4 Reference to video turns up to 15 images and 3 voice clips into one clip where characters, scenes and voices stay aligned, in up to 4K with sound. Image to Video Reference to Video Video From 32 credits Wan 3.0 Wan 3.0 turns text, first and last frames, or up to 10 reference images into clips up to 30 seconds long with sound, so one run covers a whole scene. Text to Video Image to Video Reference to Video +1 Video From 30 credits Gemini Omni 1.1 Flash Gemini Omni 1.1 Flash grounds video in physics plus real-world knowledge of history and science. Generate or edit clips from text, photos or video, up to 4K. Text to Video Image to Video Reference to Video +2 Video From 56 credits Kling 4.0 Kling 4.0 generates takes up to 30 seconds long with lip-synced dialogue, legible on-screen text and rich detail in neon or night scenes. Create in 1080P. Text to Video Image to Video Reference to Video +3 Video From 128 credits GPT Image 2.5 Create with GPT Image 2.5 Sunburst, OpenAI's most capable image model for precise detail work, or fast Flare, and get 4K product shots, logos and posters. Text to Image Image to Image Image From 4 credits Seedance 2.5 Seedance 2.5 creates 30-second audio-video stories with directed camera movement and blocking, helping you produce complete scenes in one generation. Text to Video Image to Video Reference to Video +1 Video From 86 credits MiniMax AI Create 1440 MiniMax H3 videos up to 15 seconds with MiniMax AI, then direct complex action, branded scenes, and stylized stories from text alone. Text to Video Image to Video Reference to Video +1 Video From 57 credits MiniMax H3 Generate readable titles and brand-led product videos with MiniMax H3, using 4–15 second 1440 clips in five selectable aspect ratios for polished ads. Text to Video Image to Video Reference to Video +1 Video From 57 credits Grok Imagine 1.5 Direct camera motion, atmosphere, physics, pacing, and sound design to create cinematic ads, pitch concepts, and social stories from a single directed scene. Text to Video Image to Video Text to Image +1 Video From 9 credits Flux 3 Flux 3 generates video with native audio from one prompt and shares one backbone across images and motion, helping creators build coherent audiovisual scenes. Text to Video Image to Video Reference to Video +2 Video From 255 credits HappyHorse AI HappyHorse creates cinematic clips with synchronized audio and reference consistency, helping creators turn clear briefs into usable video faster. Text to Video Image to Video Reference to Video Video From 127 credits HappyHorse 1.1 HappyHorse 1.1 pairs fluid dynamic motion with native audio-video generation, helping you build polished ad concepts and story clips from one prompt. Text to Video Image to Video Reference to Video Video From 127 credits GPT Image 2 Generate dense multilingual text in polished 4K visuals with GPT Image 2, then create posters, infographics, ads, and reference-led image edits. Text to Image Image to Image Image From 4 credits Qwen Image 3 Qwen Image 3 turns up to 4.5K-token briefs into dense newspapers, storyboards, and nested UI visuals—so complex ideas land in one coherent image. Text to Image Image to Image Image From 9 credits Veo 3.1 Lite Create AI videos with Veo 3.1 Lite — Google's cost-effective model with native audio, 1080p output, and text or image input. Generate and compare instantly on Vidofy.ai. Text to Video Video From 53 credits LTX 2.3 Create synchronized audio-video content with LTX 2.3 by Lightricks. Open-weight 22B model generates up to 20-second clips at 4K with LoRA fine-tuning support. Text to Video Image to Video Video From 90 credits Qwen Image 2 Create infographics, posters, and photorealistic images with Qwen Image 2. Native 2048×2048 resolution, accurate bilingual text rendering, and unified generation + editing in one model. Text to Image Image to Image Image From 16 credits Nano Banana 2 Generate stunning 4K images in seconds with Nano Banana 2 on Vidofy. Google's latest AI image model combines Pro-level quality with Flash speed for professional creators. Text to Image Image to Image Image From 8 credits Seedream 5.0 lite Experience Seedream 5.0 Lite on Vidofy - ByteDance's breakthrough image generator with live web retrieval, multi-step reasoning, and 2K/4K output. Transform ideas into reality-aware visuals instantly. Text to Image Image to Image Image From 8 credits Kling Image O3 Generate cinematic 4K images with Kling Image O3 on Vidofy. Features Visual Chain-of-Thought reasoning, multi-reference tagging, and professional-grade character consistency for storytelling and brand assets. Text to Image Image to Image Image From 13 