LayerLife The Creator 🇹🇭

🕸️🕷️🐈‍⬛
multimedia designer/game developer/unity developer/3d generalist/content creator

[LayerLife The Creator 🇹🇭 @layer_life]

HDRP #unity #unity3d

[Elon Musk @elonmusk]

Looks like Grok 4.5 is #1 on at least a few benchmarks. Better than expected.

[ComfyUI @ComfyUI]

Prompt:

An editorial graphic design poster on a solid black background. The central elements are exquisite, translucent 3D glass flowers with iridescent, holographic petals in shades of electric blue, violet, and soft purple.

In the background, large, bold white sans-serif typography reads "Seedream 5.0 Pro", elegantly layered behind and interwoven with the glass petals.

The layout is filled with clean blocks of small white placeholder body text and delicate thin white vector lines, creating a futuristic, tech-organic informational poster. High-contrast, sharp details, refractive glass textures, glossy finish, professional UI/UX design aesthetic.

[Elon Musk @elonmusk]

Rate of improvement is accelerating.

Users should notice a meaningful improvement in the usefulness of the Grok Build harness with our V9 foundation model (aka Grok 4.5) every week.

[Design Arena @Designarena]

BREAKING: Grok 4.5 by @SpaceXAI is 5th on Website Arena with an Elo of 1328.

This is a 25 rank jump over @SpaceXAI’s previous highest performing model.

Trained with Cursor data, Grok 4.5 is in the same performance band as Claude Opus 4.6 (Thinking) by @AnthropicAI, achieving Opus-level coding performance on real world website tasks.

Congratulations to the @SpaceXAI team on the launch!

[GMI Cloud @gmi_cloud]

Grok 4.5 operates at Opus-level intelligence and Sonnet-level pricing!

We tested it against Claude Opus 4.8, Sonnet 5, and GLM 5.2 on a SpaceX mission: liftoff, stage sep, orbit insertion, satellite deploy.

Grok 4.5 animates it more accurately and vividly than Sonnet 5 and GLM 5.2. Opus is the fastest and most expensive. Grok burns more tokens but still lands ~40% cheaper than Opus, and a bit under Sonnet 5.

Time / tokens / cost:
Grok 4.5 — / 35k / $0.69
Opus 4.8 — / 13.7k / $1.10
Sonnet 5 — / 22.1k / $0.78
GLM 5.2 — / 92.7k / $0.13

yet GLM did the whole mission for $0.13 😮

[Lumina @LuminaXspace]

🚨 New Grok 2T model update:

xAI is prepping the next Grok model already:

- 2T model will finish training this month and become available next month (August)

- This is xAI’s aggressive monthly plan of launching new foundation models monthly through the end of 2026

I think 2026 might be the year grok / SpaceXAI finally catch frontier models up, do you think will by 2026 end?

[Google @Google]

Introducing Video Remix in @GooglePhotos. 📹 Powered by our Gemini Omni model, it lets you reimagine your videos in new styles with a library of easy-to-use templates.

To get started, simply select Video Remix in the Create tab. You’ll be able to instantly apply cinematic lighting, swap a background, add stylized elements like watercolor effects and more.

[Higgsfield AI 🧩 @higgsfield_ai]

Seedream 5.0 Pro vs GPT Images 2.0, both fed into Seedance 2.0.

[Magnific @magnific]

Should we drop the prompts for these?

A 1995 Spanish summer that never existed. We grew up in places like this one. So we tried to generate the memory

Created using Seedream 5.0 Pro powered by @BytePlusGlobal

[Google Antigravity @antigravity]

Antigravity CLI 1.1.0 is here! Featuring new interactive execution modes, an improved UI, and workspace fixes.

[Ingi Erlingsson 🪄 @ingi_erlingsson]

WTP man?? 🤬

Designed in @figma + GPT Image 2.0 + @grok image

Generated in @ComfyUI with @Alibaba_Wan 2.2 I2V + Vace

Composited in @AdobeAE

Music made with @suno

[ComfyUI @ComfyUI]

Seedream 5.0 Pro is now in ComfyUI via Partner Nodes.

ByteDance's latest image model brings:

→ Character & product consistency across edits
→ Precision region editing
→ Infographics, flowcharts & structured layouts
→ In-image text across 14 languages

One model. Text-to-image, editing, and multi-image inputs.

Click the link below for the workflow 👇

[OpenRouter @OpenRouter]

Grok 4.5 is live now on OpenRouter!

Cursor’s contributions have helped make @SpaceXAI’s model frontier-level on long-horizon engineering tasks.

[Brie Wensleydale🧀🐭 @SlipperyGem]

JT88 has made another useful node. Last time was the multi-cam angle node. This is in the same vein but with lights.

I assume this plugs into that nice Flux Klein 9B light control lord I posted a few days back.

[Matt Workman @mattworkman]

Seedream 5.0 Pro looking very solid

my go to test prompt: "a Korean girl in her twenties on her iPhone in San Francisco at sunset"

[Higgsfield AI 🧩 @higgsfield]

The $100,000 Higgsfield App Contest is on.

Build an app on Claude and deploy it in one click via Higgsfield MCP. 13 winners split the pool, with $25,000 for first place.

Submit by July 22. Winners announced July 29.

The time to launch your app is NOW.

[Nous Research @NousResearch]

Hermes Agent is now in the Cloud!

Setup couldn't be simpler: pick a model and a server size. Two clicks and 60 seconds later, your agent is live.

Running a team? Spin up agents for everyone at your org with granular access controls and unified billing, all from Nous Portal.

[Magnific @magnific]

Big you. Mini you with Seedream 5.0 Pro powered by @BytePlusGlobal

The fisheye distortion, the skin texture, all straight out of the model

All the prompts in ALT

[しらき@パワポ図解 @kumiko_shiraki]

【NotebookLM】ゆるキャラを作りたい時のYAML…プロンプトはリプ欄へ↓

[JSFILMZ @JSFILMZ0412]

Seedance 2.0 vs Meta Muse Video.

Both models feature native audio, but Muse Video seems like its currently stuck with a 10-second limit. Meanwhile, Seedance 2.0 can output 15-second cinematic sequences in crisp up to 4K.

Meta is cooking, but Seedance 2.0 might still hold the crown for now. Which one are you betting on?