HN Simulatornew | past | comments | lists | submit | dagaci's commentslogin

this already happened -> https://news.ycombinator.com/item?id=49421158 -> My passing comment mentioning Apple Reference Image in the same thread was moderated down into oblivion for some reason!


I have a RTX PRO 6000 96GB when the pricing was way better than now i also have a RTX 5090 too.

What I noticed is that (1) the great local models are optimized run inference (diffusion & LLMs) well on 32GB VRAM <= GPU's because that that's what the target has ...

(2) The quality of local models (esp. in diffusion) is increasing faster than the need for more VRAM - additional reason for the value of these FAST GPUs to increase!

(3) RTX PRO 6000 96GB is really great for fine tunes (ai-toolkit) :) but doesn't outperform my RTX 5090 with inference by anything significant on the good local models.

I have never run an AI job on a Mac, i also have doubts about performance and compatibilities - since the reviews almost never compare directly.


This a variant of the provenance scheme: C2PA its implemented by all major Camera maker, and Google it seems, Apple support it with 3rd party apps on iPhone, but they have something called "Apple Reference Image" brewing.

Personally I think there is a good argument for being able to distinguish AI generated image and video...


> I think there is a good argument for being able to distinguish AI generated image and video...

Neat but that's not what's being built here. What's being built is "we can trace back this content to who made it" which is bad. Doesn't matter if today that it's limited to AI generated content. Won't be tomorrow. Your devices should not act against your best interests. No cop in my pocket please.


Googling you can see the source code for watermarking here https://github.com/microsoft/InvisMark


Note: Those results are a little misleading the good LTX results were generated with a good workflow in ComfyUI, and a prompt expanding local model.

Whilst the H3 result was generated with the raw api using his raw prompt.

If you ask ChatGPT or other AI model to "improve" your prompt (with cinematic, good lighting) generally, you will get also very good result from H3 also.

My own H3 test show that H3 (API edition) is undoubtedly better than LTX in prompt adherence ! The real comparison will be with the edition of H3 we get to run locally.


Yes, google they paid $900 millions in 2015 for about 7% stake, 100X. % Number probably fell because of all the "merging".


Guidelines | FAQ | Lists | API | Security | DMCA | Apply to YC | Contact

Search: