%20--%3e%3cdefs%3e%3cstyle%3e%20.st0%20{%20fill:%20%23061b40;%20}%20.st1%20{%20fill:%20%23306af1;%20}%20.st2%20{%20fill:%20%235ce5cf;%20}%20%3c/style%3e%3c/defs%3e%3cg%3e%3cpath%20class='st0'%20d='M55,10.5h9v3h-9v9h12V7.5h-12v3ZM64,19.5h-6v-3h6v3Z'/%3e%3cpolygon%20class='st0'%20points='69%2016.5%2078%2016.5%2078%2019.5%2069%2019.5%2069%2022.5%2081%2022.5%2081%2013.5%2072%2013.5%2072%2010.5%2081%2010.5%2081%207.5%2069%207.5%2069%2016.5'/%3e%3cpolygon%20class='st0'%20points='95%2010.5%2095%207.5%2083%207.5%2083%2022.5%2095%2022.5%2095%2019.5%2086%2019.5%2086%2016.5%2095%2016.5%2095%2013.5%2086%2013.5%2086%2010.5%2095%2010.5'/%3e%3cpath%20class='st0'%20d='M40,1.5v21h11.6l1.4-1.4v-7.6h0c0,0-1.4-1.5-1.4-1.5l1.4-1.4V2.9l-1.4-1.4h-11.6ZM50,19.5h-7v-6h7v6ZM50,10.5h-7v-6h7v6Z'/%3e%3c/g%3e%3cpath%20class='st1'%20d='M23.1,24L14.7,4.8l-4.9,11.2h3.8l-1.8,4H3.3L12.1,0H2C.9,0,0,.9,0,2v20c0,1.1.9,2,2,2h21.1Z'/%3e%3cpath%20class='st2'%20d='M34,0h-16.8l10.6,24h6.2c1.1,0,2-.9,2-2V2C36,.9,35.1,0,34,0ZM32.5,20h-4V4h4v16Z'/%3e%3c/svg%3e)
OpenAI once again stirs the AI image generation market. This morning, the company officially released its new image model, GPT Image 1.5, and announced that it will be available to all free ChatGPT users - no subscription required, you can experience the most advanced text-to-image capabilities.
The new model achieves four key upgrades compared to the previous generation GPT Image 1:
- More accurate instruction following: it can accurately understand complex and multi-condition prompts;
- More precise editing control: local modifications no longer disrupt the overall composition;
- Better preservation of details: the consistency of facial features, textures, and lighting is significantly improved;
- Four times faster generation speed: greatly reducing user waiting time.
More notably, GPT Image 1.5 supports parallel generation of multiple images, allowing users to make multiple requests at the same time without queuing, thus doubling the creative efficiency. In terms of cost, both input and output prices for images have been reduced by 20%, allowing more high-quality images to be generated with the same budget, highlighting the cost-effectiveness advantage.
To lower the usage barrier, the ChatGPT web version now has a new "Images" dedicated entry in the sidebar, featuring various preset art styles, popular prompt templates, and filters, enabling even beginners to instantly generate professional-level images with one click.
The most eye-catching part is that OpenAI CEO Sam Altman personally promoted it on the X platform - he shared a photo of a "sexy calendar male model" generated by GPT Image 1.5. The image shows clearly defined muscle lines and delicate lighting, sparking netizens' hilarious comments: "It's not too late to delete it" and "Altman finally edited himself into a male model."
This move not only demonstrates the breakthroughs of the model in generating human figures but also sends a clear signal: OpenAI is fully pushing image generation from a "technical demonstration" to a "mass creation tool." In the context where Sora has not yet been fully opened, the free strategy of GPT Image 1.5 is undoubtedly a crucial step for OpenAI to capture user attention and build a multimodal ecosystem - making AI image generation truly enter everyone's daily life.