11 ай бұрын
Пікірлер
@violentpixelation5486 13 күн бұрын
💯👍 true. Great tip!
@RezaulKarimArif 14 күн бұрын
Thanks
@violentpixelation5486 14 күн бұрын
❤👍🔥💯 #Flux #Lora
@dspdsp1279 14 күн бұрын
What video editing software do you use?
@violentpixelation5486 14 күн бұрын
I did just try SD 3.5 out inside of Supermachine and WOW 💯
@violentpixelation5486 14 күн бұрын
🎉🔥👍 YEEESSSS! ❤ I've bought a Supermachine license yesterday. Great timing! 😁 Hats off to the Supermachine team!
@violentpixelation5486 15 күн бұрын
Just took advantage off the appsumo life-time deal and after generating a handful of images.....I'm not looking back! You guys created an image generating powerhouse. 🔥🔥🔥 Hats off!
@StickyPedro77 18 күн бұрын
Is Supermachine the right tool for creating great looking, realistic food photography? And how far can you get with 1000 credits of experience?
@uri-re4bq 19 күн бұрын
Thanks for the video. The only thing I miss is the possibility to store my settings, like a prechecked model. For example, if I start with Supermachine I always want to start with Amatuer Photo, 4 copies and a a width of 16:9. It would be great to have it. Thks
@doyourown 22 күн бұрын
Hi, can you also show us how to do this in Zerowork?
@neoacla Ай бұрын
Flux logos generation coming?
@alekosbehrens Ай бұрын
When comes the supermachine music generator?! 😂 no, for real: how are you made this? 🙏🏻
@martinb3483 Ай бұрын
super cool presentation with this music. 🙂
@martinb3483 Ай бұрын
negative prompt: large breasts
@astorymedia Ай бұрын
Well done mr!
@UldisBiz Ай бұрын
Stuart, you are a beast, man! I bought into Supermachine time ago, and at the time I wasn't even sure if I'll be using it much. Also, I had a bit of a concern that it will be one of the projects that will perish after the initial hype and enthusiasm settles, especially considering how much competition you've got for these types of tools. But, man, you just keep coming up with all these features and improvements, and posting a lot of really, really helpful tutorials. I feel like if I give enough time to learn to improve my prompts and settings I choose, I can get all my image generation needs done with Supermachine. Any tech startup or pretty much any tech company could learn from you. I'm one of your very happy customers, and I wish you and your team a lot of success. P.S. Secret Labs chair. Is it worth it? I'm working behind the desk a lot, have been considering an upgrade... ;)
@supermachineart Ай бұрын
haha, we'll continue to make it better. I like the XL Secret Lab chairs. Very roomie! I do have a standing desk though so I can stand sometimes also.
@ricbrajack Ай бұрын
Can you upload two images to make one new one?
@supermachineart Ай бұрын
only one images currently.
@madrooky1398 Ай бұрын
I find img2img more interesting and useful with lower denoise rates, but also depending on what type of scheduler is set up. Flux default "simple" scheduler is fairly random and changes quite a bit even with low denoise, the "Beta" scheduler on the other hand is very rigid in the composition, which can be great if you want to upscale without too much change, or improve images with broken details like hands or eyes. It would keep the position of the hand but improve the fingers for instance. When you use a denoise of 0.8 upwards there is almost no point using img2img to begin with, especially since Flux can be prompted so precisely for all kinds of framings and compositions.
@haljordan1575 Ай бұрын
can you inpaint?
@supermachineart Ай бұрын
not at the moment but we would like to add it in the future.
@davidspyres Ай бұрын
Wow.....love this Stuart!!!! I sent you an email about the possibility of adding Ideogram 2.0 as well 😁
@astorymedia 2 ай бұрын
lovely way to create own imagery
@djkemi_ 2 ай бұрын
Hör zu Bob, was du da in dem Clip treibst ergibt gar keinen Sinn. Immer die Möchtegern Tutors die glauben sie sind der käs.
@UldisBiz 2 ай бұрын
Not sure if this is the right place to ask but I'll ask anyway. How to decide which resolution to choose for a generation? I've been always using the largest number in a fear that I will generate an awesome outcome but it will be unusable, and I won't be able to get the same result again. If you could elaborate on this, please. Much appreciated. Thanks.
@UldisBiz 2 ай бұрын
Can I upload multiple pictures of the same person from different perspectives to provide better training? Can it be used for imaginary creatures, animals or only humans?
@UldisBiz 2 ай бұрын
Underrated tool. Love constant innovation and updates.
@karmeshvar_deva 3 ай бұрын
Yes, thank you for adding it. It is truly a great model
@imtechnologyltd 3 ай бұрын
Just had a quick test and I like it
@saynomore1291 3 ай бұрын
will it become available for your api machine? that would be really next level
@supermachineart 3 ай бұрын
we do plan on making it
@saynomore1291 3 ай бұрын
any ETA?
