130 AI apps for visual creation in 11 categories
A curated list of generative AI applications for creating, editing, and enhancing visual assets: images, videos, 3D models and more.
๐ : nearly unmatched
โญโญโญ : global market leaders
โญโญ : good or very good but not recognized as global market leaders
โญ : value to be ascertained
๐ฟ Foundational models and fine-layer aggregators of such models
| # | Logo | App Name | API | One line description | quality | "nationality" |
|---|---|---|---|---|---|---|
| 1 | ๐จ | Seedream | โ | ByteDanceโs model for creative image generation. | โญโญโญ | ๐จ๐ณ |
| 2 | ๐ฅ | Seedance | โ | ByteDanceโs model for creative video generation. | โญ | ๐จ๐ณ |
| 3 | ๐ฅ | CapCut | ByteDanceโs free video editor | โญโญโญ | ๐จ๐ณ | |
| 3 | ๐จ | Nano Banana | โ | Google's latest image model accessible via Gemini or Flow | ๐ | ๐บ๐ธ |
| 4 | ๐ฅ๐ถ | VEO | โ | Google's latest video model accessible via Gemini or Flow | ๐ | ๐บ๐ธ |
| 5 | ๐จ ๐ฅ ๐ถ | Flow | Google Labs' tool for image and video generation and post processing with Nano Banana and VEO | โญโญโญ | ๐บ๐ธ | |
| 6 | ๐ฅ | Hailuo AI | โ | Text-to-video generator producing short cinematic clips. Integrated in an app with editing capabilities | โญโญโญ | ๐ธ๐ฌ |
| 7 | ๐๐๏ธ | InfinityTalk | โ | AI model for dubbing. Research model integrated in Comfy and others | โญโญโญ | ๐จ๐ณ |
| 8 | ๐จ | Midjourney | Image generation model for concept art and visuals. | โญโญโญ | ๐บ๐ธ | |
| 9 | ๐จ | Reve | โ | image generation with a focus on post editing | โญโญ | ๐บ๐ธ |
| 10 | ๐จ | Stable Diffusion | โ | Stability's flagship model for image generation | โญโญโญ | ๐ฌ๐ง |
| 11 | ๐ฅ | Stable Video Diffusion | Stability's flagship model for video generation | ? | ๐ฌ๐ง | |
| 12 | ๐จ๐ฅ | Dream Studio | Stability's platform for image and video generation | โญโญโญ | ๐ฌ๐ง | |
| 13 | ๐จ | Photon | โ | Luma Labs AI' flagship model for image generation | โญโญโญ | ๐บ๐ธ |
| 14 | ๐ฅ | Ray | โ | Luma Labs AI' flagship model for video generation | โญโญโญ | ๐บ๐ธ |
| 15 | ๐จ๐ฅ | Dream Machine | Luma Labs AI's studio for image and video generation + editing | โญโญโญ | ๐บ๐ธ | |
| 16 | ๐ฅ | Runway | โ | video generation | โญโญโญ | ๐บ๐ธ |
| 17 | ๐จ | ChatGPT image | โ | After Dall.E 3, OpenAI's image generation inside the chat interface | โญโญโญ | ๐บ๐ธ |
| 18 | ๐ฅ ๐ถ | Sora | โ | OpenAI's model for video generation. Includes sound, realistic physics, cameo, etc. | ๐ | ๐บ๐ธ |
| 19 | ๐จ | Firefly | โ | Adobe's model and app for image generation | โญโญโญ | ๐บ๐ธ |
| 20 | ๐จ ๐ฅ ๐ถ | Imagine | โ | X / Grok's model for image and video generation | โญโญโญ | ๐บ๐ธ |
| 21 | ๐ฅ๐ถ | Wan | โ | Alibaba's flagship model for video + audio generation | โญโญโญ | ๐จ๐ณ |
| 22 | ๐จ | Flux | โ | Black Forest Lab's series of models for image generation and transformation | โญโญโญ | ๐ฉ๐ช |
| 23 | ๐ฅ | Vivix | โ | Offers very fast video generation (a few seconds) | โญโญ | ๐บ๐ธ |
| 24 | ๐ฅ | Magi | โ | Sand.ai's flagship model for video generation | โญโญ | ๐จ๐ณ |
| 25 | ๐จ | MAI-Image | โ | Microsoft AI (MAI)'s flagship model for image generation | โญ | ๐บ๐ธ |
| 26 | ๐ฅ๐ถ | MuseSteamer / ็ปๆณ | โ | Baidu's flagship model for video generation | โญโญ | ๐จ๐ณ |
| 27 | ๐จ | Manus | Butterfly Effect's app for agentic AI, including image generation | โญโญ | ๐จ๐ณ | |
| 28 | ๐จ | Emu | A model without an app at the moment, equivalent to Nano Banana. Seems very good at image editing by prompting | โญโญโญ | ๐จ๐ณ |
๐ ๏ธ Specialized tools (post processing...)