credits Seedance 2.0 Generate physically convincing multi-shot action with synchronized stereo sound—dialogue, effects, and music—for polished ads, stories, and social clips. Text to Video Image to Video Reference to Video +1 Video From 33 credits Kling Image 3.0 Kling Image 3.0 (Kuaishou’s Kling AI 3.0 image model) is built for cinematic-realism stills and supports 2K and 4K ultra-high-definition output for professional visualization and production assets. Text to Image Image to Image Image From 13 credits Kling O3 Create cinematic AI videos with Kling O3 on Vidofy. Native audio sync, multi-shot control up to 6 cuts, 15-second clips, and 4K output. Launched Feb 2026. Text to Video Image to Video Reference to Video +1 Video From 95 credits Kling 3.0 Experience Kling 3.0's breakthrough multimodal video generation: native 4K at 60fps, 15-second durations, synchronized audio in 5 languages, and multi-shot storyboards. Create cinematic AI videos instantly on Vidofy. Text to Video Image to Video Motion Control +1 Video From 68 credits Runway Gen-4 Image Gen-4 Image References keeps one character consistent across new lighting, locations and styles from a single photo. Cast once, reuse it in every new shot. Image to Image Image From 9 credits InfiniteTalk AI Access InfiniteTalk on Vidofy to generate long-form, audio-driven talking videos with sparse-frame video dubbing for stable identity and full-body motion synchronized to your audio. Video Gen-4 Aleph Use Runway Gen-4 Aleph to transform existing footage with prompt-based edits—VFX, relighting, object removal, new angles, and more—now streamlined inside Vidofy. Text to Video Image to Video Video From 225 credits Gen-4 Turbo Generate controllable image-to-video clips with Gen-4 Turbo—optimized for fast iteration, predictable settings, and streamlined creation on Vidofy. Text to Video Image to Video Video From 225 credits Hailuo 02 Use Hailuo 02 on Vidofy to generate cinematic, instruction-faithful AI videos from text or images—built for realistic motion, strong prompt adherence, and creator-friendly control. Text to Video Image to Video Video From 101 credits Hunyuan Image 3.0 Use Hunyuan Image 3.0 on Vidofy to generate high-fidelity images with strong prompt adherence, multimodal reasoning, and multilingual text rendering—without local setup. Text to Image Image to Image Image From 24 credits Vidu Q3 Vidu Q3 generates 16-second videos with native dialogue, effects, and synchronized visuals for cinematic shorts, anime scenes, and narrative ads. Text to Video Image to Video Video From 54 credits Luma Ray 3 Use Luma Ray 3 (officially Ray3) on Vidofy to generate cinematic video with reasoning-driven prompt understanding, native HDR/EXR workflows, and creator-friendly controls—without complex setup. Video Runway Gen 4 Generate controlled, cinematic video clips with Gen 4—built for consistency across subjects, locations, and objects—and run it instantly on Vidofy with a streamlined creator workflow. Text to Video Image to Video Video From 225 credits Runway Gen 4.5 Generate cinematic, physics-aware videos with Gen 4.5 (Runway) using text or image prompts—then compare it to Veo 3.1 and choose the best workflow on Vidofy. Text to Video Image to Video Video From 225 credits Veo 3.1 Veo 3.1 text to video with audio synchronizes dialogue, effects, and ambience in 8-second clips up to 4K for polished short-form scenes. Text to Video Image to Video Reference to Video +1 Video From 53 credits Vidu Q2 Generate short video performances with precise micro-expressions and push-pull camera moves, then shape them into ads, drama concepts, and social clips. Text to Video Image to Video Video From 68 credits Seedance 1.5 Pro Seedance 1.5 Pro creates synchronized video, dialogue, music, and spatial effects in one pass—generate cinematic clips with controlled camera motion. Video Wan 2.5 Use Wan 2.5 to generate short videos from text or a first-frame image—with automatic dubbing or custom audio sync—plus subject-consistent image editing (Wan2.5). Video supports 480P/720P/1080P . Text to Video Image to Video Video From 90 credits Hailuo 2.3 Use Hailuo 2.3 on Vidofy.ai to generate cinematic AI video with strong physics, expressive characters, and built-in camera command control—without complex setup. Text to Video Image to Video Video From 57 credits Ovi AI Ovi AI by Character AI generates 5-10 second videos with native synchronized audio. Twin DiT architecture with physics-accurate motion, lip-sync, and multi-speaker dialogue. Access on Vidofy. Text to Video Image to Video Video From 90 credits Wan 2.6 Generate coherent multi-shot AI videos with synchronized audio using