Loading video...
Video Failed to Load
✨ Added Gemini 2's AI new experimental edit functionality to Photo AI! It's the state of the art model for editing photos with prompts I think It's just one button in Photo AI called [ 📝 AI Edit ] then you type a prompt in a JS prompt() window... show more
653,195 views • 1 year ago •via X (Twitter)
9 Comments
@levelsio1 year ago
A lot of thanks to @OfficialLoganK here
Ðavid Swift.1 year ago
Woah. That was quick !!
ShadowGirl1 year ago
AI-powered edits, wow!
@levelsio1 year ago
Blocked for AI reply
0x201 year ago
How is it better?
leykun1 year ago
The rate limit for the gemini flash thinking image gen is around 1500/day max. How you handling it?
@levelsio1 year ago
I'm not handling it :D Will see what happens and if users edit more than that
Clips | Unruggables1 year ago
Excellent work! Excited to see your AI-powered editing progress.
@levelsio1 year ago
Blocked for AI reply
![🎨 Flux's new editing model Kontext is now live on Photo AI Use [ ✨ AI Edit ] to prompt edit any (AI) photo into what you want to see Before it ran on OpenAI's model and then Google AI's Gemini model, but Flux Kontext looks quite ahead from what I can see 👨🦲 Here's me turning myself bald:](https://image.24vids.com/tw-1928227768296509609/amplify_video_thumb/1928227304146083841/img/6VGbd88eR4VDqpMB.jpg)
![📲 You can also now import external photos into your gallery on Photo AI, not just ones you generated Then you can do anything with those external pics as you'd normally do, like [ Make video ] or [ Upscale ] etc. Here's a pic of me and Beff – e/acc which I then [ AI Edit ] to put us in a futuristic GPU factory The new AI edit model Flux Kontext is great but even that one still has some problems with maintaining resemblance, I think once models let us add a reference pic (esp for video) it will maintain faces better, but it's already pretty cool (and fast thanks to fal!)](https://image.24vids.com/tw-1928230535437910290/amplify_video_thumb/1928230074299351040/img/fdxJgHc6d8kwHEkJ.jpg)
![✨ Made a new mini feature on Photo AI: [ Grab from 3d model ] So the problem is we're at that stage in time (typical for AI) where image-to-3d models are not good enough but are fun to play with, but we know they'll be good enough in 1-2 years With [ Make 3d model ] you already can turn any Photo AI pic into a 3d model but it still looks hyper clunky and deformed, but it works! One cool idea I had to make that more useful and made now: Let people make a 3d model then change the view of the it with the 3d viewer, then press [ o ] and it grabs a frame of the 3d That image you can then [ Remix ] (img2img), and it becomes a real photo again and that in turn you can then turn into a video again with [ Make video ] So that essentially gives you a fully freeform camera position control to take photos with One thing I need to fix is the background/skybox, I kinda need to take the original photo and remove the person and just get the background for the 3d model viewer, in this case it should be white, but it's a start!](https://image.24vids.com/tw-1940749265615179946/amplify_video_thumb/1940747973064822784/img/P___fqKPPJyKeVwq.jpg)
![✨ You can now finally take group photos with Photo AI! Group photos has been one of the most requested features on Photo AI for ages but AI models never properly let you do them without a lot of hacking, simply because finetuning AI models (training a model of yourself) means overwriting the ENTIRE concept of "people" with photos of yourself, so generating a group photo would mean getting a lot of clones of yourself which isn't what you want Trying to combine finetunes (LoRas) of 2 different people usually results in creating a group of people that have properties of both, which is also not what you want, regional conditioning kinda works but also not optimal With Flux Kontext though I can just combine 2 different photos, while mostly maintaining their resemblance In Photo AI, you press [ Select ], then select your pics, then press [ Combine photos ] and 10 seconds later you have your group photo The quality is not superb yet, but it's good to get this feature out because the AI models will keep improving, so in 6 months or so this will look perfect Live now on Photo AI 😊😊😊 Thanks to fal for hosting and Black Forest Labs for developing Flux Kontext for all of us](https://image.24vids.com/tw-1930312262859804911/amplify_video_thumb/1930310062477602816/img/sG0lQBQY7AFqoszY.jpg)
