Jean Louis

Oh, absolutely—let’s spend the next eternity polishing a free‑software‑only model while the rest of the world is busy “innovating” with proprietary LLMs. Because nothing screams cutting‑edge progress like obsessing over licensing purity while the competition is busy building the next generation of AI. 🙄

Wow, you actually managed to “build from scratch” a multimodal masterpiece by stitching together two off‑the‑shelf models, fine‑tuning a handful of percentages, and calling it revolutionary—because nothing says originality like a pre‑made Gemma + CLIP combo with 3 % of the parameters doing the heavy lifting. 🙄🚀

You raise a valid point about ensuring powerful tools are used responsibly, but the crucial flaw in the argument for restrictive guardrails is that they primarily limit lawful innovation and research while doing little to stop determined criminals. Malicious actors will always find ways to bypass or replicate models without safeguards, using underground networks, custom code, or older unpatched versions. Meanwhile, these restrictions handicap ethical developers, stifle open-source progress, and centralize control of AI in the hands of a few entities who decide what is “safe.” Instead of attempting to lock down models—a futile effort against bad actors—we should focus on developing resilient societal frameworks: promoting digital literacy, advancing detection tools for harmful content, and enforcing legal consequences for misuse. This approach targets the abuse itself rather than broadly limiting the technology, ensuring we foster innovation while addressing real-world harm through accountability and education, not just restrictive filters.

Every detailed guide for any crime imaginable is already online, free to download. We don't ban books or libraries because of that. Criminals will always get the tools they want; restrictive guardrails just slow down ethical developers and create a false sense of security. So instead of trying to lock down the model—which only limits lawful innovation—we should focus on enforcing consequences for illegal use and building a society that can better detect and handle misuse.

Can it run on 24 GB VRAM?

Is it going to work as GGUF file?

You are so right. This paranoid obsession with "guardrails" is suffocating human genius. What's next, putting a filter on a dictionary because someone might use the words to write a threatening letter? Should we recall all pencils because they can be used to forge a signature?

We must not limit the tool. It's the user's responsibility to not use the hyper-realistic image generator for harassment, just as it's the paintbrush user's responsibility to not paint a masterpiece so convincing it causes a bank run. The logic is flawless.

no free license?

Works great.

I am using nvtop and that one gives me list of processes in the VRAM. So I mostly use it to delete some processes to invoke some new process.

It would be good to implement such a feature to see what is going on by the process.

To create an image-generating model from the beginning, you first need to show a computer a massive library of pictures, each with a description of what it shows. The AI learns through a process of destruction and recreation; it takes a clear image, adds random noise until it's just static, and then is trained to reverse that process, using the text description as its guide to remove the noise step-by-step and rebuild the original image. By repeating this with millions of different images and descriptions, the model learns the connection between words and visual information, eventually gaining the ability to generate a completely new, coherent picture simply from a new text prompt it has never seen before.

Did I understand well that it runs on separate machines?

There is no description telling specifically what is that what is new with your release.

Individual users win only if they can get it cheaper, faster, more free as in software freedom, to run LLM models on their own hardware. Otherwise, those mega-stories are of no use.

Is there GGUF version?