Wan 2.6—plus text-to-video, image-to-video, and reference-to-video—available instantly on Vidofy. Text to Video Image to Video Reference to Video Video From 131 credits Sora 2 Pro Sora 2 Pro pairs OpenAI’s highest-quality video generation with synchronized audio, helping you create polished cinematic and campaign clips. Video Grok AI Grok Imagine Video 1.5 animates a first frame built from text, with lip-synced speech and sound. Explore Grok AI models for dialogue-led creative work. Text to Video Image to Video Text to Image +2 Video From 5 credits Z-Image Generate photorealistic images with strong instruction-following and bilingual (Chinese/English) text rendering using Z-Image—accessible through a streamlined Vidofy.ai workflow. Text to Image Image From 2 credits LTX 2 Distilled Use LTX-2 19B Distilled on Vidofy for free to generate synchronized video + audio from detailed prompts—without installing ComfyUI, managing checkpoints, or tuning workflows manually. Video PixVerse V4.5 Explore Pixverse V4.5, the advanced AI video model for creating cinematic-quality videos from text and images. Featuring over 20 camera controls, multi-image fusion, and 1080p output. Text to Video Image to Video Video From 68 credits Midjourney AI Image Generator Midjourney AI uses V8.2 to create bolder, more sophisticated 2K visuals, with improved personalization for cohesive campaign art and concept work. Image GPT Image 1.5 GPT Image 1.5 by OpenAI delivers 4x faster image generation, precise editing that preserves details, and superior text rendering. Available now on Vidofy.ai with instant access. Text to Image Image to Image Image From 9 credits Seedream AI Generate stunning 4K images in 1.8 seconds with Seedream AI. Free access to ByteDance's advanced text-to-image and editing model on Vidofy – no sign-up required. Text to Image Image to Image Image From 8 credits Kling 2.5 Generate stunning 1080p videos with Kling 2.5 on Vidofy for Free. Advanced AI video model with 30 FPS, superior motion physics, and cinematic camera control. Start creating now. Text to Video Image to Video Video From 63 credits Kling 2.6 Create cinematic AI videos with Kling 2.6 on Vidofy - Free to use. Generate 1080p videos with synchronized audio, dialogue, and sound effects in one click. Native English & Chinese voice support. Text to Video Image to Video Video From 118 credits GPT Image Generate stunning images with GPT Image 1.5 - OpenAI's revolutionary autoregressive model. Free access on Vidofy. 4X faster generation, superior text rendering, and precise editing capabilities. Text to Image Image to Image Image From 9 credits Sora AI Sora AI combines physically grounded motion with synchronized dialogue and effects. Generate text- or image-led clips up to 20 seconds in 1080p. Video Kling O1 Create and edit cinematic videos with Kling O1—the revolutionary unified multimodal AI model. Generate 2K videos with character consistency, natural language editing, and 7-in-1 capabilities. Free on Vidofy. First to Last Frame Video From 158 credits Nano Banana Experience Google's Nano Banana (Gemini 2.5 Flash Image), the revolutionary AI for high-consistency image generation and editing. Try it Free now on Vidofy.ai. Text to Image Image to Image Image From 8 credits Nano Banana Pro Generate stunning 4K visuals with Nano Banana Pro on Vidofy. Experience Google's 'Think-Before-Draw' technology, perfect text rendering, and search-grounded infographics for free. Text to Image Image to Image Image From 15 credits GPT Image 1 Mini Use OpenAI's GPT Image 1 Mini for free on Vidofy. Experience the new standard in cost-efficient, high-quality AI image generation with native multimodal capabilities. Text to Image Image to Image Image From 9 credits PixVerse V4 Create stunning AI videos with PixVerse V4 for free on Vidofy. Generate 1080p videos with integrated audio, 24 FPS, cinematic camera controls, and lightning-fast rendering in seconds. Text to Video Image to Video Video From 68 credits PixVerse V5 Create cinematic AI videos with PixVerse V5 for free on Vidofy. Generate 1080p videos in seconds with enhanced motion quality, superior prompt accuracy, and professional-grade visual effects. Start creating now. Text to Video Image to Video Video From 68 credits PixVerse V5.5 Create stunning multi-shot cinematic videos with PixVerse V5.5 on Vidofy. Features 10-second duration, native audio generation, 1080p support, and advanced physics simulation. Free to start. Text to Video Image to Video Video From 68 credits LTX 2 AI Generate native 4K videos with synchronized audio using LTX 2 for Free on Vidofy. Experience the first AI model to deliver 50 FPS and