@trynninlakorn6786 3 ай бұрын
Just tried it on Supermachine and really like it! I would say it's even better than Dalle. How it understands our writing language is another level :)
@sushka4122 3 ай бұрын
does ControlNet works over API?
@davidhuff6225 3 ай бұрын
So when should you increase the step count?
@udo9999 4 ай бұрын
Hey, are you the same guy from the Wiz Write channel? Interesting. Nice.
@saynomore1291 4 ай бұрын
Thanks - this helped. I finally figured it out. An additional question though: say I would like to transmit an additional information (e.g. a name of a character) so I can later match it back in a database: how would I set this up?
@supermachineart 4 ай бұрын
I think that a job id or similar so you can match the request to the response makes sense, will look into making that happen.
@jijojosein 4 күн бұрын
Hi @@supermachineart is this feature added? Thank you
@larry_james 4 ай бұрын
Supermachine seems to work really well when the focus of the image is a person, how does it work with inanimate objects such as furniture, buildings and vehicles? Is there a specific model to use for inanimate objects? Can you create a video to show me how to create images that focus on inanimate objects?
@karaghostsongs 4 ай бұрын
it's a pay service ridicolous!
@UldisBiz 2 ай бұрын
Have you tried it? I personally like it. And they keep developing and adding improvements and features all the time
@Topshelfskie 10 күн бұрын
@@UldisBiz Agreed!
@gungager 4 ай бұрын
for some reason if you input stuff like this "--v 5.2 --ar 73:128" <- it makes abomination of and image, can't distinguish what it is
@supermachineart 4 ай бұрын
Tags like this only work for Midjourney, as this technology is not midjourney, using such tags will not have a positive effect on the output.
@danishraza8843 4 ай бұрын
what is the difference between img2img or DWpose?
@TheRahasyaFiles 4 ай бұрын
Please provide image to video features
@gojeffriego 5 ай бұрын
Thank you for posting these vids. You've been cranking them out. They do bring clarity to how I use the tools.
@aye5kay 5 ай бұрын
This is so dope! But what if I wanna be funny and put my face on every person in a photo of 5 people? Also, does this work on anime or cartoonish figures?
@supermachineart 5 ай бұрын
It will work on anime / cartoon models. It won't replace every person in the image with the same head.
@karl-ford 5 ай бұрын
Well done Stuart. Excellent addition!
@neoacla 5 ай бұрын
consistent character is nice but is it possible to use a custom character like for example I want my daughters photo to be use as a reference character and do something similar to this video.
@supermachineart 5 ай бұрын
Check out the Super Clone feature in Supermachine, it can do what you ask just with one image. Try it out in Supermachine!
@karl-ford 5 ай бұрын
Hello Staurt,it would be useful if the "Image to Prompt" would include a suggested model. It will be super useful. Hope you consider adding this in future updates. Thank you.
@ladiferencia777 5 ай бұрын
Hello. When is inpainting coming? Thanks!
@peTeMelster 6 ай бұрын
Does this offer designs for logos, icons, typography, etc. that are more suitable for tee-shirts, mugs, door mats, banners, shower curtains, leggings, and other print-on-demand products? I don't just want artwork imagery. I want designs. Thanks!
@MrPascalAdams 6 ай бұрын
What if i want only his clothes change?
@Stefan-j3o9m 6 ай бұрын
Great video! Thanks a lot. I didn't notice the strength slider. 🙂 What I'm missing is a straightforward method to create icons for applications or mobile apps, particularly for generating business-related icons such as "settings," "add profile," and "delete." It would be fantastic if there was a tool designed for this purpose. Additionally, it would be excellent if users could download these images in SVG format.
@davidwatts3314 6 ай бұрын
Great Stuff How can I add Tshirts to a model? I need product placements for my etsy stuff. Thanks man.
@supermachineart 6 ай бұрын
You can do this using the Depth or Canny ControlNet mdoels. We have videos upcoming on this.
@udo9999 6 ай бұрын
Where is your "later in this video"? Is this an extract of a larger video? Where is it?
@supermachineart 6 ай бұрын
@@udo9999 We did a very long video here - kzbin.info/www/bejne/goHGqqh7irOIkMU with all of the parts. We are releasing all of the sections in 4K over the next few weeks. All of the sections are in the larger video.
@andreas7181 6 ай бұрын
The video quality is only 360p, I cannot see it very clearly. Please improve the video quality to be better.
@supermachineart 6 ай бұрын
It is a 4K upload. KZbin puts a version live before they have the full 4K ready. Come back in 1 hour and you should be good to see it in 4k
@stefano94103 6 ай бұрын
It looks interesting but there's no free trial so it's a hard pass
@andreas7181 6 ай бұрын
It is worth it, if you need AI image.