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

131–140 of 140 posts

Re: FLUX.1 Kontext

#131

Post by turnsout »

pkkkzip wrote: post #121
fc417fc802 wrote: post #84

Earlier quoted context omitted.

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.

Calling out overt racism is not “hypersensitivity” and in what fucking world could it be racism? This mentality is why the tech industry is so screwed up.

Re: FLUX.1 Kontext

#132

Post by shift8 »

a2128 wrote: post #48
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…

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

anything is more accurate than the llms at generating images. chatgpt, google gemini, all of them... they're not optimized for image generation. it's why veo is an entirely different model from google for example. and even veo isn't the best video model either. people dedicated to images and video are just spending more time here (such as black forest labs). as a result, those specialized models are better.

Re: FLUX.1 Kontext

#135

Post by jackdawipper »

vunderba wrote: post #45

Some of these samples are rather cherry picked. Has anyone actually tried the professional headshot app of the "Kontext Apps"? https://replicate.com/flux-kontext-apps I've thrown half a dozen pictures of myself at it and it just completely replaced me with somebody else. To be fair, the final headshot does look very professional.

so "consistent character" is just marketing hype then, not really possible?

Re: FLUX.1 Kontext

#136

Post by shamsiev »

jackdawipper wrote: post #135
vunderba wrote: post #45

Some of these samples are rather cherry picked. Has anyone actually tried the professional headshot app of the "Kontext Apps"? https://replicate.com/flux-kontext-apps I've thrown half a dozen pictures of myself at it and it just completely replaced me with somebody else. To be fair, the final headshot does look very professional.

so "consistent character" is just marketing hype then, not really possible?

Totally possible. Try `Draw side view of this character` or `Draw this character looking directly at viewer`.

Re: FLUX.1 Kontext

#137

Post by sigmoid10 »

dragonwriter wrote: post #50
sigmoid10 wrote: post #9

Earlier quoted context omitted.

Distilled is a real downer, but I guess those AI startup CEOs still gotta eat.

The open community has a done a lot with the open-weights distilled models from Black Forest Labs already, one of the more radical being Chroma: https://huggingface.co/lodestones/Chroma

I don't doubt that people can do nice things with them. But imagine what they could do with the actual model.

Re: FLUX.1 Kontext

#138

Post by Gothmog69 »

shift8 wrote: post #132
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

anything is more accurate than the llms at generating images. chatgpt, google gemini, all of them... they're not optimized for image generation. it's why veo is an entirely different model from google for example. and even veo isn't the best video model either. people dedicated to images and video are just spending more time here (such as black forest labs). as a result, those specialized models are better.

What's better than veo?

Re: FLUX.1 Kontext

#139

Post by AWTom »

vunderba wrote: post #41

I'm debating whether to add the FLUX Kontext model to my GenAI image comparison site. The Max variant of the model definitely scores higher in prompt adherence nearly doubling Flux 1.dev score but still falling short of OpenAI's gpt-image-1 which (visual fidelity aside) is sitting at the top of the leaderboard. I liked keeping Flux 1.D around just to have a nice baseline for local GenAI capabilities. https://genai-sh…

Thanks for sharing, this was a great read.
Post reply on HN