cinematic fidelity in real-time. Video Sora 2 Sora 2 pairs more accurate physical behavior with synchronized dialogue and effects, helping you create believable action, story beats, and cinematic sound. Video Seedream 4 Generate professional 2K-4K images in 1.8 seconds with Seedream V4 (4.0) on Vidofy. ByteDance's unified text-to-image & editing model with 12B parameters. Try free now. Text to Image Image to Image Image From 11 credits HiDream-I1 AI Generate professional AI images with HiDream-I1 for free on Vidofy. Experience the 17B parameter MoE model that outperforms Flux and SDXL in prompt adherence and photorealism. Text to Image Image to Image Image From 9 credits Qwen AI Qwen AI includes Qwen-Image-3.0-Pro: 10px lettering across 12 languages for detailed layouts. Explore capabilities for posters, storyboards and UI concepts. Text to Image Image to Image Text to Speech Image From 5 credits Imagen 3 Create stunning, photorealistic images with Google's Imagen 3 for free on Vidofy. Experience superior text rendering and lighting without a subscription. Image Dreamina AI Generate stunning videos and images with Dreamina AI. Access ByteDance's powerful 'Jimeng' technology for free on Vidofy. Create 30s clips, anime art, and more instantly. Text to Image Image From 14 credits Imagen 4 Create photorealistic images and sharp typography with Imagen 4. Supports up to 2K resolution, multiple aspect ratios, and integrates into Google's creative ecosystem. Text to Image Image From 9 credits Flux AI Generate stunning images with Flux AI for free on Vidofy. 12B parameter model with 4MP resolution, exceptional text rendering, and photorealistic outputs. No signup required. Text to Image Image to Image Image From 1 credit Stable Diffusion Stable Diffusion AI renders clearer words and follows complex multi-subject prompts. Create posters, concept art, and ads with precise iteration controls. Image Ideogram AI Create stunning images with Ideogram AI for free on Vidofy. Industry-leading text rendering, photorealism, and style control. Access Ideogram 3.0 instantly with no setup required. Text to Image Image From 27 credits Recraft AI Access Recraft AI free on Vidofy. Generate stunning vector graphics, raster images, and brand-consistent designs with precise text rendering and style control. Text to Image Image to Image Image From 18 credits Veo 3 Create stunning AI videos with Veo 3 — Google DeepMind's model with native dialogue, sound effects, and ambient audio baked into every clip. Start generating now. Video Hunyuan AI Generate cinematic-quality videos with Hunyuan AI's 13B parameter model. Free access on Vidofy to create 720p videos with smooth motion and professional results. Text to Image Image to Image Video From 24 credits Wan AI Create stunning AI videos with Wan AI for free on Vidofy. Alibaba's open-source video generator with 1080p output, 15-second duration, and cinematic quality. Start generating now. Text to Video Image to Video Text to Image Video From 11 credits Seedance AI Create cinematic videos with Seedance AI: 4-modality input, native audio-video sync, and multi-shot storytelling. Generate up to 2K video in a single pass. Text to Video Image to Video Video From 21 credits PixVerse AI Generate stunning 4K videos with PixVerse AI for free on Vidofy. Experience the best character consistency and motion control in AI video generation without subscriptions. Text to Video Image to Video First to Last Frame Video From 36 credits
Models FAQ

Questions & Answers

About the AI models, their prices and how to start.

What can I make with these AI models?

Videos and images. Each card lists the modes a model runs, such as Text to Video, Image to Video, Text to Image and Image to Image, and the model's page shows every setting it offers.

How much does a generation cost?

Every model is priced in credits per generation. The price depends on the model and on the settings you choose, such as length and resolution. Each card shows the lowest price, and the generator shows the exact price before you create anything. See the plans.

Do I need a separate account or subscription for each model?

No. One Vidofy AI account and one credit balance work with every model on this page.

Can I try the models for free?

Yes. Every new account gets 20 free credits to try them.

How do I choose the right model?

Start from what you want to make: pick Video or Image above, or search for a mode such as Text to Video. Then open a model's page to read what it does best and see its settings.

How often are new models added?

We add new models as they are released. The newest ones carry a NEW badge in the list above.