🖼️
Modalities
Image Upload / Vision
Upload images, screenshots, or photos for the AI to analyze, describe, and understand (Vision capabilities).
Which AI has Image Upload / Vision?
53 of 108 tools in the CanIUse matrix support Image Upload / Vision. Open a tool-by-feature answer for the exact plan and source.
Which AI tools support this?
| Tool | Status | Notes | Link |
|---|---|---|---|
| 🤖 ChatGPT | Yes | — | Try ChatGPT (opens in a new tab) |
| 🧠 Claude | Yes | — | Try Claude (opens in a new tab) |
| ✨ Google Gemini | Yes | — | Try Google Gemini (opens in a new tab) |
| 🐋 DeepSeek | Yes | — | Try DeepSeek (opens in a new tab) |
| 🎨 Midjourney | No | Auto populated | Try Midjourney (opens in a new tab) |
| ✏️ Recraft | Yes | Upload reference images for image-to-image and style matching. | Try Recraft (opens in a new tab) |
| 🖌️ Canva Magic Studio | Yes | Upload images for editing, background removal and Magic Edit. | Try Canva Magic Studio (opens in a new tab) |
| 🔥 Adobe Firefly | Yes | Reference images for structure and style matching. | Try Adobe Firefly (opens in a new tab) |
| 🎥 HeyGen | Yes | Upload a photo or footage to create an avatar. | Try HeyGen (opens in a new tab) |
| 🎬 Runway | Yes | Image-to-video and reference images for style. | Try Runway (opens in a new tab) |
| ⚡ Pika | Yes | Image-to-video from a still frame. | Try Pika (opens in a new tab) |
| 🎙️ ElevenLabs | No | — | Try ElevenLabs (opens in a new tab) |
| 🎧 Descript | Yes | — | Try Descript (opens in a new tab) |
| 🎵 Suno | No | No image input. | Try Suno (opens in a new tab) |
| 🎼 Udio | No | No image input. | Try Udio (opens in a new tab) |
| 🕸️ Graphify | No | No image input. | Try Graphify (opens in a new tab) |
| 📊 Napkin AI | No | No image input. | Try Napkin AI (opens in a new tab) |
| 📐 Eraser | No | No image input. | Try Eraser (opens in a new tab) |
| 💡 Whimsical | No | No image input. | Try Whimsical (opens in a new tab) |
| 📌 Miro AI | Yes | Images can be added to a board and used as context. | Try Miro AI (opens in a new tab) |
| 🔮 Gamma | Yes | — | Try Gamma (opens in a new tab) |
| 📝 Notion AI | No | — | Try Notion AI (opens in a new tab) |
| 📈 Julius AI | Yes | Upload charts and images for interpretation. | Try Julius AI (opens in a new tab) |
| 💻 Cursor | Yes | You can drag an image into chat or paste a screenshot. Agent also reads image files (.png, .jpg, .gif, .webp, .svg) for vision-capable models. | Try Cursor (opens in a new tab) |
| ⚡ v0 | Yes | Auto populated | Try v0 (opens in a new tab) |
| 🐙 GitHub Copilot | Yes | Vision support in chat | Try GitHub Copilot (opens in a new tab) |
| 🏄 Windsurf | Yes | Paste screenshots and mockups into the chat as context. | Try Windsurf (opens in a new tab) |
| 🤖 Microsoft Copilot | Yes | — | Try Microsoft Copilot (opens in a new tab) |
| 🧠 Grok | Yes | — | Try Grok (opens in a new tab) |
| 🔍 Perplexity AI | Partial | Limited support | Try Perplexity AI (opens in a new tab) |
| 🌬️ Mistral AI | Yes | — | Try Mistral AI (opens in a new tab) |
| 🦙 Meta AI | Partial | Limited support | Try Meta AI (opens in a new tab) |
| 🦙 Llama | Yes | Llama 3.2 | Try Llama (opens in a new tab) |
| 🥧 Pi by Inflection | No | — | Try Pi by Inflection (opens in a new tab) |
| 🎯 Cohere | No | — | Try Cohere (opens in a new tab) |
| 🤗 HuggingChat | Yes | With multimodal models | Try HuggingChat (opens in a new tab) |
| ❓ Poe by Quora | Yes | — | Try Poe by Quora (opens in a new tab) |
| 👤 Character.AI | Yes, requires plus plan | — | Try Character.AI (opens in a new tab) |
| ✍️ Jasper | Partial | Limited support | Try Jasper (opens in a new tab) |
| 🖊️ Writesonic | Partial | Limited support | Try Writesonic (opens in a new tab) |
| 📝 Copy.ai | No | Auto populated | Try Copy.ai (opens in a new tab) |
| 📄 Rytr | No | — | Try Rytr (opens in a new tab) |
| 🌍 DeepL | No | Auto populated | Try DeepL (opens in a new tab) |
| 🎨 Krea | Yes | Real-time image-to-image from a sketch or reference. | Try Krea (opens in a new tab) |
