81–90 of 233 posts
Not a single human face in these samples. I wonder how well it does on faces.
Saul Goodman if he was a character in Twin Peaks: https://media.discordapp.net/attachments/999426920376717513/... Generated with Midjourney Beta
Earlier quoted context omitted.
Google hasn't released squat . Google's product is vaporware and we shouldn't afford them any airtime until they release something usable. They're just trying to butt in and get press off of the backs of the teams actually working in the open, and that's super lame. Release your model, Google, or stop bragging and talking over the others here. You're greedily sucking oxygen out of the conversation, and as a trillion…
I kind of get the sentiment about openness but I think it's way more nuanced than you are making out. There are very good reasons for withholding SOTA models, primarily from the info hazard angle and avoiding escalating the capabilities race which is basically the biggest risk we have right now. Google / Deepmind have actually made some good decisions to try and slow down the race (such as waiting to publish).
Earlier quoted context omitted.
Is 3d a different problem, or a similar one but considerably harder? I'd expect the data encoding (vertices vs pixels) to change a bit about it but I'm not familiar enough to know.
Pixel values are discrete (length x width x r256 x g256 x b256) and vertex values are continuous, so that is one major difference. Secondly, there's vastly more labeled image data in the world than 3D data, so creating a CLMP (contrastive language and mesh pairing) model is harder. It's very late but I may be able to give a much better answer on more of the nuances of 3D generation tomorrow.
I can imagine you'd have the problem of stray floating voxels then, which isn't as noticeable when it happens with 2D pixels.
Every single time I see an article about a new AI model that has a section called "societal impact" I know immediately they are not releasing the model, the training set, nothing... It seems to be the kind of bullshit statement that those companies put in place of "we paid $500k training this model and we're not giving it for free to anyone".
These tools are amazing for prototyping. I had an idea for a promotional poster, and seeing my idea just by writing it felt like magic. The generated image had too many artifacts to use, but gave me a guideline to follow when creating the real thing in Pixlr. AI content generation (text, image, source code, video, music) will be a huge boon for prototyping where applied judiciously.
It worked okay - one issue was DALL-E wants to keep "style" consistent so any stray bit of debris greatly affected the interpretation, but I did in fact get 1 design idea out of it which changed how I think we'll do a bit of it.
These things in many ways are just extremely enhanced search tools - "describe what you want to see"
Is there an AI that creates realistic text from photos?
EDIT: Just found this[1] as well, though setup might also be a pain.
[0] https://softology.pro/tutorials/tensorflow/tensorflow.htm [1] https://replicate.com/methexis-inc/img2prompt
Earlier quoted context omitted.
Someone on the midjourney discord is making a comic with images generated by the bot. Another person is making a Magic The Gathering card pack with generated art (it looks good too!). People are already using it for stock photos One murky area we're still far away from but I'm curious to follow the developments on: AI-generated movies. Once generated clips gets good, what if some movie buff can just generate a movie,…
How do they get consistent looks? I mean if you are using it for a comic book your characters should look the same throughout the story. From my experience, the results between prompts are completely different even with minor variations.
Here's a slew of images (1 through 5) I generated all from the same seed and same prompt sans a word or two: https://www.instagram.com/p/Chg60Fou6xB/
Is there an AI that creates realistic text from photos?
There are some obvious mistakes in tools like this. Such as: Human faces are wrong, writing is usually scrambled, fingers look weird etc... Do you know if we need to have a major breakthrough similar to what happened 6 months ago to fix this or could these be fixed with incremental improvements in current techniques / datasets?
Also, I seem to recall that at least some models deliberately harmed generation of human faces (e.g. by selection of training data) to draw away attention from the deepfake/fakenews usecases and the related ethical,political and PR issues; I would assume that if any of them wanted to actually try and make specifically faces look good, that would be purely a matter of some engineering work without any breakthroughs needed - I mean, we have evidence from face-specific models that the same technical architecture can do decent faces.