Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

FLUX.1 Kontext

bfl.ai

Post reply on HN
Print view View original

121–130 of 140 posts

Re: FLUX.1 Kontext

#121

Post by pkkkzip »

fc417fc802 wrote: post #84
turnsout wrote: post #74

Earlier quoted context omitted.

Wow, that is some straight-up overt racism. You should be ashamed.

It reads as racist if you parse it as (skin tone and attractiveness) but if you instead parse it as (skin tone) and (attractiveness), ie as two entirely unrelated characteristics of the output, then it reads as nothing more than a claim about relative differences in behavior between models. Of course, given the sensitivity of the topic it is arguably somewhat inappropriate to make such observations without sufficient…

I find that people who are hypersensitive to racism are usually themselves pretty racist. It's like people who are aroused by something taboo are usually the biggest critic. I forget what this phenomena is called.

Re: FLUX.1 Kontext

#122

Post by claudefocan »

sujayk_33 wrote: post #117

So here is my understanding of current native image generation scenario, I might be wrong so please correct me, I'm still learning it and I'd appreaciate the help. First time native image gen was introduced in Gemini 1.5 Flash if I'm not wrong, and then OpenAI was released for 4o which took over the internet by Ghibli Art. We have been getting good quality images from almost all image generators like Midjourney, Open…

This is not fully correct.

The people behind flux are the authors of stable diffusion paper that dates back to 2022.

Openai initially had dallee but stable diffusion was a massive improvement on dallee.

Then openai inspired itself from stable diffusion for gpt image

Re: FLUX.1 Kontext

#123

Post by anibalin »

echelon wrote: post #77
a2128 wrote: post #48

Earlier quoted context omitted.

It seems more accurate than 4o image generation in terms of preserving original details. If I give it my 3D animal character and ask it for a minor change like changing the lighting, 4o will completely mangle the face of my character, it will change the body and other details slightly. This Flux model keeps the visible geometry almost perfectly the same even when asked to significantly change the pose or lighting

gpt-image-1 (aka "4o") is still the most useful general purpose image model, but damn does this come close. I'm deep in this space and feel really good about FLUX.1 Kontext. It fills a much-needed gap, and it makes sure that OpenAI / Google aren't the runaway victors of images and video. Prior to gpt-image-1, the biggest problems in images were: - prompt adherence - generation quality - instructiveness (eg. "put the…

Thanks for the detailed post!

Re: FLUX.1 Kontext

#124

Post by rmorey »

sujayk_33 wrote: post #117

So here is my understanding of current native image generation scenario, I might be wrong so please correct me, I'm still learning it and I'd appreaciate the help. First time native image gen was introduced in Gemini 1.5 Flash if I'm not wrong, and then OpenAI was released for 4o which took over the internet by Ghibli Art. We have been getting good quality images from almost all image generators like Midjourney, Open…

I think actually 4o image generation in ChatGPT is still a tool call with a prompt to an “image_gen” tool, I don’t think the generator receives the full context of the conversation. If you do a ChatGPT data export and inspect the record of a conversation using 4o image gen, you’ll see it’s a tool call with a distinct prompt, much like it was with dalle. And if you pass an image in as context, it’ll pass that to the tool as well.

I imagine this is for anti-jailbreak moderation reasons, which is understandable

Re: FLUX.1 Kontext

#127

Post by throwaway314155 »

amazingamazing wrote: post #80
throwaway314155 wrote: post #60

Earlier quoted context omitted.

Even if you provide another image (which you totally can btw) the model is still generalizing predictions enough that you can say it's just making a strong guess about what is concealed. I guess my main point is "this is where you draw the line? at a mostly accurate reconstruction of a partial of someone's face?" this was science fiction a few years ago. Training the model to accept two images (which it can, just not…

is it mostly accurate though? how would you know? suppose you had an asian woman whose face is entirely covered with snow. sure you could tell AI to remove the snow and some face will be revealed, but who is to say it's accurate? that's why traditionally you have a reference input.

> sure you could tell AI to remove the snow and some face will be revealed, but who is to say it's accurate? that's why traditionally you have a reference input.

As I stated a few times, the model HAS SUPPORT FOR MULTIPLE IMAGES. The article here doesn't try your very specific reference-image-benchmark but that doesn't mean you can't do it yourself - and it also doesn't imply there's anything wrong with the article or BFL - they're merely presenting a common usecase - not defining how the model should be used.

Re: FLUX.1 Kontext

#128

Post by geekkong »

rvz wrote: post #7
anjneymidha wrote: post #5

Technical report here for those curious: https://cdn.sanity.io/files/gsvmb6gz/production/880b07220899...

Unfortunately, nobody wants to read the report, but what they are really after is to download the open-weight model. So they can take it and run with it. (No contributing back either).

[dead]

Re: FLUX.1 Kontext

#129

Post by geekkong »

minimaxir wrote: post #21

Currently am testing this out (using the Replicate endpoint: https://replicate.com/black-forest-labs/flux-kontext-pro ). Replicate also hosts "apps" with examples using FLUX Kontext for some common use cases of image editing: https://replicate.com/flux-kontext-apps It's pretty good: quality of the generated images is similar to that of GPT-4o image generation if you were using it for simple image-to-image generations…

[dead]

Re: FLUX.1 Kontext

#130

Post by turnsout »

fc417fc802 wrote: post #84
turnsout wrote: post #74

Earlier quoted context omitted.

Wow, that is some straight-up overt racism. You should be ashamed.

It reads as racist if you parse it as (skin tone and attractiveness) but if you instead parse it as (skin tone) and (attractiveness), ie as two entirely unrelated characteristics of the output, then it reads as nothing more than a claim about relative differences in behavior between models. Of course, given the sensitivity of the topic it is arguably somewhat inappropriate to make such observations without sufficient…

You have your head in your ass. Read the text:

> Chinese text2image generate attractive and more light skinned humans. > I think this is another area where Chinese AI models shine.

That is racism. There simply is no other way to classify it.

Post reply on HN