FLUX 3 Image

232 points by minimaxir a day ago on hackernews | 53 comments

looks cool, eternally greatful these models are marked for open weight releases. Pretty excited

That sort of steering ability that has been possible with the latest Gemini releases has been nice to work with over previous generations. It’s great to see this improve on the platform with declarative controls built into the API and coming soon as an open model.

arnaudsm | 5 hours ago

The UX looks amazing and very steerable, congrats to the team for focusing on the interface.

Chats can be awful user interfaces.

neals | 4 hours ago

It's this a new model or a new ui?

: swiftcoder | 2 hours ago
Porque no los dos? Presumably you need a model conditioned on the bounding box input to make effective use of the new UI

htrp | 4 hours ago

https://news.ycombinator.com/item?id=49031796

What's new from the last post? GA?

: zamadatix | 4 hours ago
The original article mentions:
> We will open up an early access phase for FLUX 3 Image in the following weeks.
Not sure if there was a separate post for early access or if they just skipped to this.

myself248 | 4 hours ago

Unrelated to the flux images used for floppy disk archiving? Sigh.

: pizzafeelsright | 3 hours ago
Every new piece of software needs a name.
Flux is in the top 9000 of the most common words.

vunderba | 4 hours ago

One of the things they seem to be emphasizing here is the UX around being able to place specific elements where you want them in an image. If the positions of the components in the overall composition are very important, this seems to make that a lot easier and kind of reminds me of InvokeAI.

Ideogram V4, an open-weight model released back in June can also do this [1], but you have to use a relatively cumbersome JSON structure to describe all the different bounding boxes. So it’s definitely a bit of a hassle.

I'll probably be waiting until it goes open-weight (hopefully soon) like they did with Flux.2 / Klein.

[1] - https://docs.ideogram.ai/using-ideogram/getting-started/prom...

kranke155 | 4 hours ago

You just get an LLM to do the bounding box stuff or use the ComfyUI node that provides a GUI for bounding box generation

CuriouslyC | 3 hours ago

I always hated Comfy's node based UI, but agents make it tolerable. Now I just have them set up a workflow and I go in and tweak it manually if the results aren't where I want them. I even have agents cherry doing multiple runs and cherry picking the best outputs, models have gotten good enough that it's a real time saver, assuming you have references they can and a rubric to check against.

hdjrudni | 2 hours ago

How do you get agents to set up a workflow? You just get them to modify the JSON directly and then import it, or do you have a tighter integration (e.g. in the UI)?

: CuriouslyC | an hour ago
The agents can interact with Comfy via API pretty well, which afaik ends up being directly with JSON.

swiftcoder | 2 hours ago

> I always hated Comfy's node based UI

It's one of the most uniquely hostile user experiences I've ever had the (dis)pleasure of working with

vunderba | 3 hours ago

Yeah, given how much better Ideogram v4 outputs are when you use the proper structured JSON (background, elements, etc.) I think most users probably have stuck some kind of Qwen/Gemma-based LLM between their raw prompt and the CLIP encoder.

popalchemist | 3 hours ago

Ideogram 4.5 released 2 days ago with more features along these lines

https://www.youtube.com/watch?v=2mecWZgbaEg

NBJack | an hour ago

Adobe has had something like this for a while with Generative Fill. Drag a box, specify contents.

vergessenmir | 4 hours ago

I think we are all waiting for the open weights or local model releases.

pixelesque | 4 hours ago

Has that been announced?

The website mentions:

> FLUX 3 Image is available under a commercial weights license for companies running image generation at scale. Fine-tune and deploy it on your own infrastructure. Reach out to us to learn more.

I guess the open ones would be non-commercial?

vunderba | 4 hours ago

If it is anything like the previous release Flux.2 [dev] - then yeah it'll probably be a non-commercial license.

https://bfl.ai/legal/non-commercial-license-terms

LordDragonfang | 3 hours ago

There's been an increasing trend of previously-open-weight models going closed-source once they reach a certain size (and size is proportional to capital investment). That the latest release will be open-weight is not necessarily a given just because the previous one was.

: trentor | 2 hours ago
What trend? BFL was always non commercial. The "only" trend would be qwen image not being apache anymore.
: vunderba | an hour ago
It was literally in the announcement from Black Forest Labs:
"Open Weights version of FLUX 3 Image is launching in the coming weeks."
https://nitter.cf/bfl_ai/status/2105734605621825738

JimDabell | 2 hours ago

> Open Weights version of FLUX 3 Image is launching in the coming weeks.

— https://x.com/bfl_ai/status/2105734605621825738

KazaNLP | 4 hours ago

Agreed with other comments about the UX. I'm more interested in that than the model itself. Would like to start seeing UI like this where you get to choose the model and compare different models. Can't jump all over the internet to each model developers sandbox just to test their models. Doing it from one place would be nice.

assimpleaspossi | 3 hours ago

I shouldn't have to scroll all the way down, click to use the thing, then fumble around to figure out what this does. It should be clear at the top of the first page (so I know right away that I don't need this).

richardfulop | 3 hours ago

It is a version 3 of a product.If you actually used or needed these, you would have known right away what this is and how it works.

: nazgulsenpai | 3 hours ago
Unless the version 3 announcement is your onboarding point, like it is for me just now. I can go research FLUX from here, but the original poster's point still holds.
: assimpleaspossi | 2 hours ago
But I don't use it or need it and wasted my time trying to figure out what it did. Clarity should be up front.

thorum | 3 hours ago

Not sure what you mean. The top of the linked page is a video showing the product being used. Immediately below are the words “Compose images from scratch” and more examples, followed by “Text-to-image with strong prompt following and a native understanding of composition.” This is all within the first 100 words of content on the page.