| # | Logo | App Name | API | One line description | quality | "nationality" |
|---|---|---|---|---|---|---|
| 1 | ๐ท๐ | Topaz Photo AI | โ | Upscaling, sharpening, noise reduction, etc. | โญโญโญ | ๐บ๐ธ |
| 2 | ๐ฅ | EbSynth | โ | Editing and restyling videos : VFX, retouching, rotoscopy | โญโญ | ๐จ๐ฟ |
| 3 | ๐ฅ | sync.so | โ | Translation of videos with preservation of dubbing | โญโญโญ | ๐บ๐ธ |
| 4 | ๐ท๐ | Clarity AI | โ | Image upscaler | โญโญโญ | ๐บ๐ธ |
| 5 | ๐ท๐ | Magnific AI | โ | Image upscaler and enhancer + generator | โญโญโญ | ๐บ๐ธ |
| 6 | ๐ค | drFonts | Font generator | ? | ? | |
| 7 | ๐จ | AI Palette Generator | Pantone color palette generator | โญโญโญ | ๐บ๐ธ | |
| 8 | ๐ | Mixboard | AI supported moodbard by Google | ? | ๐บ๐ธ | |
| 9 | โ๏ธ๐๏ธ | SketchPro | AI sketching assistant for architecture an design | ? | ๐บ๐ธ | |
| 10 | ๐ | ThumbMagic | Make YouTube thumbnails with AI | ? | ๐น๐ญ | |
| 11 | ๐ค | Ideogram | โ | Specialist of text manipulation in generated visuals. Tries to diversify since Google's image model is good on this dimension | โญโญโญ | ๐จ๐ฆ |
๐๏ธ Focus on art, animation, storytelling
| # | Logo | App Name | API | One line description | quality | "nationality" |
|---|---|---|---|---|---|---|
| 1 | ๐ฅ | Morphic | Generation of video and editing, including for games | โญโญโญ | ๐บ๐ธ | |
| 2 | ๐ฅ | AniSora | Text-to-anime video generator with stylized output. | ? | ๐จ๐ณ | |
| 3 | ๐ฅ | Boba Anime | Text-to-anime video generator with stylized output. | ? | ๐ฌ๐ง | |
| 4 | ๐ฅ | Flick | Focus on the creation of short films | ? | ๐บ๐ธ | |
| 5 | ๐ฅ | Hypernatural | Generation of video with an emphasis on story telling | ? | ๐บ๐ธ |
๐จโ๐ค๐คณ Generation of portraits, selfies, avatars
| # | Logo | App Name | API | One line description | quality | "nationality" |
|---|---|---|---|---|---|---|
| 1 | ๐ ๐จโ๐ค๐ท | Caimera | AI photo studio for fashion and portrait photography. | ? | ๐ฎ๐ณ | |
| 2 | ๐ฉ๐๏ธ๐ฅ | HeyGen | โ | Avatar-driven AI video generator for marketing and training. | โญโญโญ | ๐บ๐ธ |
| 3 | ๐ฉ๐๏ธ๐ฅ | MakeUGC | Generates ready-to-use influencer-style video ads. | ? | ๐ฌ๐ง | |
| 4 | ๐คณ๐ฅ | PhotoAI | Generates selfies and portraits from selfies | โญโญโญ | ๐ณ๐ฑ | |
| 5 | ๐ฉ๐๏ธ๐ฅ | synthesia | Generates a video of avatars and voice from text | โญโญโญ | ๐ฌ๐ง | |
| 6 | ๐ฉ๐๏ธ๐ฅ | Gaga | โ | Sand.ai's flagship model for avatar video generation | โญโญโญ | ๐จ๐ณ |
| 7 | ๐ฉ๐๏ธ๐ฅ | VEED | โ | Video creation and editing platform with a focus on avatars | ? | ๐ฌ๐ง |
| 8 | ๐ฉ๐๏ธ๐ฅ | Character.ai | Avatar creation. A service by character.ai which is an AI-based chatbot / conversational platform | ? | ๐บ๐ธ | |
| 9 | ๐ฉ๐๏ธ๐ฅ | Mirage | Generates ready-to-use influencer-style short videos. | ? | ๐บ๐ธ | |
| 10 | ๐ฉ๐๏ธ๐ฅ | Liminal | Generates ready-to-use influencer-style short videos. | ? | ๐ญ๐ฐ | |
