Ideogram 4 has gone open source!
According to current benchmarks and arena rankings, it's one of the strongest open-source image generators available.
"Ideogram 4 is Ideogram's first open-weights model, trained from scratch. It features a structured JSON prompt format, best-in-class multilingual text rendering, deep language understanding, color palette control, and native 2K generation with aspect ratios up to 6:1."
With just 9.3B parameters, it should run on modest GPUs (Qwen-Image: 20B, FLUX.2 [dev]: 32B).
For the geeks:
• Flow-matching text-to-image model built on a fully single-stream DiT architecture. • Text and image tokens are processed together by the same 34-layer transformer. • Uses Qwen3-VL-8B-Instruct, providing richer visual understanding than CLIP or T5.
Trained on JSON annotations and includes a prompt enhancer and guide.
Some content moderation is built in (Hive AI). The license is non-commercial.
GitHub repo (weights, code, docs, guides): https://github.com/ideogram-oss/ideogram4

3D generators are coming for the sacred territory — organic modeling, specifically head modeling.

This is Rodin 2.5. They offer 12K textures and generation at 10 million polygons.

The input is several head images from different angles — either generated images or photos.

https://hyper3d.ai/

Claude Fable 5 might drop today.

Leaks claim Anthropic is preparing to release Mythos publicly under the name Claude Fable 5, but nothing is official yet.

Are Game devs in trouble?

Fable 5 is the biggest step up I've felt in our models since Opus 4.5 back in November.


We just one shot GTA 6 and it works. No miskates.

One prompt. 15 minutes. The whole game.

Rockstar took 12 years. Fable took a quarter of an hour.

Mythos was deemed too dangerous to release, this is the nerfed version. And it still does THIS.

Game devs, are we in trouble?

Krea 2: Procedural Images

Krea now has real-time sliders: intensity, complexity, and movement.

Basically: prompt intensity, noise/details, and object movement within the frame.

This definitely makes the generation process more interactive and speeds up image selection.

It also reminds me of procedural textures. If you’ve worked with them, you’ll remember all those endless knobs for tweaking patterns, noise, and textures.

If you haven’t, think of the effect preview in Photoshop: you see the result immediately.

I wonder how many more sliders they could add: color grading, 3D depth, typography, layer separation, background…

The idea is to give regular users as many clear and understandable controls as possible — instead of all that CFG Scale, Sampling Method, and so on — and keep them inside the generation interface.

AI video is getting wild.

On June 15, Dreamina is releasing Seedance 2.0 Mini, and this is huge:

Same performance level as Seedance 2.0, but much cheaper.

That means creators can generate more AI drama shots, test more ideas, and build cinematic videos without burning insane credits.

AI video is not slowing down.

Grok Imagine Video 1.5

It’s out of Preview.

The interesting part: 720p, 15 seconds — but the SuperGrok subscription page says “30-second videos.”

That’s a marketing trick. The API clearly says 15 seconds. The “30 seconds” refers to the Extend from Frame feature, which is available there.

There’s also Grok Imagine Video 1.5 Fast — it generates 720p videos in 25 seconds.

https://x.ai/news/grok-imagine-video-1-5

Who will win the World Cup before it happens?

Soccer Buddy uses AI-style prediction logic, 80+ match parameters, 10,000 simulations, and deep pro stats to find stronger football angles before kickoff.

xG, BTTS, overs, corners, cards, shots, possession, home and away splits.

AI + stats = smarter soccer predictions.

https://zcodesystem.com/soccerbuddy/?WC2026

Seedance 2.5

ByteDance announced the new version at Volcano Engine FORCE 2026.

The interesting part: native 30-second video generation in a single run. Previous public versions were limited to 15 seconds, so this is a major jump.

Another big upgrade: up to 50 multimodal references — images, videos, and audio — to control style, characters, motion, and editing.

Seedance 2.0 also received an upgrade and now supports native 4K video generation.

The model is currently in enterprise beta and is expected to launch publicly in early July.

🤖 AI company Anthropic is expanding its presence in Europe

Anthropic, the company behind the Claude AI assistant, has hired the head of artificial intelligence from the French telecom company Orange. This move is part of Anthropic’s major expansion into the European market.

It seems that competition between leading AI companies is no longer just about building the best models — it is also about attracting the world’s top experts.

Comfy MCP

Comfy Org has launched the beta version of its MCP server for ComfyUI.

MCP allows AI agents to interact with and manage ComfyUI more easily:

• Run workflows using natural-language descriptions
• Search for models, nodes, and templates across the ecosystem
• Import workflows directly from a URL
• Rerun saved workflows with new inputs
• Access hundreds of ready-made workflows with automatic updates

Documentation

They are also launching the beta version of Comfy CLI and the Comfy Skill repository for AI agents.

⚡ Breaking: Nano Banana 2 Lite

And by “flash,” I mean lightning-fast: just 4 seconds to generate an image.

https://deepmind.google/models/gemini-image/flash-lite/

Nano Banana 2 Lite is available in Google AI Studio, the Gemini API, and the Gemini Enterprise Agent Platform.

Seedance 2.5 is about to go crazy.

We are talking about native 30-second AI videos, 4K output, up to 50 references, native audio sync, region-level editing, better prompt accuracy, and no stitching needed.

And some beta users are already revealing insane 180-second outputs.

Early results look crazy. Just look at these examples. This is wild. Hollywood is in trouble again.

What do you think, will Hollywood try to ban it again, or will these platforms solve the copyright issues right from the start?

I honestly can’t wait to try it.

Seedance 2.5 is coming soon to major platforms like Dreamina @dreamina_ai , @capcutapp , and @openart_ai .

Vidu S1

Vidu, which many had almost forgotten about, has rolled out its answer to Runway Characters.

Real-time video generation in 540p at 25 FPS.

Avatars, lip sync, and two-way real-time communication:
https://www.vidu.com/ru/vidu-stream

“After logging in and verifying your account, you can upload your photo, choose a voice or record your own, and create a personal digital human to communicate with.”

There’s also an API.

META JUST CRASHED INTO THE VIDEO AI RANKINGS. 🔥
Meta Muse Video @AIatMeta just landed at #3 in the Text-to-Video @arena with a 1459 score.

It beats Alibaba’s HappyHorse 1.0 by +30 points and ranks ahead of Sora 2 Pro, Grok Imagine and Google Veo-3.1.

But the real question is timing.

Seedance 2.5 is also dropping, and if it brings stronger motion, longer usable shots, better consistency, and real creator controls, Muse Video might not hold that spot for long.

Still, this is a huge signal. Meta is officially at the video AI frontier now.

The video model war is getting brutal.

This is WILD.

GPT-5.6 by @OpenAI just dropped and the model war got messy fast.

Fable 5 still looks like the raw intelligence king, sitting at 60 on Artificial Analysis.

But GPT-5.6 Sol is right behind at 59, takes #1 in coding agents with 80, and does it at roughly one-third the cost.

Meanwhile Grok 4.5 @grok is the chaos pick. Not the smartest, but cheap, fast, efficient, and suddenly close enough to make everyone nervous.

So the race is no longer just “who is smartest?”

It’s Fable for raw brain. But too expensive!
GPT-5.6 for work and coding.
Grok 4.5 for price pressure and speed.
AI labs are not fighting for benchmarks anymore.
They’re fighting for who becomes the default worker.