| 🖼️ Leonardo.Ai | Yes | Image-to-image, inpainting and reference-guided generation. | Try Leonardo.Ai (opens in a new tab) |
| 📢 AdCreative.ai | Yes | — | Try AdCreative.ai (opens in a new tab) |
| 🎥 Sora | Yes | Generate video from a still image. | Try Sora (opens in a new tab) |
| 👨🎤 Synthesia | No | Auto populated | Try Synthesia (opens in a new tab) |
| 🎙️ Murf AI | Yes | — | Try Murf AI (opens in a new tab) |
| 📹 Fliki | No | — | Try Fliki (opens in a new tab) |
| ✨ Luma Dream Machine | Yes | Image-to-video from a start or end frame. | Try Luma Dream Machine (opens in a new tab) |
| ⚡ Bolt New | No | Auto populated | Try Bolt New (opens in a new tab) |
| 💖 Lovable | Yes | Auto populated | Try Lovable (opens in a new tab) |
| 🔎 You.com | Yes | — | Try You.com (opens in a new tab) |
| ⬆️ HighLevel | No | — | Try HighLevel (opens in a new tab) |
| ⌨️ Claude Code | Yes, requires pro plan | Attached photos in the Claude app are passed into the session as vision context. | Try Claude Code (opens in a new tab) |
| ☄️ Comet | Unknown | Vision on the current page is plausible for an in-browser agent, but Comet help does not spell out image attach. | Try Comet (opens in a new tab) |
| 🎞️ Veo 3 | Yes, requires free plan | Image-to-video is a documented Veo 3.1 input; the Gemini API model card lists text and image in. | Try Veo 3 (opens in a new tab) |
| 🎥 Kling AI | Yes, requires free plan | Image-to-video and start/end-frame-to-video are documented for VIDEO 3.0; Omni adds multi-image and video element reference. | Try Kling AI (opens in a new tab) |
| 📓 NotebookLM | Yes, requires free plan | Help documents Gemini Notebook working across text, graphs, and images, and accepting Google Slides and other visual sources. | Try NotebookLM (opens in a new tab) |
| 🛸 Google Antigravity | Unknown | Vision attach in the agent panel was not confirmed on the product homepage or plans doc. | Try Google Antigravity (opens in a new tab) |
| 🧭 Kiro | Partial | Homepage mentions multimodal inputs and Figma as context. A general image-upload vision API was not separately documented. | Try Kiro (opens in a new tab) |
| ⬛ FLUX | Yes, requires plus plan | FLUX.1 Kontext and Fill/Expand endpoints take images for editing. Hosted API is pay-as-you-go. | Try FLUX (opens in a new tab) |
| 🌀 Stable Diffusion | Yes, requires plus plan | Edit, Control, inpainting, and image-to-image APIs take uploaded images. | Try Stable Diffusion (opens in a new tab) |
| 🔤 Ideogram | Yes, requires free plan | Remix, Edit, Reframe, Replace Background, and character-reference endpoints take an image. | Try Ideogram (opens in a new tab) |
| 🐰 CodeRabbit | Unknown | Designs can feed Coding Plans; a general vision-upload path was not confirmed. | Try CodeRabbit (opens in a new tab) |
| 🧃 Replit | Unknown | Infinite Canvas is a visual design surface. Screenshot/vision upload was not confirmed. | Try Replit (opens in a new tab) |
| 🤝 Aider | Yes, requires free plan | Homepage: add images to the chat for visual context and screenshots. | Try Aider (opens in a new tab) |
| 🚀 Warp | Unknown | Screenshot/vision attach in the agent was not confirmed on the homepage. | Try Warp (opens in a new tab) |
| 🔷 Tabnine | Unknown | Vision attach in IDE chat was not confirmed on the pricing page. | Try Tabnine (opens in a new tab) |
| 📝 Grammarly | No | A writing assistant, not a vision model. | Try Grammarly (opens in a new tab) |
| 🔗 n8n | Unknown | Nodes can fetch files. A first-party vision input was not confirmed. | Try n8n (opens in a new tab) |
| ⚡ Groq | Unknown | Vision on hosted models was not confirmed on the quickstart page. | Try Groq (opens in a new tab) |
| 🔀 OpenRouter | Yes, requires plus plan | Homepage: text, images, videos, and audio through one interface. Vision depends on the routed model. | Try OpenRouter (opens in a new tab) |
| 🤗 Hugging Face | Yes, requires free plan | Hub covers image/video/audio/3D models and Spaces demos. | Try Hugging Face (opens in a new tab) |