| 11 | ๐ฉ๐๏ธ๐ฅ | Argil.ai | โ | Generates ready-to-use influencer-style short videos. | ? | ๐ซ๐ท |
| 12 | ๐ฉ ๐ฅ๐๏ธ | PixVerse | โ | Text-to-video and image-to-video platform producing short animated clips. | โญโญ | ๐จ๐ณ |
| 13 | ๐ฉ ๐ฅ๐๏ธ | BigVu | โ | Generates ready-to-use influencer-style short videos. | ? | ๐บ๐ธ |
๐ฏ๐ Focus on marketing, design and brand communications
| # | Logo | App Name | API | One line description | quality | "nationality" |
|---|---|---|---|---|---|---|
| 1 | ๐ | Fotographer AI | โ | AI-generated fashion and product photoshoots. | ? | ๐ฏ๐ต |
| 2 | ๐จ | Recraft | โ | Image generation and editing made easy for designers, creatives and teams | ? | ๐บ๐ธ ๐ฌ๐ง |
| 3 | ๐ฅ | SeeLab | โ | Video clip generation for brands. Focus on entreprise. | ? | ๐ซ๐ท |
| 4 | ๐ฅ | Vidu | โ | Text-to-video tool for product marketing presentations | ? | ๐จ๐ณ |
| 5 | ๐ | Fermat | Turning sketches into realistic (3D) renders, for fashion and luxury brands | โญโญ | ๐บ๐ธ | |
| 6 | ๐จ๐ฅ๐ก | StoryFlow | all-in-one app for the visual creation process for designers and marketers | ? | ๐ฌ๐ง | |
| 7 | ๐ฅ๐คณ๐ฆ | arcads | โ | creating social media ads with AI actors, such as unboxing videos | ? | ๐ซ๐ท |
| 8 | ๐ | AIO | AI co-pilot for faster, smarter fashion design and production | ? | ๐บ๐ธ | |
| 9 | ๐จ๐ฅ๐ก | Kapwing | all-in-one app for the visual creation process for designers and marketers | ? | ๐บ๐ธ | |
| 10 | ๐จ๐ฅ๐ก | Qlip | make social media ready videos | ? | ๐ซ๐ท | |
| 11 | ๐จ๐ฅ๐ก | Lovart | Generation of images and videos with an emphasis on design | ? | ๐บ๐ธ |
๐ง 3D model creation
| # | Logo | App Name | API | One line description | quality | "nationality" |
|---|---|---|---|---|---|---|
| 1 | ๐ชโ๏ธ | Hyper3D (Rodin) | โ | Turns 2D images into editable 3D objects | โญโญโญ | ๐จ๐ณ |
| 2 | ๐ฅ | Kinetix | No-code motion capture: 3D-Conditioned AI Video Model | โญโญโญ | ๐ซ๐ท | |
| 3 | ๐จ | Omi 3.0 | virtual photo studio: turn photo shoots into 3D visuals, especially for advertising | ? | ๐ซ๐ท | |
| 4 | ๐ง๐น๏ธ | Scenario | AI pipeline for consistent game assets, characters, and 3D-ready textures. | โญโญโญ | ๐บ๐ธ | |
| 5 | ๐จ | Spline | โ | Browser-based tool for designing and publishing 3D assets and worlds, with AI generation services | โญโญโญ | ๐บ๐ธ |
| 6 | ๐ฅ | Krea | Real-time AI tool for images, videos, and text-to-3D workflows. | โญโญ | ๐บ๐ธ | |
| 7 | ๐ฅ | Hunyuan | โ | Raw model to turn 2D images into 3D assets | โญโญ | ๐จ๐ณ |
| 8 | ๐ชโ๏ธ | Meshy | โ | Creation of 3D assets | โญโญโญ | ๐บ๐ธ |
| 9 | ๐ชโ๏ธ | Stable 3D | โ | Stability's flagship model for 3D generation | ? | ๐ฌ๐ง |
| 10 | ๐ฅ๐ง | Simulon | VFX studio on iPhone to integrate / mix 3D models in videos. Blender plugin available. | ? | ๐ฟ๐ฆ | |
| 11 | ๐จ๐ง | SAM 3D | Meta's model to create 3D scenes from pictures (2D objects) | โญโญโญ | ๐บ๐ธ |
๐ฆพ All in one visual creation tooling suites ( ๐ฎโ๐จ crowded space!)
