Thanks for making learning so fun and inspiring! Your videos have brought me so much joy and knowledge. Wishing you a wonderful Christmas and happy holidays!
You are a champion Pixaroma! Back in the days of A1111, it was easy to use IP Adapter to instantly maintain constant characters. Is it possible with Flux & comfy somehow? Maybe with PULID or something else? Would love to see a tutorial about it (without training a Lora for hours). I really miss the ease of IP Adapter. Thanks!
I don't use ipadapter and pulid because it use insightface that causes a lot of problems and also is not for commercial use so i can not use it. I am waiting for better solutions. And i am training lora either on openart but has like only 2 models training per month but is super fast only a few minutes, either on tensor art that is slower but i can train more. I didn't train locally yet, it only cost a few dollars, i am sure there are more sites for training and for me Lora worked ok with flux
Soon we'll get to the point where a photo or video can't be considered evidence or proof. I wonder what will happen then? Will “experts” (yobs with a paper expert) say what is true and what is not? PS: Nice work. 👍
Unfortunately you cannot extend VRAM, you need to replace it with a better video card 😁 but I will tell Santa and if you have been good he will know if to send it to you or not 😂
Видео достойно уваженїя, это лучшее, что можно сдѣлать на сегодняшнїй день. Но если честно - на выходѣ пока еще получается кринжово, это не упрекъ художнику, просто пока еще ИИ не достигъ уровня даже самого невзрачного живого футажа. Какъ бы это генеративное ИИ не оказалось дегенеративным пузыремъ, въ который вложены баснословныя деньги, а въ результатѣ - получился выхлопъ изъ трубы. Но не бѫдемъ о плохомъ наканунѣ праздника. Поздравляѫ съ Рождествомъ! Въ новомъ году все обязательно станетъ лучше. The video is worthy of respect, it's the best thing you can do today. But to be honest, the output is still cringe-worthy, this is not a reproach to the artist, it's just that the AI has not yet reached the level of even the most unsightly live footage. This generative AI may not turn out to be a degenerative bubble, which has been invested with fabulous money, and the result is the exhaust from the pipe. But let's not talk about bad things on the eve of a holiday. Merry Christmas! Everything will definitely be better in the new year.
Wonderful video. Have a fantastic Christmas and a happy new year.
Happy holidays Marcel ☺️🎄❄️
May your holidays be merry and bright, and the new year bring wonderful moments to cherish.
Happy holidays ivo, thanks for all the help ☺️🎄
Happy holidays pixaroma 🎁🎄☃️
Happy holidays Uday ☺️
Excellent! Joyeuses fêtes à vous de même!
Merci à toi aussi
I LOVED!!! HAPPY HOLIDAYS 🎅🎅🎅
Thanks, happy holidays 🎄🎅
😂
😊
👍
Watched it three times, can't stop laughing!
Thank you!
Happy Holidays. 🎅
🤣
Happy holidays 😁🎅
Thanks for making learning so fun and inspiring! Your videos have brought me so much joy and knowledge. Wishing you a wonderful Christmas and happy holidays!
Thanks, happy holidays ☺️🎄
Happy holidays, Pixaroma and all.
Happy holidays ☺️
Best video 2024,
I saw.
You are a champion Pixaroma! Back in the days of A1111, it was easy to use IP Adapter to instantly maintain constant characters. Is it possible with Flux & comfy somehow? Maybe with PULID or something else? Would love to see a tutorial about it (without training a Lora for hours). I really miss the ease of IP Adapter. Thanks!
I don't use ipadapter and pulid because it use insightface that causes a lot of problems and also is not for commercial use so i can not use it. I am waiting for better solutions. And i am training lora either on openart but has like only 2 models training per month but is super fast only a few minutes, either on tensor art that is slower but i can train more. I didn't train locally yet, it only cost a few dollars, i am sure there are more sites for training and for me Lora worked ok with flux
it's really awesome, #PANKY :)
Thanks ☺️
When is the tutorial video coming?
I will have a tutorial for something similar on 28 December on the ai2play channel ☺️
Soon we'll get to the point where a photo or video can't be considered evidence or proof. I wonder what will happen then? Will “experts” (yobs with a paper expert) say what is true and what is not?
PS: Nice work. 👍
I guess we will see, probably the law needs to change and adapt to new technology
is the song also ai xD?
Yes 😁
Please send me VRAM. I'm stuck at 8 GB 🎅
Unfortunately you cannot extend VRAM, you need to replace it with a better video card 😁 but I will tell Santa and if you have been good he will know if to send it to you or not 😂
Видео достойно уваженїя, это лучшее, что можно сдѣлать на сегодняшнїй день. Но если честно - на выходѣ пока еще получается кринжово, это не упрекъ художнику, просто пока еще ИИ не достигъ уровня даже самого невзрачного живого футажа. Какъ бы это генеративное ИИ не оказалось дегенеративным пузыремъ, въ который вложены баснословныя деньги, а въ результатѣ - получился выхлопъ изъ трубы. Но не бѫдемъ о плохомъ наканунѣ праздника. Поздравляѫ съ Рождествомъ! Въ новомъ году все обязательно станетъ лучше.
The video is worthy of respect, it's the best thing you can do today. But to be honest, the output is still cringe-worthy, this is not a reproach to the artist, it's just that the AI has not yet reached the level of even the most unsightly live footage. This generative AI may not turn out to be a degenerative bubble, which has been invested with fabulous money, and the result is the exhaust from the pipe. But let's not talk about bad things on the eve of a holiday. Merry Christmas! Everything will definitely be better in the new year.
I am sure it will get better and better each year, The same happened with image generation, we see improvement each month, happy holidays ☺️