Using a single model to unify all image generation tasks, including many computer vision tasks and visual language reasoning, could transform future image generation models. Although some capabilities, like text-to-image, aren't perfect, it's a significant advancement. The model's ability to integrate so many tasks with strong instruction-following skills is impressive. I'm excited about the broad impact OmniGen could have on future research.
Show HN: AI OmniGen – AI Image Generator with Consistent Visuals
31–40 of 60 posts
Re: Show HN: AI OmniGen – AI Image Generator with Consistent Visuals
#32Earlier quoted context omitted.
The simplest commercial product for finetuning your own model is probably Adobe firefly, although there’s no API access support yet. But there are cheap and only slightly more involved options like Replicate or Civit.ai. Replicate has solid API support. Check out: https://replicate.com/blog/fine-tune-flux
Is it Flux 1 possible to download and deploy to my own server? (And make a simple API on top of it?) I don't need fine tuning.
The easiest flux api I’ve seen is with Fal.ai
It is expensive though- Flux dev images are like $0.035/image
Re: Show HN: AI OmniGen – AI Image Generator with Consistent Visuals
#33With consistent representation of characters, are we now on the precipice of a Cambrian explosion of manga/graphic novels/comics?
I would say we already had one of those. There's more hand crafted human made content available than anyone cares to read.
While this will enable a certain degree of more spam it will more importantly, on the positive side of things, democratize the creative process to those who want to tell a story in images but lack the skill and resources to churn it out traditionally.
Re: Show HN: AI OmniGen – AI Image Generator with Consistent Visuals
#34Anyone know how it handles Text? That's kind of my deal breaker, I like Ideogram for it's ability to do really cool fonts, etc.
Re: Show HN: AI OmniGen – AI Image Generator with Consistent Visuals
#35I am working on a API to generate avatars/profile pics based on a prompt. I tried looking for train my own model bt I think it's a titanic task and impossible to do it myself. Is my best solution use an external API and then crop the face for what was generated?
You can use a few controlnet templates and then whatever model you like and consistently get the posture correct. The diffusion plugin for Krita is a great playground for exploring this.
Re: Show HN: AI OmniGen – AI Image Generator with Consistent Visuals
#36https://github.com/VectorSpaceLab/OmniGen
Cool they even released the weights![1] didn't expect that from the tone of the release post to be honest.
Re: Show HN: AI OmniGen – AI Image Generator with Consistent Visuals
#37Earlier quoted context omitted.
Same, I left running for half an hour but nothing happened.
The author updated their code a couple of days ago, and it runs smoothly on my end, producing results in about one minute. https://github.com/VectorSpaceLab/OmniGen
Left it running 1 hour nothing happens. Maybe this is a social experiment.
Re: Show HN: AI OmniGen – AI Image Generator with Consistent Visuals
#38it seems like there's a lot of potential for abuse if you can get it to generate ai images of real people reliably.
We literally already had AI fake porn of Taylor Swift making the rounds a while ago. Prepare for women in public positions to face that kind of bullshit more frequently.
Re: Show HN: AI OmniGen – AI Image Generator with Consistent Visuals
#39Earlier quoted context omitted.
The author updated their code a couple of days ago, and it runs smoothly on my end, producing results in about one minute. https://github.com/VectorSpaceLab/OmniGen
Left it running 1 hour nothing happens. Maybe this is a social experiment.
Left it running overnight. Set output to 512x512 in an attempt to speed things up. Nothing.
Re: Show HN: AI OmniGen – AI Image Generator with Consistent Visuals
#40With consistent representation of characters, are we now on the precipice of a Cambrian explosion of manga/graphic novels/comics?
It’s not really consistent - or anymore consistent than, say, SDXL with IP adapter. Even in their example images the character they’ve input comes out wearing different clothes.