If you make things with AI, we want to know your name. Introducing the Higgsfield Creator Partnership Program. > Get a monthly Higgsfield plan > Extra credits for bigger projects > Early access to new models > Access to an exclusive partner community > Affiliate earnings and direct line to our team Apply now.

Imagine a Formula-style car accelerating while the road literally disappears behind it Seedance 2.5 x @runwayml

Creative pipeline is about to change forever. Opus 5.5 is building the games, 3D worlds, the videos + the ads. 10 wild examples. Bookmark this.

MAJOR update for Grok Imagine by @SpaceXAI 🔥 Grok Imagine now supports keyframes for video generation! You can choose images for the beginning, end, and specific moments in between, then let Grok generate the motion connecting them. Much more control over how your video unfolds. First Frame and Last Frame were already available, but intermediate keyframes are new. The feature has appeared in the interface without an official announcement yet. You heard it here first! 👀

I gave Claude another 18 hours.. and I think this one is the best one yet Macrohard: Windows XP I'm blown away

Ben Affleck talks about building InterPositive, the AI video startup he sold to Netflix for ~$590m. Says when he first saw AI text-to-video, he told Matt Damon: “Dude, we have to do as many movies in the next few years as we can. We’re finished.” He later felt the AI video models didn’t fully understand filmmaking (they had raw video knowledge but didn’t convey “cinematic language”). Affleck raised money and his team (16 employees total) spent 8 months with various cameras and equipment shooting footage as inputs to train a new model (letting other filmmakers build a model for each film based on daily footage, which presumably makes it easier to do post-production edits): “[We built our own] data set that would serve as late-stage training for open models to do discrete tasks…It was geared toward actual specific tasks that would generate value, as opposed to, ‘Oh, this is novel. That’s kind of cool. Look what it can do.’ It was more, ‘it needs to hit these criteria’… We built the workflow. [It] is designed to train from a filmmaker while they’re making their movie. Rather than exposing what you’re doing to everybody to learn from, they retain the proprietary nature. In other words, they benefit from the learning they’re creating. They train their own discrete model using the same technique we did, just on top of that additional layer we had created.“

Ideogram 4.5 debuts at #23 on the AA-Image-Editing v2.0 leaderboard, Ideogram's first model on the board, and lands at #34 on AA-Image-T2I v2.0 Ideogram 4.5 is Ideogram's new image model, released on September 30. Ideogram positions it as a high precision edit model, built to reduce pixel shifts, color changes and texture artifacts across multi-turn edits. It also supports Text to Image. We evaluated Ideogram 4.5 at “high” quality level. In AA-Image-Editing v2.0, Ideogram 4.5 takes #23, just behind HiDream-O1-Edit-1.5 and HunyuanImage 3.0 Instruct and ahead of ByteDance's Seedream 5.0 Lite. It is the first Ideogram model on our Image Editing Leaderboard. In AA-Image-T2I v2.0 it ranks #34, climbing from #40 for Ideogram 4.0. At the High quality setting we evaluated, Ideogram 4.5 is priced at $0.22 per image ($220 per 1k images) for edits and $0.10 per image ($100 per 1k) for Text to Image. Lower quality tiers start at $0.008 per image for edits and $0.03 per image for Text to Image. Ideogram 4.5 is live in Ideogram, the Ideogram API and Ideogram's launch partners, with open weights coming soon. Congratulations to @ideogram_ai on the release! See below for our analysis and example outputs of Ideogram 4.5 in the Artificial Analysis Image Arena 🧵

AI painting of the day. Created with ChatGPT image 2.5

“The most beautiful part of our bond was not healing each other’s wounds; it was never feeling the need to hide them.”

A few more ✨ Wish we could post more than 4 images. This is what I used on Midjourney --sref 2116795492 --profile lbffree --stylize 750

Consistent character identity and pre-production references address the core limitation of current AI video tools. A structured path from character sheet to time-coded 30-second sequence supports repeatable anime storytelling

IS FLUX 3 IMAGE A GPT IMAGES KLLER? 🔪 A NANO BANANA KILLER? Well...... Check it out vs the competition in the video below. I am hopeful Open Source Cool Kids can work their magic in the coming weeks when it goes open source. Prompt Screen tests 4 different women auditioning 16x9 Still 2x2 from a 1989 serious edgy international science fiction film an age 28 female close-up real actors accurate on location filming physical fx and props vintage photography

We made a new & nice model: FLUX 3 Image is out ✨ Built on the multimodal FLUX 3 backbone, it's extremely strong at multi-turn editing, generates natively at up to 4K, and supports bounding boxes for precise localized editing and generation. An open-weight variant is coming.

Meet Higgsfield × FLUX 3 Image. With Black Forest Labs' new image model, you can: > edit one detail without touching the rest > place objects with bounding boxes > combine up to 10 references > generate in up to 4K Available now on Higgsfield.

Introducing FLUX 3 Image. Control every pixel. Make precise multi-turn edits without changing any other pixel. Lay out the image exactly how you want using bounding boxes. Generate in up to 4K to preserve details. Use up to 10 references to compose an image. Commercial Weights available for companies running image generation at scale. Open Weights version of FLUX 3 Image is launching in the coming weeks.

ChatGPT has GPT Image. Gemini has Nano Banana. Grok has Imagine But why the hell does Claude still not have its own image or video model? Anthropic, I desperately want to see what you guys can cook in Image generation.. Agreed guys ???

QT your redhead 🦰

I asked Gemini to convert my slides into nano banana pics It did this