# I Tested ChatGPT’s New Image Model Source: https://www.youtube.com/watch?v=jFJAIOAzFqQ Recap page: https://rapidrecap.app/video/jFJAIOAzFqQ Generated: 2025-12-16T21:32:12.123+00:00 --- ## Quick Overview OpenAI has launched a new version of ChatGPT Images (GPT-4o) featuring improved image editing capabilities, including precise edits, stylistic filters, and conceptual transformations, which the presenter found to be very effective, especially in handling complex prompts like creating a specific style of drawing or making detailed changes to an uploaded image. **Key Points:** - The new ChatGPT Images model (GPT-4o) offers up to 4x faster image generation and improved editing features compared to the previous version. - The model excels at precise edits, maintaining original image elements while applying changes like lighting, composition, and clothing/hairstyle try-ons. - The presenter successfully tested creative transformations, such as turning a photo into an ultra-detailed 3D graphite pencil sketch of Sam Altman, which exceeded expectations (1:14). - The model demonstrated strong instruction following, accurately creating a 6x6 grid of emojis based on a detailed written prompt, unlike the previous version which struggled with object placement (11:57). - The tool can perform complex edits, such as removing a hand and a notebook from a drawing and replacing them with a single piece of paper, though the presenter noted some AI artifacts (4:46). - The image generation for a custom YouTube tech YouTuber bobblehead, including specific accessories, was highly impressive and well-executed (10:17). - The presenter anticipates that this improved image model will significantly streamline content creation for social media and other business needs (7:15). ![Screenshot at 1:14: The presenter demonstrates the new image model's ability to apply a specific stylistic transformation, successfully rendering Sam Altman as a detailed, cuddly plush toy based on a detailed prompt.](https://ss.rapidrecap.app/screens/jFJAIOAzFqQ/00-01-14.png) **Context:** The video reviews the new image generation capabilities released by OpenAI for ChatGPT, powered by the GPT-4o model update. The presenter tests the new features, focusing on image editing, creative transformations using preset styles, and instruction following when generating images from uploaded photos or text prompts, comparing the new results against the prior model's performance. ## Detailed Analysis The video provides a hands-on review of the newly launched ChatGPT Images model (GPT-4o), highlighting its superior speed (up to 4x faster) and enhanced editing features. The presenter demonstrates its ability to perform precise edits on uploaded photos, such as changing outfits or applying stylistic filters while preserving critical details. A key test involved transforming a photo of the presenter into a 'Sam Altman plush toy portrait' using a detailed prompt, which yielded an impressive result that surpassed expectations (1:14). The review also covers improved instruction following, showcasing a comparison where the new model accurately generates a complex 6x6 emoji grid based on written row-by-row instructions, whereas the previous model failed to correctly place items (11:57). Furthermore, the presenter tested object removal and replacement on a pencil sketch, successfully removing a hand and notebook and replacing them with a blank piece of paper, although some minor artifacts were present (4:46). The model also successfully created a custom 'YouTube YouTuber bobblehead with accessories' based on an uploaded photo, demonstrating strong contextual understanding (10:17). The presenter concludes that the enhanced capabilities, especially in iterative editing and complex prompt adherence, make the new tool highly valuable for content creators. ### Initial Launch Overview - OpenAI released a new version of ChatGPT Images powered by GPT-4o - Features include up to 4x faster generation, precise edits, stylistic filters, and conceptual transformations - New images model is rolling out to all users and via API (0:01, 10:57) ### Precise Edits & Stylistic Transformations - Model adheres better to intent on uploaded images, handling lighting, composition, and appearance changes reliably - Examples include transforming a selfie into an anime-style image (0:04) and a plush toy (1:14) - The plush toy transformation of Sam Altman was highly successful (1:14) ### Instruction Following - New model follows complex instructions more reliably than the initial version - Comparison shows new model correctly generating a 6x6 emoji grid based on row/column prompts, while the previous model failed (11:57) ### Creative Transformations - Model excels at changing elements like text and layout while preserving important details - Example shows transforming a movie poster image, changing actors' names from Wojciech Zaremba and Greg Brockman to others (11:40) ### Text Rendering - Model takes another step in text rendering, handling denser and smaller text better - Example shows correctly rendering a dense, multi-section document titled 'Introducing GPT-5.2' (12:30) ![Screenshot at 0:01: The introduction slide highlighting the launch of the new ChatGPT image model with the logo and the word 'OpenAI'.](https://ss.rapidrecap.app/screens/jFJAIOAzFqQ/00-00-01.png) ![Screenshot at 1:14: Demonstration of the 'Plushie' style transformation applied to an image of Sam Altman, resulting in a highly detailed, cute stuffed toy version.](https://ss.rapidrecap.app/screens/jFJAIOAzFqQ/00-01-14.png) ![Screenshot at 4:32: The output of the 'Sketch' style applied to an image of the presenter holding a martini, which still includes the hand and notebook, prompting further refinement \(4:46\).](https://ss.rapidrecap.app/screens/jFJAIOAzFqQ/00-04-32.png) ![Screenshot at 11:57: Side-by-side comparison showing the new model accurately rendering a 6x6 grid based on complex instructions, while the previous version failed to place elements correctly.](https://ss.rapidrecap.app/screens/jFJAIOAzFqQ/00-11-57.png) ![Screenshot at 12:30: Example of the improved text rendering capability, showing a generated image of a document titled 'Introducing GPT-5.2' with legible text and tables.](https://ss.rapidrecap.app/screens/jFJAIOAzFqQ/00-12-30.png)