super soup sound like a Katy Perry song 😆

they of course dont allow that cause people would be stealing voice to make their ai songs, left and right

Today they added Flux Dev Canny, Redux, and Depth LoRAs to the ComfyUI block on Glif. One free way to use them.

can you please make an install guide for comfy ui with the correct workflow

14:40 Two Guys One Lemon 🤠🍋🤠

As a developer, I can build this now. I’m actually hoping these companies DON’T release these things right away, because I have a strong advantage and can sell these solutions for 10’s of thousands of dollars right now.

About the character consistency, I think they meant that the output image won't match the initial input image you give it, but if you generate 4 outputs from the same input image, those will be all consistent between themselves but not with the original input.

Thanks for the thorough breakdown video, this looks amazing.

Does it gets expensive for an Designer use it a lot from API?

I wanna see them ad in LORA' s as well as face swamping in flux

Wow, I just turned my rubber duck into Matt, but it scared me, so I'm changing it back. Great video.

Character consistency is the holy grail of ai image generation. OpenAI seemed to have stumbled across the answer with their talk of making ChatGPT "multi-modal" last spring, but as far as I can tell, they never released it and haven't mentioned it since.

I write my lyrics but this is awesome

Loving the new models! Im pretty sure u would get better masking/Inpainting results if u broke your prompts up, like get your moon surface background the way you like, then add your green alien, then the Earth in space, instead of one shot prompting it...

I'm just wondering when is FLUX 1.1 [Dev]

Love watching your videos man! Keep up the good work bro

14:51 that would be a good thumbnail.

47MI 137 L 20 C 278K S 1 587 V NOV 21 2024

i don't know photoshop generative fill seems better and easier.

Flux did MUCH better with your hair than ideogram. Excited to play!

The Flux.1 Depth model doesn't estimate the depth from an existing image, it's the other way around. It generates an image that could match the existing depth map it's given as input. They're using another (probably third party) model to generate the depth map from the input image.

I'm still going to use dall-e mostly because it's processing the longest prompts

RAW = huge

Maybe create a comparison between websites offering FLUX Pro ?

Black Forest Labs needs a validation process, ideally a central functional website that is theirs.

People going to use you as a template, just a warning @1:57

I’m afraid that soon we might treat music as useless furniture

Matt what's the ring you wear? Looking at the RingConn gen 2 myself as there's no monthly sub cost

Fourth

flux more like flex

Let us know when we can download such things on our own computer. ty

Huge thanks to everyone for watching! Now would be a great time to leave a like and maybe even subscribe if you're enjoying my content :)

third

Lol not going to lie you should release the “pass the butter” song that was fire

First

Being able to create a persona from uploaded audio may be problematic for Suno since you could upload another artist's voice?

I've been hearing a lot of people talk about "laser sound effects" in V4?

I tried to make a song for my wife but it keeps generating a female voice to the song. How can I make it to where Suno has a male voice generated as the singer of the song? Is there a prompt I need to input? Hope to hear from you soon

Im sure the layer/tile/cloud tellemitry is faking that anything you just did as an opperator, as diverse as it might be is not converted to a serialized api action trunk _/\_ tentacle.

I need a real assistant not a talkie

That first song was pretty lit. I still remember the video you did on the amazing new "song" generator that basically made static-filled beeps and boops. That must have been months ago. Good times.

Wow this sounds amazing!

I don't care much for the vocal stuff, the stuff at the 30min mark was very impressive and inspiring for me as a music producer.

I haven't seen that many people talking about it here in the comments, but I have noticed some major problems with V4. Most noticeably in the beginning of songs, its some weird artifacts or wobbly ringing sound on every single song I make.

PLEASE HELP ME GUYS! I wanna remaster a song that i’ve done with a different profile then my main account (where i have a paid subscription with the V4) but i can’t see the “get the whole song” option that i see with others people song in the app home. I’ve made the song public with the other account, but still i don’t see the option. U need another subscription in the other account? Or there’s a way without it? Please let me know 🙏🏻🙏🏻🙏🏻 thanks a lot

Matt ''Pretty Darn Good'' VidPro.

just record your voice with all the sounds you can make in 2 minutes, upload it.. and you will sing.. check EQORIA songs

That "Pass the Butter" song slams.

Nice, wonder if Producers/DJ's will be replaced by A.I as well, or maybe even the crowd lol