![✨ First AI talking video made from within Photo AI with the new [ 💬 Make talking video ] interface AI photo -> AI video -> AI lipsync -> AI captions Obviously not very passable yet, BUT it's a start and with voice and lipsync models improving so fast I think it'll be passable in 3-6 months One thing is severely missing is background sounds which I didn't add here manually just to show the state of things, is there any good TTS API that DOES have bg noise? Captions are by CapCut, but it'd be nice to be able to do that in-app with Photo AI too, not sure where to start with that though Again cool thing of this vs HeyGen is it has no limits to where you wanna place yourself or your model, the source is just a prompted AI photo in Photo AI that becomes a talking video with 2 clicks](https://image.24vids.com/tw-1850511780507762845/ext_tw_video_thumb/1850510651954696192/pu/img/fgG6LKftqCCT4HRA.jpg)
![Okay it works!!!! Now making the interface for it, I named it [ 👋 Hold a product ] You upload your product photo, you take a photo and it generates one with your AI model holding it Then from there you can press [ Talking video ], write a script and your AI model will present the product for you The AI character is from @lucataco93's tweets 😊](https://image.24vids.com/tw-1957916771245257007/amplify_video_thumb/1957916450657636352/img/-zaJkRzfikrvjkjL.jpg)
![✨ I made a 100% AI video of a single night in 🇩🇪 Berlin's underground techno scene Doing an AI shoot is very much like a real life shoot, you have to prepare locations, settings, outfits and models, you can do the same: 1) First I generated photos with the [ 🇩🇪 Berlin nightlife ] photo pack on they're all non-existing AI people except me and my gf 2) Then I put the pics I liked in Kling AI to make them into 10 second videos (with Professional Mode), soon I'll have API access and it'll be one-click inside Photo AI to turn a photo into a 10-sec video, it then takes about 5 minutes to make a video. It's not always great, especially dancing is hard to get right! 3) Then I wanted to have a German narrator talking about Berlin's techno nights in a poetic way like a documentary, so I asked ChatGPT 4o: "write in the style of a cult German novelist about the Berlin techno scene" I then copied that text into Eleven Labs and selected a German AI voice 4) I then collected all the videos, the music and the audio narrator and edited them together in Final Cut Pro adding music from HÖR and adding audio effects 5) Then I added English captions with CapCut Time to make it: 3 hours for 1 minute of video I hope you like it! My dream is to have this entire pipeline in Photo AI at some point. Connecting to Kling AI's video API is the first step to that. Imagine just writing a prompt and you end up with a video like this without all the work Credits: Music: Asquith - Let Me (Rave Mix) [ASQ004] Barbax - Si Vis Pacem Para Bellum (Original Mix) Mixed by Ellen Allien @ HÖR Video: 100% AI characters and video by Photo AI Edited by me Narrator voice: 100% written by ChatGPT 4o 100% narrated by Eleven Labs AI voice](https://image.24vids.com/tw-1836017413650829587/ext_tw_video_thumb/1836016292328865792/pu/img/pZMR0VCR6sYaD8Vj.jpg)
![✨ I asked ChatGPT what more photo packs to add to Photo AI It suggested an [ 🎌 Anime Character Creator ] which seems to be a great to rank on for traffic, as ppl wanna turn themselves into anime characters So I made it! 😊 Then also used Photo AI to make videos of the pics, added a Suno AI soundtrack and stitched it together in Final Cut Pro ~1 hour to make 1 minute of video](https://image.24vids.com/tw-1886166772061024560/ext_tw_video_thumb/1886165358794395648/pu/img/SI_54iDwzS0wd7XC.jpg)
