Is there a test I can periodically do to see how my cognitive abilities are being affected by my AI usage all day?

Comments URL: https://news.ycombinator.com/item?id=49557687

Points: 8

# Comments: 1

Seedance 2.5 is likely taking the spotlight today but I wanted to do a deep dive into FLUX.3 so it can get some attention.

My general observation is that FLUX.3 video is the most "clay-like" video model I've played with.

Specifically: - Adding and rerunning video prompts feels additive/subtractive and not completely random generations (I feel much more in control of the medium). - "Draft" and "Enhance" modes (rerunning generations with the same seed) feel like getting to work with clay before committing in a kiln. Certainly a faster and cheaper way of working with generative video.

Excited to share results here.

The canvas has all generations with the prompts included.

Spent ≈$1,000 on this test.

Disclosure: I'm the co-founder of Martini (W26), which is where I ran the test

Comments URL: https://news.ycombinator.com/item?id=49213712

Points: 1

# Comments: 0

Prompt: "A white female in their 30s winks at the camera with her right eye.

She is standing in a quiet dark green forest, backlit by the sunset during golden hour."

So I built a benchmark around getting video models to wink.

Every model gets the same prompt and the same starting frame.

Prompt: “She winks with her right eye.”

Models tested: Veo3 / Kling 2.1 Master / Runway Gen-3 / SeedDance 1.0 Pro / Moonvalley Marey / Wan 2.2 / Minimax Hailuo-02 / Midjourney

I've ran 9 random seeds for each model.

It looks like Kling 2.1 Master is doing the best of this batch.

Would love to hear other small, quirky things you've struggled video models to do — I’ll try to add them!

Comments URL: https://news.ycombinator.com/item?id=45509580

Points: 2

# Comments: 1

What are you developing a spectral CMS for? Is it for lighting or materials or something imaging related?

Maxwell's "color wheel" experiment (https://cudl.lib.cam.ac.uk/view/PH-CAVENDISH-P-02000/1) is more commonly known, which preceded this experiment I wrote about. (Which by the way is also a very clever experiment which blends color by spinning a wheel with different ratios of primary colors).

Here's a link to Maxwell's original paper: https://royalsocietypublishing.org/doi/10.1098/rstl.1860.000...

You can see some diagrams of his original apparatus that I worked off of in the last two pages!

How We Met – https://how-we-met.c47.studio/

Each day, I create a new 30-second episode based on the plot direction voted on by the audience the day before.

I'm trying to see how far the latest Video GenAI can go with narrative content, especially episodics. I'm also curious what community-driven narratives look like!

For the past week, I've been tinkering mostly with Runway, Midjourney, and Suno for the video content. My co-creator vibe coded the platform on Lovable.

Please do let me know if you have any additional questions or feedback about my interactive!

Comments URL: https://news.ycombinator.com/item?id=44408484

Points: 44

# Comments: 10

These cards are ubiquitous in Japan so I’m very confused how this can happen.

Can someone that has some understanding of semiconductor supply chain explain what’s going on here?

The chips inside these cards surely don’t seem like the high-end chips that the AI crowds are going around.

I'm glad you pointed out the music. The music was also AI generated with a tool called AIVA [1]. I'd never composed a piece of music before, and I was pretty surprised by what I could "create". I spent 30~60 minutes max creating the score.

Some parts of their product still feel janky, but as an overall concept, it's quite fascinating. One of the interactions I enjoyed was that AIVA creates scores with different tracks (layers). So I was able to edit tracks I don't like (e.g., change a Piano track to Brass) or have AIVA completely regenerate certain sections of the score (e.g., redo the bridge, regenerate the chorus sections).

One difference from Midjourney is that there's no text-based prompting. Instead, you "prompt" through music inspiration.

[1] https://www.aiva.ai/

One recent feature the guide missed is the permutation and repeat features [1]. They're quite helpful for power users that want to explore multiple styles quickly.

Last week I tried putting together a short film using GPT-4 and Midjourney v5. I was stunned by the cinematic frames Midjourney v5 was able to create:

https://youtu.be/6O_tOuUcG9s

I (human) wrote the prompts for Midjourney, though.

[1] https://docs.midjourney.com/docs/permutations