Can ChatGPT create images?

OpenAI's world-leading chatbot can generate AI images

ChatGPT can generate images for OpenAI's AI art generator DALL-E 3

PC Guide is reader-supported. When you buy through links on our site, we may earn an affiliate commission. Prices subject to change. Read More

Last Updated on

As we see more and more artificial intelligence (AI) tools released on the internet, the popularity of this technology continues to skyrocket. The current AI model in the spotlight is OpenAI’s ChatGPT. Previously an LLM (Large Language Model), it has evolved into a VLM (Visual Language Model) with the upgrade to the computer-vision-enabled GPT-4V model. Does this make ChatGPT an AI image generator, meaning that ChatGPT can create images?

Can ChatGPT create images?

Multimodal AI is becoming one of the most popular phrases in artificial intelligence. Multimodality is the ability of an AI to understand or interpret multiple types of media, such as text, audio, images, and video. By “understand”, we mean that the AI will accept that kind of media as an input. That same AI may be able to output multiple types of media and even translate between them.

At the time of writing, there is a clear winner for each category. ChatGPT for text, ElevenLabs for audio, Midjourney for images, and Runway for video.

However, Sam Altman’s ChatGPT does have strong competition where multimodality is concerned. Microsoft Copilot (formerly Bing Chat) and Google Bard are both making significant progress in their abilities to interpret the content of images and generate their own. As we begin 2024, the AI race is so close that any of the three could overtake the other two without warning.

Can Microsoft Copilot, Google Gemini, and Anthropic Claude make images?

This is to say nothing of Claude, the AI chatbot rival from Anthropic, which excels across several industry-standard LLM benchmarks; Anthropic Claude-2 ranks second only to GPT-4. Google Gemini also beats GPT-4 in several multimodal tasks, with Gemini Ultra scoring 90.04% in MMLU (Massive Multitask Language Understanding), followed by GPT-4 with 87.29%

Text-to-image output is no small feat of an LLM (Large Language Model) and in fact, requires a whole extra AI model working in tandem with the LLM. The natural language GPT-4 model is only capable of text-based output by itself.

Essential AI Tools

Editor’s pick

7-in-1 AI Content Checker – One-click, Seven Checks

7 Market leading AI Content Checkers in ONE click. The only 7-in-1 AI content detector platform in the world. We integrate with leading AI content detectors to give unparalleled confidence that your content appear to be written by a human.
Only $0.00015 per word!

Winston AI detector

Winston AI: The most trusted AI detector. Winston AI is the industry leading AI content detection tool to help check AI content generated with ChatGPT, GPT-4, Bard, Bing Chat, Claude, and many more LLMs.
Only $0.01 per 100 words

Originality AI detector

Originality.AI Is The Most Accurate AI Detection.Across a testing data set of 1200 data samples it achieved an accuracy of 96% while its closest competitor achieved only 35%. Useful Chrome extension. Detects across emails, Google Docs, and websites.
EXCLUSIVE DEAL 10,000 free bonus credits

Jasper AI

On-brand AI content wherever you create. 100,000+ customers creating real content with Jasper. One AI tool, all the best models.
TRY FOR FREE

WordAI

10x Your Content Output With AI. Key features – No duplicate content, full control, in built AI content checker. Free trial available.

How to get ChatGPT to generate images

Yes, ChatGPT can create images as of the “Vision update”, which combined the GPT-4 model with DALL·E 3, forming GPT-4V.

ChatGPT is an AI language model. It works by opening up a question-and-answer style dialogue between you and the bot. The AI model responds to your request by analyzing the data it was trained on – formulating the most appropriate response based on past patterns and trends in human dialogue.

Prior to this AI image model integration, users still found ways for ChatGPT to aid them in generating AI art. For the majority of 2023, a paid subscription to ChatGPT has enabled plugins, including some that themselves could output images. In addition to this, you can ask an AI chatbot to help write prompts for Midjourney, DALL·E 3, Stable Diffusion, or any other AI image generator.

My personal recommendation would be to use Midjourney for AI image creation. However, if you really must use ChatGPT to make images, there is a way. ChatGPT Plus and ChatGPT Enterprise enable plugins for ChatGPT, and those plugins include exactly what you’re looking for.

Can ChatGPT Plus make images?

Yes, ChatGPT Plus and ChatGPT Enterprise can make images. The paid subscription plans for the OpenAI chatbot enable GPT-4V with DALL·E 3.

MixerBox ImageGen is one such plugin and makes use of OpenAI’s own AI art generator, DALL·E 2. Also, try Michelangelo or Argil AI as alternative AI image plugins for ChatGPT.

Can GPT 4 make images? – ChatGPT’s output

Take it from ChatGPT itself (specifically GPT 3.5, which is admittedly outdated).

A ChatGPT generates an image displaying a message about a product on a webpage.
Can ChatGPT create images – Answered by ChatGPT

No, ChatGPT is a text-based model and does not have the capability to create images. It can generate and understand text, answer questions, provide explanations, and perform various language-related tasks, but it does not have the ability to generate visual content like images or graphics.

ChatGPT, about ChatGPT
Can GPT 4 create images - Answered by GPT 3.5
Can GPT 4 create images – Answered by GPT 3.5

As of my last update in September 2021, GPT-4 or any other version of the GPT series developed by OpenAI is primarily focused on generating and understanding text. They do not have the inherent capability to create images. However, there are other AI models and technologies that specialize in generating images, such as generative adversarial networks (GANs) and convolutional neural networks (CNNs). These models can create images based on the patterns and styles they’ve learned from training data.

It’s possible that developments have occurred since my last update, so I recommend checking OpenAI’s official sources for the latest information on their models’ capabilities.

GPT-3.5, about GPT-4

Can ChatGPT draw pictures?

Yes! ChatGPT can draw pictures. Paid users with a ChatGPT Plus or Enterprise subscription can enable DALL·E 3 for GPT-V, which can output images directly within the ChatGPT interface.

Is ChatGPT an AI art generator?

No, ChatGPT is a text-based software, but it does come with an AI art generator built in! A paid subscription to ChatGPT (Plus, Team, or Enterprise) will enable DALL-E 3 for use with the GPT-4 AI model. DALL-E is the AI art generator, but it is controlled with text prompts, in the same way you would normally use ChatGPT for text-based tasks.

Can ChatGPT create images from text?

No, ChatGPT can not create images from text by itself, although it can serve these as responses. ChatGPT does not have any illustration or artistic capabilities coded into it. However, it has been shown that ChatGPT can provide images by interoperation with Stable Diffusion.

However, ChatGPT can be used as a prompt generator for AI art generators. Consider the best AI image generators below!

What are the best AI image generators?

These are AI tools (neural networks trained on visual media) that can output AI-generated images. So it seems that ChatGPT isn’t the best option for AI art generation. But what other options are out there? We have summarized a list of the top AI generators currently on the market. Some are best for abstract art, and others for realistic images. So, save yourself time scouring the web and check out our top picks below.

  • Jasper Art – A popular AI tool that converts a text prompt or textual description to images.
  • DALL-E2 – OpenAI’s image-generating tool, the best quality open-source model, with a steep learning curve.
  • Night cafe – Another popular tool, known for its wider range of features compared to its rivals.
  • Photosonic – An art generator with the option of image generation or image modification.
  • Midjourney – A leading AI art generator, excellent at all art styles and #1 for photorealism.

Conclusion

Unfortunately, ChatGPT cannot directly create images. The model is a conversational bot built to output text responses and not pixel images. However, we have shown you that it is possible to use ChatGPT to generate an AI image, you just need the help of a text-to-image synthesizer.