| # | Logo | App Name | API | One line description | quality | "nationality" |
|---|---|---|---|---|---|---|
| 1 | ๐จ | Dzine | AI design platform for generating and editing images | ? | ๐บ๐ธ | |
| 2 | ๐จ | Freepik AI Suite | โ | Aggregates AI models to images with just a prompt or an image reference. | ? | ๐ช๐ธ |
| 3 | ๐ค | Glif | โ | Collaborative platform where agents for visual generation can be created and shared. | ? | ๐บ๐ธ |
| 4 | ๐ฅ | Pippit | Video and image generation with a veneer of broader services (asset management, "analytics"...). By the creators of CapCut. | ? | ๐จ๐ณ | |
| 5 | ๐จ | FLORA (FloraFauna) | AI creative suite for images, motion, and storytelling. | ? | ๐บ๐ธ | |
| 6 | ๐จ๐ฅ๐๏ธ | Comfy | โ | AI creative suite for images, motion, and storytelling. | ๐ | ๐บ๐ธ |
| 7 | ๐จ๐ฅ๐๏ธ | Kling AI | โ | AI video generator capable of realistic motion synthesis. | โญโญโญ | ๐จ๐ณ |
| 8 | ๐จ๐ฅ | Seedance | AI Art (image/video) generator. Not related to Bytedance's "seedance", it seems. | โญ | ๐จ๐ณ | |
| 9 | ๐จ๐ฅ | Awen | single space to create and edit content across text, images, video, and 3D. | โญโญ | ๐ซ๐ท | |
| 10 | ๐จ๐ฅ | Higgsfield | model aggregator for image and video generation and edition, with a focus on building a social community. | โญโญ | ๐บ๐ธ | |
| 11 | ๐จ๐ฅ | LTX Studio | professional video production tooling suite | โญโญโญ | ๐ฎ๐ฑ | |
| 12 | ๐จ๐ฅ | Adobe Suite | since Sept 2025, Adobe Illustrator integrates Google's flagship model for image generation | โญโญโญ | ๐บ๐ธ | |
| 13 | ๐จ๐ฅ | Leonardo.ai | โ | studio for image and video generation and post processing | โญโญโญ | ๐ฆ๐บ |
| 14 | ๐จ๐ฅ | imagine.art | studio for image and video generation and post processing | โญ | ๐บ๐ธ | |
| 15 | ๐จ๐ฅ | letz.ai | โ | studio for image and video generation and post processing | ? | ๐ฑ๐บ |
| 16 | ๐จ๐ฅ | Hedra | studio for image and video generation | ? | ๐บ๐ธ | |
| 17 | ๐จ๐ฅ | Skyreels | studio for image and video generation | โญโญ | ๐จ๐ณ | |
| 18 | ๐จ๐ฅ | Video Ocean | studio for image and video generation | ? | ๐ธ๐ฌ | |
| 19 | ๐จ๐ฅ | Weavy | Nodal workflow for visual creation | ๐ | ๐ฎ๐ฑ | |
| 20 | ๐จ๐ฅ | Genspark | A "do everything with AI" app | โญโญโญ | ๐บ๐ธ | |
| 21 | ๐จ๐ฅ | invideo | video generation and editing | ? | ๐ฎ๐ณ | |
| 22 | ๐ฅ | Velvet | video generation and editing | ? | ๐บ๐ธ | |
| 23 | ๐ฅ | Wondercraft | โ | video generation and editing | ? | ๐ฌ๐ง |
| 24 | ๐ฅ | mosaic | video editing with nodal UI | โญโญโญ | ๐บ๐ธ | |
| 25 | ๐จ๐ฅ | submagic | video and image editing | ? | ๐ซ๐ท | |
| 26 | ๐จ๐ฅ | filmora | video and image editing | ? | ๐จ๐ณ | |
| 27 | ๐จ๐ฅ | flexclip | studio for image and video generation | ? | ๐จ๐ณ | |
| 28 | ๐จ๐ฅ | artlist | studio for image and video generation | ? | ๐ฎ๐ฑ | |
| 29 | ๐จ๐ฅ | flixier | studio for image and video generation | ? | ๐ท๐ด |
๐คธ end to end creation of web applications and documents
| # | Logo | App Name | API | One line description | quality | "nationality" |
|---|---|---|---|---|---|---|
