ChatGPT Images 2.0 First Impressions
A user tests ChatGPT's new image generation capabilities by creating a brand kit for their company Chat PRD. While the initial AI-generated design had good typography and layout, it required reference images from Midjourney to achieve the desired aesthetic that better matched their brand identity.
Summary
The speaker demonstrates ChatGPT's updated image generation feature by requesting a brand kit for their company, Chat PRD, providing general brand design guidance. The initial results showed significant improvement in typography quality compared to previous versions, with the AI successfully creating a nine-grid layout showcasing different brand kit components. However, the speaker noted that while technically competent, the generated design didn't capture their company's authentic visual identity. To address this, they provided reference images from Midjourney that better represented their brand aesthetic, featuring pixelated landscape imagery. The AI's second attempt incorporated these references effectively, producing a more pink-toned design that aligned much better with their brand vision. The speaker expressed genuine satisfaction with the updated results, indicating that ChatGPT's image generation capabilities have notably improved in both technical execution and ability to interpret and incorporate user feedback and reference materials.
Key Insights
- The speaker observed that ChatGPT's typography has improved and no longer has the classic poor text appearance of previous GPT image generations
- The AI successfully created a nine-grid layout for different parts of a brand kit, demonstrating improved layout capabilities
- The speaker noted that while the initial AI-generated brand kit wasn't bad technically, it didn't capture their company's authentic identity
- When provided with Midjourney reference images featuring pixelated landscape imagery, ChatGPT successfully incorporated these visual elements into the updated design
- The speaker expressed genuine excitement about the final results, stating the updated brand kit made them 'so happy' and praising GPT image 2's capabilities
Topics
Transcript
[0:00] So, I asked it to create it for my company, Chat PRD. I just gave some general brand design guidance off this. I had ChatGPT write this for me and asked it to generate it. And what I will say is it did a really lovely job in terms of text. It doesn't have that classic GPT image text [music] looks to it. So, typography has gotten a little bit better. I think it's kind of amazing it can do this nine-grid layout of different parts of the brand kit. And I don't think it's bad. It's just not me. [0:31] And so, I loaded up some images from Midjourney here that I think we use more in our…
Full transcript available for MurmurCast members
Sign Up to AccessMore from How I AI
GPT-5.6's video editing via Codex is genuinely one of my favorite new workflows
A product manager describes using GPT-5.6 with Codex to automate video editing for social media clips. By simply dragging a file and providing natural language instructions, the AI generated five polished, fast-paced hype videos from a long conference talk recording, dramatically reducing the time-intensive manual clipping process.
Theoretically Intelligent vs. Practically Effective: Why GPT-5.6 Sol Beats Fable for Product Work
An executive contrasts two AI models (Fable and Soul/GPT-5.6 Sol), arguing that Soul is superior for product work because it prioritizes practical effectiveness over theoretical intelligence. The speaker values the ability to ship products to customers and understand end-user goals over theoretical sophistication.
Build a harness when the same workflow needs the same setup and the same outcomes, every time
Building a harness for repetitive workflows allows you to be more prescriptive about job execution, resulting in greater efficiency, consistency, and better outcomes. Rather than explaining requirements to an AI agent each time, a harness lets you use a simpler interface like pasting a link while the agent already understands the intended task.
GPT 5.6-Sol vs. Claude Fable: Why OpenAI’s new model crushes my benchmark
Claire Vo compares OpenAI's new GPT 5.6 models (Soul, Terra, Luna) against Claude's Fable using her custom "How I AI" benchmark, finding that GPT 5.6 Soul excels at practical product work, prototyping, and natural communication, while Fable is theoretically intelligent but pedantic and difficult to collaborate with.
Context offloading is an underrated AI use case
The speaker highlights context offloading as an underrated AI use case, where AI serves as a safety net for routine cognitive tasks like email management and personal finances. Rather than adding new capabilities, AI reduces anxiety about missing important information or making mistakes by handling monitoring tasks, thereby freeing up mental bandwidth.