| 🎙️ Whisper | No | Speech recognition, not vision. | Try Whisper (opens in a new tab) |
| 🦞 OpenClaw | Yes, requires free plan | Users send photos (e.g. a snake in the yard) and the agent identifies them. Vision depends on the model you attach. | Try OpenClaw (opens in a new tab) |
| 🦦 Otter.ai | No | Meeting transcription, not a vision model. | Try Otter.ai (opens in a new tab) |
| ⚡ Zapier | Unknown | Zaps can move files. A first-party vision model was not on the pricing page. | Try Zapier (opens in a new tab) |
| ✨ Genspark | Unknown | Not confirmed on the public homepage this round. | Try Genspark (opens in a new tab) |
| 🔥 Fireflies.ai | No | Meeting recorder, not a vision model. | Try Fireflies.ai (opens in a new tab) |
| 🌊 Fathom | No | Meeting notes, not vision. | Try Fathom (opens in a new tab) |
| 🖼️ Photoroom | Yes, requires free plan | You upload product photos. Background removal is the core loop. | Try Photoroom (opens in a new tab) |
| 🦜 LangChain | Unknown | Depends on the model you wire. Not a first-party vision SKU. | Try LangChain (opens in a new tab) |
| ♻️ Replicate | Yes, requires plus plan | Many models take reference images (FLUX, Seedream, etc.). You pass files/URLs in the API. | Try Replicate (opens in a new tab) |
| 🤝 Together AI | Unknown | Vision on hosted models was not confirmed on the marketing homepage. | Try Together AI (opens in a new tab) |
| 📐 Linear | Unknown | Issue attachments exist. A vision model on Linear Agent was not on the pricing page. | Try Linear (opens in a new tab) |
| ✅ ClickUp | Unknown | Whiteboards/clips exist. Vision on Brain² was not specified. | Try ClickUp (opens in a new tab) |
| 🌸 Asana | Unknown | Attachments exist. Vision on AI Teammates was not on the homepage. | Try Asana (opens in a new tab) |
| 🔗 Make | Unknown | Homepage timed out this round. File modules likely exist; vision was not confirmed. | Try Make (opens in a new tab) |
| 🎨 Figma | Yes, requires free plan | Place images; AI image editing and Weave tools. Agent can add images/files. | Try Figma (opens in a new tab) |
| ✨ Adobe Express | Yes, requires free plan | You upload photos to edit. That is the editor loop. | Try Adobe Express (opens in a new tab) |
| 🪶 QuillBot | No | Writing assistant, not vision. | Try QuillBot (opens in a new tab) |
| 📝 Wordtune | No | Writing assistant, not vision. | Try Wordtune (opens in a new tab) |
| 📊 Beautiful.ai | Yes, requires plus plan | Add custom images; AI image maker; stock library. | Try Beautiful.ai (opens in a new tab) |
| 📕 Tome | No | No live product at tome.app. | Try Tome (opens in a new tab) |
| 🪨 Amazon Bedrock | Partial | Multimodal models (e.g. Claude on Bedrock) accept images via the Converse API. | Try Amazon Bedrock (opens in a new tab) |
| ☁️ Azure OpenAI Service | Yes, requires plus plan | GPT-4o and later chat models on Azure accept text and images. | Try Azure OpenAI Service (opens in a new tab) |
| 🔺 Vertex AI | Yes, requires plus plan | Gemini multimodal accepts images in the API and console. | Try Vertex AI (opens in a new tab) |
| 🌲 Pinecone | No | Vector database, not a vision chat product. | Try Pinecone (opens in a new tab) |
| 🗣️ D-ID | Yes, requires plus plan | Upload a face photo for talking-photo/video generation. | Try D-ID (opens in a new tab) |
| 🎙️ Deepgram | No | Speech platform, not vision. | Try Deepgram (opens in a new tab) |
| 🎧 AssemblyAI | No | Speech platform, not vision. | Try AssemblyAI (opens in a new tab) |
| 📻 Adobe Podcast | No | Audio enhancement product, not vision. | Try Adobe Podcast (opens in a new tab) |
| 🎵 Stable Audio | No | Audio product, not vision. | Try Stable Audio (opens in a new tab) |
| 🎬 InVideo | Yes, requires plus plan | Upload images for clips and storyboards. | Try InVideo (opens in a new tab) |
| ⌨️ Raycast AI | Partial | Screen capture and file context. General image upload was not separately documented. | Try Raycast AI (opens in a new tab) |
| ⚡ Superhuman | Unknown | Whether AI reads images in mail was not checked. | Try Superhuman (opens in a new tab) |