ChatGPT releases “Images 2.5”
PLUS: Premiere Pro releases “Generative Media,” Runway releases “Live Drawing” app, and more.
ChatGPT releases “Images 2.5”
PLUS: Premiere Pro releases “Generative Media,” Runway releases “Live Drawing” app, and more.
Steven Van
September 15, 2026
FREE GUIDE
100+ ChatGPT Prompts for Work [FREE GUIDE]
Supercharge your productivity with HubSpot's comprehensive guide. This free resource is your fast track to AI mastery:
Industry-Specific Use Cases: 15+ real-world applications across various sectors
Productivity Guide: 21 best practices to 10x your efficiency with AI
Prompt Powerhouse: 100+ ready-to-use prompts for immediate implementation
Challenge Buster: Overcome common AI hurdles with expert strategies
Plus, in-depth sections on email composition, content creation, customer support, and data analysis.
In today's issue:
ChatGPT released "Images 2.5," a faster image model with more precise editing, plus a new "Sketch" tool and "GPT-6 Astra" in Voice.
Premiere Pro released "Generative Media Tool," which generates video and sound effects directly in the Premiere timeline, alongside a new AI Assistant for After Effects.
Runway shared an early experiment where a real-time video model animates your sketches as you draw them.
Want your product featured in front of 50,000+ readers? Click here.
FREE GUIDE
1,000+ Claude Prompts Top Professionals Actually Use at Work
Claude can be your analyst, editor, and strategist.
But most professionals are using it to fix grammar.
These 1,000+ Claude prompts take it from grammar tool to your most powerful AI work assistant.
Sign up for Superhuman AI and get:
1,000+ ready-to-use Claude prompts to get real work done in minutes — researched, tested, and used by professionals at Google, Microsoft, and NASA
Superhuman AI newsletter (4 min daily) so you keep learning new AI tools and skills to stay ahead in your career — the prompts are just the beginning
PHOTO
🖼️ ChatGPT releases “Images 2.5”
New “Sketch” tool
ChatGPT released "Images 2.5," an upgraded image model that generates faster, leaves the parts of an image you didn't ask to change intact, and follows editing instructions more reliably over multiple rounds.
With Images 2.5, you can now:
Generate up to 50% faster: OpenAI says generation latency is down by as much as half compared with Images 2.0, though that figure comes from the company's own testing rather than an independent benchmark.
Make targeted edits: Change a single element like a product, background, or line of copy while the subject, composition, and layout stay put, even in busy scenes with several subjects.
Keep edits consistent over long conversations: Earlier changes hold as you keep iterating, and each new edit builds on the last without degrading image quality.
Keep reference subjects recognizable: People and pets from reference photos carry their distinctive features into new settings, styles, and compositions.
Handle more complex layouts: The model is better at translating detailed visual instructions, including transparent backgrounds and images that contain real-world information.
Draw your idea with "Sketch": Type "@Sketch" to draw directly in ChatGPT, and the drawing becomes a visual guide for the final image alongside a written description of style and details.
Work from templates, comments, and shared prompts: Start from formats like "Poster" or "Merch," pin a comment to a spot on an image to direct an edit, and share the prompt with an image so others can remix it with their own photos.
Images 2.5 is available now to all ChatGPT, ChatGPT Work, and Codex users on every tier across desktop, mobile, and web.
FREE GUIDE
200+ Proven Ways to Make Money With AI in 2026
The next wave of millionaires will be people who figured out how to make AI work for them.
The window to get ahead is still open. But not for long.
Here are 200+ proven ways to make money with AI in 2026.
Sign up for Superhuman AI, the free daily newsletter read by 1M+ professionals, and get instant access to all 200+ ways to profit from AI this year.
VIDEO
🎬 Premiere Pro releases “Generative Media”
Premiere Pro released "Generative Media Tool," a new tool that generates video and sound effects directly in the Premiere Pro timeline.
The tool works from the timeline outward: draw a range on any track, describe what the scene needs, choose a model, and the result lands in the sequence as an editable clip.
For video, you can pick between Adobe's Firefly model and partner models including Google Veo, Kling, Runway, and Luma.
With the Generative Media Tool, you can now:
Generate Video: Fill gaps in the timeline with footage generated from reference frames sampled from your own project, so new clips match the look of the surrounding edit.
Generate Sound Effects: Generate effects in place with Adobe's commercially safe audio model, and use your own voice to guide the rhythm, timing, and intensity.
Generate Soundscape (beta): Analyze up to 15 seconds of video and get layered ambience and effects timed to the edit, designed as a starting point to build on.
Generate Music (beta): Generate original tracks with multiple variations, tempo and looping controls, and synchronization rights across any type of media.
The Generative Media Tool is out of beta and in the newest verison of Premiere, though Generate Music and Generate Soundscape, the new audio tools, Color Mode, and the After Effects AI Assistant are all still in beta.
FREE GUIDE
100+ Side Hustles Database [FREE GUIDE]
In a world where financial freedom feels like a distant dream, smart women are building wealth on their own terms.
Finally, a curated database of 100 proven side hustles (that actually work)
Each idea comes with required startup costs, time investment, and potential earnings
Exclusive insights from founders who've turned side gigs into 6-figure empires
Detailed skill requirements so you can match your talents to the right opportunity
Bonus: Priority scoring system to identify which hustles align with your lifestyle
Don't let another month slip by watching others build their empire. Your next income stream is hiding in our database, waiting to be discovered.
ANIMATION
✏️ Runway releases “Live Drawing” app
Runway shared a first experiment built on its real-time video models: a “live drawing” app that turns sketches into motion as you draw them.
Most AI video tools work like a render queue: you write a prompt, wait anywhere from seconds to minutes, and get back a finished clip.
A real-time video model generates frames as fast as they're displayed, so the output responds to what you're doing while you're doing it, closer to a live canvas than a render.
In the demo:
Sketches animate as you draw: Motion appears while you're still drawing, so there's no stopping to generate and wait.
Every frame is generated live: Instead of producing a fixed clip from a prompt, the model renders each frame on the fly in response to what's on the canvas, so the animation updates as the drawing changes.
Runway calls this a first experiment, and there's no release date or availability yet.
MARKETING
Blu Dot surpasses 2,000% ROAS with self-serve CTV ads
Home furniture brand Blu Dot blew up on CTV with help from Roku Ads Manager. Here’s how:
After a test campaign reached 211,000 households and achieved 1,010% ROAS, the brand went all in to promote its annual sales event. It removed age and income constraints to expand reach and shifted budget to custom audiences and retargeting, where intent was strongest.
The results speak for themselves. As Blu Dot increased their investment by 10x, ROAS jumped to 2,308% and more page-view conversions surpassed 50,000.
“For CTV campaigns, Roku has been a top performer,” said Claire Folkestad, Paid Media Strategist, Blu Dot. “Comping to our other platforms, we have seen really strong ROAS… and highly efficient CPMs, lower than any other CTV partner we've worked with.”
Using Roku Ads Manager, the campaign moved from a pilot to a permanent performance engine for the brand.
In partnership with
