Видео

Thanks ☺️

Thanks Ivo ☺️

Thanks ☺️

thanks uday :)

for generating images with AI i have on @pixaroma channel. For video only if I do in the future more. But for kling is quite simple you just upload an image and give a prompt nothing complicated, and in 1-3 tries you usually get a decent video

With kling ai, you can generate a video from image and if the lips are visible the entire 5 sec video you can add your audio and it will sync the lips

@AI2Play thanks I'll check out kling.

😀

thank you 🙂

try to add those and see what happens when you add it to image to video, the ai will start moving those around even if it supposed to be on glass, is hard to tell ai that something is moving through space and is see through glass, more details you add and floating things, more artefacts and mistakes the video will have.

I don't have enough credits to generate so many videos, and I can not afford to pay 100$ per month for more credits, and the short video was just an example of can be done, if you have enough credits you can do long videos

Not to mention it still looks off. I'm finding other AI tools more useful than full video generators. I'm working on a workflow right now that uses AI to make 3d models and HDRIs of characters and then animating them. I'm thinking of making a video about my workflow. If that sounds interesting let me know. I'm working on optimizing the models AI creates as well. I'm basically getting the help of AI rather than having AI do everything. I maintain higher creative control and outsource only things that are time consuming and not my area of expertise.

That’s true. I am a graphic designer and illustrator, and it has definitely affected my sales, but I need to adapt and learn new technologies if I want to stay relevant and continue working in design. When cameras first appeared, a lot of painters lost their jobs since people could simply press a button to get a picture. For a while, photography wasn’t even considered art, but now galleries display photos as art. Painters had more time to adapt; with AI, the change is happening so fast that we don’t have time to adjust. Like you, I have mixed feelings, but I do like technology, so I’ll experiment to see if there are tools that can make my job easier.

@AI2Play Yes, we definitely need to adapt. I like the camera example. The problem as you pointed out is how fast things are moving on nowadays. Another problem is that the general mindset is not that focused on quality anymore. A lot of content is more important than quality. Calling art 'content' is in itself diminishing and shows the lack of respect for artists and the work they do. I think automobiles are also a good example. People used horses for ages and cars changed the way people and goods were transported, how cities are built and pretty much everything we do in one way or another within a few years.

Thanks 🙂

Coming soon.. in our imagination 😂

I think we just saw the movie already! Every scene that transitioned into the next, in sync with the music, did make me imagine in my minds eye what was happening, and what will happen next

Thanks ☺️

Thanks Uday 🙂

thanks :)

I didn't tried it

depends on the upscaling, the normal uspcaling without generative model takes a few seconds like 3-4 seconds, the one that generate new things in it takes longer. Same in comfyui i tested a few models, if just upscale without creating something is very fast, but if you want to change the image then it takes time.

​​@@AI2Playso if want to add skin detail like pores, lines etc then it will take couple of minutes. So these models, you need to download separately or does it download automatically. I will check it out today. I would really like it if it does adds some skin details to my AI images. Yeah i don't upscale from comfy as well. I usually generate images from comfy using my workflow that generates and then fixes the face. And then i use A1111 (img to img, like from 1024 to 2048 resolution ) with my custom model to add skin details and then i use chainner to upscale (with lexica 4x model). It's a very good model for AI images, it also refines the details specially in cloths. Then i edit the image in photoshop if i need to add or fix something and then for add realistic color tones/filters.

@@zaselimgamingvideos yes the models are downloaded automatically first time you use it. I am not paid to promote it or something, I just use it for a while now and it did got better in time. I use a combination of comfyui, topaz and photoshop depends on the projects. I can get up to 4k in the comfyui with flux like I did on episode 12 on pixaroma channel

Depends on the video card I guess, is quite fast on rtx4090, compared with other upscalers. Anyway I usually only update on black friday, since then prices are lower :)

thank you 🙂

2 minutes for a 1024px upscaled 4 times on rtx4090 so is acceptable but om lower card probably takes more time

🙂

Thanks 😊

what's wrong with that?

@@AI2Play tutorial pleassee

@@newwen2102 I post behind the scene info in the ai2play-youtube channel from pixaroma server on discord discord.com/invite/gggpkVgBf3

Thanks Marcel ☺️

Thanks ☺️

Here it is starting already a month ahead 😂

thank you 🙂

klingai let you lipsync 5 sec on the video using either text and their voice, or existing audio. First you generate a video, then you select lipsync and it will let you know if can do lypsinc or not, depends if the mouth is visible the entire video or not.

Thank you ☺️

Thank you very much ☺️

Thanks ☺️🎃

11 hours 😁

@@AI2Play This is incredible! In any case, a very good application video for potential customers. Big praise!