| 1 | ๐ป ๐ฑ | Orchids | Automation of web interface design by prompting | โญโญโญ | ๐บ๐ธ | |
| 2 | ๐บ | Gamma | โ | Generation of documents: office docs, web pages... | โญโญโญ | ๐บ๐ธ |
| 3 | ๐ | MyLens | โ | Generation of infographics, flowcharts ... | โญโญ | ๐บ๐ธ |
| 4 | ๐ป ๐ฑ | Lovable | Automation of web app creation: front and back | โญโญโญ | ๐ธ๐ช | |
| 5 | ๐ป ๐ฑ | Create Anything | Automation of web app creation: front and back | โญโญโญ | ๐บ๐ธ | |
| 6 | ๐ป ๐ฑ | v0 | Automation of web app creation: front and back | โญโญโญ | ๐บ๐ธ | |
| 7 | ๐ป ๐ฑ | MagicPath | Ideation and prototyping of web interfaces | โญโญ | ๐บ๐ธ | |
| 8 | ๐ป ๐ฑ | JustCopy.ai | Natural language to full-stack application | ? | ๐บ๐ธ | |
| 9 | ๐ป ๐ฑ | vibecode | The app that builds apps. Create native apps in seconds with AI | โญโญโญ | ๐บ๐ธ |
___
๐๏ธ visual intelligence
| # | Logo | App Name | API | One line description | quality | "nationality" |
|---|---|---|---|---|---|---|
| 1 | ๐จ๐ฅ | Moondream | โ | Computer vision: make images and video searchable, tag images, enable robot understanding of their surroundings, perform UI testing etc. | โญโญโญ | ๐บ๐ธ |
๐ฉโ๐ป platforms for developers
| # | Logo | App Name | API | One line description | quality | "nationality" |
|---|---|---|---|---|---|---|
| 1 | ๐จ๐ฅ | fal | โ | Generative media platform for devs ("like Huggingface but specializing in models for visual creation") | โญโญโญ | ๐บ๐ธ |
| 2 | ๐จ๐ฅ | HuggingFace | โ | Catalogue of models for visual creation (among others) | โญโญโญ | ๐บ๐ธ |
๐ซข Value or function is not super clear - or not really launched
| # | Logo | App Name | API | One line description | quality | "nationality" |
|---|---|---|---|---|---|---|
| 1 | ๐จ | DreamEngine.ai | Image generation | ๐คจ | ๐บ๐ธ | |
| 2 | ๐ฅ | DreamEngine.app | Video and image generation | ๐คจ | ๐บ๐ธ | |
| 3 | ๐ท | FotoFluid | Minimalist UI, no clear documentation | ๐คจ | ๐ฎ๐ณ | |
| 4 | ๐ฅ | FinalFrame | Generates cinematic frames & visual storyboards. | ๐คจ | ๐บ๐ธ | |
| 5 | ๐ฅ | SkyReels | AI generator for short social media videos. | ๐คจ | ๐ธ๐ฌ | |
| 6 | ๐ฅ๐ | World Labs | spatial intelligence company building Large World Models to perceive, generate, and interact with the 3D world. In closed beta. | โญโญโญ | ๐บ๐ธ | |
| 7 | ๐ฅ | Pika | Mobile first : transform a picture, to a new picture or a video. Not perfect but focuses on ease of use. For art / hobby / communication | โญโญ | ๐บ๐ธ | |
| 8 | ๐ฅ๐ | Moonlake | โ | 2D and 3D worlds generator | ? | ๐บ๐ธ |
| 9 | ๐ฅ๐ | Genie | Google's 3D worlds generator. In preview. | ? | ๐บ๐ธ | |
| 10 | ๐ฅ๐๐น๏ธ | Odissey | AI video you can play like a game. In private beta. | ? | ๐บ๐ธ |
๐ Special thanks!
The curation of this list benefits from my reading of the news and updates posted by:
- Rรฉmi Rostan: check out "lhc"!
- Gilles Guerraz and Caroline Thireau: check out their "Generative" newsletter on substack
(a missing app or correction? send your comments just below or at clementlevallois[at]protonmail dot com)