: bonoboTP | 2 hours ago
I agree that it's clear for me and most techies, but maybe for a more general audience they could have added "AI image generation" or some variant of "generative AI" or "image generation model" or something like that. You can also compose images from scratch in Photoshop and Blender.

Mashimo | 2 hours ago

> Just write a prompt. Text-to-image with strong prompt following and a native understanding of composition.

How is this not clear?

armcat | 3 hours ago

Does anyone know if it can be used to generate accurate frame-by-frame sprite sequences? I found that no image model can do this well (with sufficient fidelity) - neither with one shot (full spritesheet), nor single frame conditioning. It would be great if an imagegen model could do this. What I do now (I use my own tool https://github.com/acatovic/ai-game-studio) is basically generate a reference image, then condition on that image to generate a very short video, then extract and prune frames. Then I get indie-level sprite fidelity about 90% of the time.

popalchemist | 3 hours ago

The task you're describing is a video model task, not an image model task. It's inherently temporal.

Generate a sprite in an image editor, then use a video model to make the loop you want; then turn the resulting video back into individual sprite images.

armcat | 2 hours ago

Sure and that's what I do, but a video can be seen as a causal generation on discreet sequence of images, each image conditioned on the one before it. It can also be seen as a series of image editing tasks. It would be cool to get this working in imagegen because of the amount of control you would get. Right now with video generation you can at best specify start and end frame and hope for the best.

popalchemist | 2 hours ago

Image edit models can probably do a grid, but the temporal accuracy / coherence will never match what a video model, which is really a world model, can do.

armcat | an hour ago

Regarding your world model statement. This is completely FALSE. Learning the visual statistics of a physical world is NOT the same thing as learning its causal dynamics. The difference is observational likelihood versus intervention-dependent dynamics. There have been great studies disproving video models as world models, like this ICML paper: https://proceedings.mlr.press/v267/kang25g.html. Unfortunately lot of people treat them as world models, mostly because of their ability to reproduce increasingly convincing physical behaviour without ever discovering the underlying physical laws. This is due to many things that I could write an essay about, but better conditioning, latent space represtnation, scaling etc, all make them look awesome.

I can still get absolutely insane results with MiniMax H3 - insane in the sense that it would not make sense at all and would make your head spin.

: popalchemist | 43 minutes ago
They are proto world models (lots written about this - flux being an example of a video model whose weights also power world-action-engines used in robots) in that they attempt to model causality in time, the thing that is required for what OP is asking for and which image models will never do because it is out of domain.

fuzzythrowaway | 3 hours ago

I like the interface; very useful for some use cases that would otherwise be quite frustrating. Dislike that it's yet another platform held back by arbitrary moderation. You can't make a bicycle for the mind that locks if you try to ride it in the wrong direction.

Trufa | 3 hours ago

So much negativity as usual and so little talk about the product, this is pretty impressive, well done, it seems to be filling decently a gap that everyone that has worked enough generating images with AI has faced.

: doctorpangloss | 2 hours ago
there basically isn't any authentic use for image generation, i would hardly say the negativity is unfounded

amelius | 3 hours ago

Yes, you can do that with AI now.

[OP] minimaxir | 3 hours ago

Of note is the OpenRouter endpoint has a promotional 50% discount, which is rare on image models: https://openrouter.ai/black-forest-labs/flux-3-image

: pwillia7 | 3 hours ago
open weights or bust
: vunderba | 2 hours ago
I think that’s less a product of OpenRouter’s generosity and more a result of promotional pricing coming directly from BFL, since other third-party vendors have it as well (Fal.ai, etc.).
https://bfl.ai/pricing

gAI | 3 hours ago

Love to see an AI lab outside of US/China releasing good models.

mromanuk | 2 hours ago

For a moment I was confused that this was a release of a new stable diffusion. What happened with Stable Diffusion?

: yorwba | 2 hours ago
Some of the original developers left Stability AI to found Black Forest Labs (so in a sense this is a successor to Stable Diffusion) and Stability AI pivoted to audio and milking their existing models.

skybrian | 2 hours ago

This isn't much of a test, but I bought $10 in credits on their playground and generated a test image. Not bad, but it didn't get the accordion keyboard right. Haven't tried editing yet.

https://pages.skybrian.com/flux3-image-test/

: swiftcoder | 2 hours ago
I wish they would work on fixing the "studio lighting" sheen that all these AI-generated humans have
: Doohickey-d | an hour ago
I also don't think there is a park that looks like that, in that location relative ton the Eiffel Tower (although I could be wrong).

imgbenchdude | 2 hours ago

Tried Flux 3 on a tiny subjective image benchmark I’m calling One Knee Wonder.

Exact prompt:

Generate a photorealistic image of M81 urban BDU camouflage cargo trousers, shown by themselves. One trouser leg should be posed with the knee lifted 30° from vertical.

Accurate reproduction of the M81 urban camouflage pattern is critical. Match its colors, shapes, scale, distribution, and overall appearance as faithfully as possible.

No person, other clothing, or props.

Ground truth swatch: https://commons.wikimedia.org/wiki/File:US_City_Camo_(M81_Ur...

Gemini 3 Pro Image (stronger pattern): https://i.postimg.cc/bZNQYYjx/2026-10-02-google-gemini-3-pro... Flux 3 (this run): https://i.postimg.cc/Xr7wNN0H/2026-10-02-black-forest-labs-f...

Flux 3 gets greyscale urban-ish trousers and a lifted knee, but the blotches aren’t real M81 Urban — softer / wrong geometry vs the swatch. Not the worst I’ve seen on this prompt; clearly behind the Gemini 3 Pro Image example above on pattern.

Curious what other models do on the same prompt.