How to create free action figure AI images using ChatGPT: Check our step-by-step guide and prompt

Since the release of ChatGPT's new image generation capabilities, the chatbot has been used for many purposes, the most famous one being to create Studio Ghibli-style images using their real life images. Over time, however, social media users realised that there was much more to be done with ChatGPT's new capabilities. While some have used the chatbot for nefarious purposes such as creating fake IDs, others have found that they can also turn their real life pictures into action figures.

If you want to join the viral social media trend with your own action figure-themed images, here's our step-by-step guide.

How to create action figured theme images using ChatGPT?

1) Open ChatGPT app or website

2) Upload your desired image.

3) We tried using ChatGPT to generate two separate action figure themed images with separate prompts. You can decide which image works better for your use case and modify these prompts accordingly.

ChatGPT Action Figure Trend Prompt:

Prompt a) “Create an action figure packaging design in the style of a modern tech-themed toy card, similar to the 'Chain Cartel Action Figure' image. The card should have a sleek, dark blue background with circuit-like patterns and a perforated top edge. In the center, feature a small, stylized action figure using my uploaded image. Above the figure, display the text 'Your Name' in bold yellow letters, below that add 'Your profession' in white colour . On the right side, include three accessory compartments: one with a laptop featuring, one with a classic pen, and one with a phone displaying a simple screen. Use a futuristic, high-tech aesthetic with a focus on clean lines and a professional vibe.”

Prompt b) “Using the photo of me that I will upload, create a realistic action figure of myself in a blister pack, styled like a premium collectible toy. The figure should be posed standing upright. The blister pack should have a red header with the text '[Your Name]' in large white letters, and below it, 'Your profession' in smaller white letters. Add an 'Ages 17+' label in the top right corner of the header. Include accessories in compartments on the right side of the figure: a notebook, a pen, a small camera, and a laptop with a ChatGPT logo on it. The background of the blister pack should be beige. Ensure the action figure retains my facial features and general appearance from the uploaded photo, with a serious expression, and render the image in high detail with photorealistic quality.”

There are a few key details to keep in mind when giving ChatGPT prompts to create images, such as describing the main subject, lighting, perspective, background and atmosphere, along with the art style for that particular image.

Prompt c) “Create a full-body action figure in its original window box packaging, using the likeness of attached images. At the top, display ' [YOUR NAME]' prominently with 'Limited Edition' below. At the bottom, add 'Action Figure'. Use vibrant colors and a retro-modern font. Include [Your choice of accessories] as the only accessories, neatly arranged to the right, proportional to the model, and placed in inset slots with the model. Design in a 3D animation style, resembling a real person with soft lighting and clear layout, like a toy store product. Set the blurred background as a toy store”

Prompt d) “Create an image of me as a real-life action figure. Be specific as possible based on what you know about me. And put multiple interesting things that represent who I am inside the packaging. I've attached an image of me for reference.”

What is ChatGPT's native image generation?

ChatGPT has had the ability to generate images using text prompts for some time, but recently OpenAI unlocked native image generation capabilities in GPT-4o (the underlying model that runs ChatGPT). The new capabilities allow the chatbot to generate images without relying on an external model such as DALL-E 3, resulting in more nuanced and accurate images.

ChatGPT can now also handle between 10-20 different objects in an image, bringing more control and consistency to the images.

Limitations of ChatGPT's new image generator:

While GPT-4o's new image generator is a step up from the previous DALL-E models used by OpenAI, there are still many problems that can occur with it. These include issues with cropping, hallucination (false or misleading information given by the chatbot), high binding issues, accurate graphing, multilingual text rendering, editing accuracy and dense information with small text.