Midjourney - this will change how you write prompts! (Blend feature) FREE alternative to Midjourney!
ฝัง
- เผยแพร่เมื่อ 20 ม.ค. 2023
- This is the best Midjourney AI tutorial about the blend feature. And we'll look at a new and FREE alternative for Midjourney. Also I share a really cool workflow hack for when working in Midjourney and a style spreadsheet and a page on Github that will really change how you write prompts.
It's made on the Wacom Cintiq Pro 32 with Stable DIffusion, DALL-E, Photoshop, Google Colab and Macbook Pro, Atem Mini Pro, After Effects and Adobe Premiere.
-------------------------------
SUBSCRIBE
▶ handle: / @levendestreg
▶ You can subscribe to our channel here: th-cam.com/users/levendes...
▶ Read more: levendestreg.dk/en
-------------------------------
▶ Style reference spreadsheet: docs.google.com/spreadsheets/...
▶ Midjourney Styles and Keywords references: github.com/willwulfken/MidJou...
▶ BlueWillow: / discord
-------------------------------
My setup
Macbook Pro M1 Max: amzn.to/3Znd44l
Wacom Cintiq 32 inch (couldn't find the 32 inch - so links is for 27 inch): amzn.to/40ubLSl
Atem Mini Pro: amzn.to/3nAe9s4
Stream Deck XL: amzn.to/3Zun5N9
Razer Tartarus v2: amzn.to/3TV239a
Logitech MX master: amzn.to/3TSFK43
-------------------------------
00:00:00
So, Midjourney has powerful blend feature that enables you to mix up two five images together.
00:00:08
Did you know there is a new alternative to Midjourney that is FREE and working on Discord? But I will get back to that in a few minutes.
00:00:36
So I have some images here that I have downloaded from Freepik.com
00:00:53
And then I have simply uploaded that URL I will show you in a moment
00:01:40
So this is how to do image blending in Midjourney. I have created a an image of Athena, God of strategic war, and I am going to try to blend her with an image of me.
00:01:53
So I am going to go in here and click on the image, open image in new tab and simply copy that URL.
00:02:03
Actually, I'm going to head over into my note app
00:02:05
and I'm just going to copy in that link.
00:02:07
Then I am going to grab an image of me
00:02:11
and simply pull it into disk click return.
00:02:15
And that's going to process.
00:02:16
I'm going to click it and then right
click it and open image in new tab
00:02:21
and I'm going to grab the URL on that one
00:02:27
And here I'm going to copy that into my note app, too. And they're only divided with a space.
So hit spacebar and copy paste that in.
00:02:45
Write /imagine,
00:02:48
and then simply copy in the URLs and hit return.
00:02:59
This blend feature depends very much on you being able to pick up images that actually work well together.
00:03:49
So let's try to guide that generation of image blending.
00:03:54
So again, I am going to write Imagine and then I'm going to copy in the URLs that I had before and I am going to write a comma after the latter of the URLs.
00:04:05
And here I am going to write: Statue of Athena, Greek goddess of war.
00:04:43
If you want to train models, well then I have an upcoming episode on how to do that in Stable Diffusion.
00:05:47
So this spreadsheet shows artists, painting styles, comics, cartoons, creatures, sci-fi style, landscapes and so on.
00:06:14
For a super powerful tip in Midjourney. The preferred suffix value.
00:07:00
So now for the styles and keywords reference page - because this is really cool.
00:08:37
Now for the new and free alternative to Midjourney.
Please notice I've not received any payment to say this.
It's called BlueWillow. It's an Ai Art Tool that works like MidJourney -
I'm going to upscale some of my old renders and blend today. I like the drop feature a lot. Think it's better on a desktop for more than two images. I've done this pretty much since the release of v4 but it's gotten better. The styles do need to work together. I create a lot of florals and abstract art and blend them with portraits and landscapes.
Yeah the blend tool works great with all types of images. And midjourney is so great for abstract art too! 🙌
Blend command is now a part of Midjourney "New feature..... The /blend command
- /blend looks at the 'concepts' and 'vibes' of your images and merges them together into novel interpretations
- This is the same as using multiple image prompts with /imagine but it's much much easier to use since you don't have to provide urls
- The command will ask you to directly upload images from your phone / computer into your message so it can merge the images
- Blend works with up to 5 images (for more than that please use image prompts with /imagine)
Thank you so much for sharing. Yes I know this and will add it to my next video. Thank you for directing my attention to it!🙌
My thoughts exactly!
@@AnnVanhuysse I’m going to dig into that this weekend in my next video!
That styles and keywords reference page is fantastic. Thanks so much for pointing us to it.
Yeah, it’s pretty great. Glad to share it with you all! 🙌
Thanks for the prompt cheat codes link! It works like a charm!!!
You’re very welcome. They work really well, I think, too! 🙌
Always informative, always entertaining, always inspiring. Thanks for another great video.
Thank you kindly, @carcus566, I really appreciate it! 🙌
you are such a wonderful lady, thank you for the well put info, I subbed, keep it up
Thank you kindly, @N3ky - I really appreciate it! It means a lot to me 🙌
Purely fantastic. Thank you so much.
You’re very welcome. Thank you kindly🙌
Omg!!!!! The angles and perspective!! So insightful!!!!
I know!!! It’s amazing, right?!
Thank you for the spreadsheet
Glad you like it. It’s really awesome I think. So thank you to all the people who worked on that sheet. Just to make it clear - I didn’t make the spreadsheet - just shared my knowledge about to all of you!
Very nice language and pronunciation … a pleasure to watch
Wow thank you kindly! You don’t know how much that means to me as a person from the Nordic countries. 🙌
@@LevendeStreg You can feed honored as I very rarly comment anything :-) Really keep going, also your imformation density is very nice, not too light like in many other youtube videos...
@@chrisr1241 thank you! Great to hear. 🙏
I've been working on my own guide a bit. It's not super extensive but it's been helping me getting consistent results.
I'm really glad to help, @ellenripley4837 (and love your photo 🤪).
Awesome and much appreciated ❤
Thank you so much, @TimGillespie - I really appreciate it 🙌
The new blend mode is actually a brand new operation using /blend , not /imagine.
As far as I know, using multiple image URLs after /imagine was always possible.....so that's not new actually.
Thank you @Louis - yeah, I know ai forgot to add the /blend. Normally I just the blends like this. So I guess I have to make a new episode where I add that too! Thanks for pointing that out!
@Levende Streg
Honestly, the results I've gotten from the /blend operator are not very good......the quality sucks. But maybe it depends on what images you're trying to blend.
But I figured that by feeding MJ a good quality image of a steam train and another of an old train station, MJ would have a fairly easy time of creating a high quality image......but it didn't. It combined the 2 concepts okay but the quality of the render each time was not good.
@@LouisGedo thank you so much for sharing you knowledge!
Correct 👌🏻
Thanks a lot for sharing this great video 👍
Thank you kindly for watching and commenting, Ali! 🙌
Thank you so much for all these information!
You’re very welcome @JM! Happy to help and inspire🙌
And thank you for talking the time to comment. I really appreciate it 👏
Great video, thanks Levende.
Thank you kindly, David. Glad you liked it!
Please try this: Create some abstract image like "abstract modern muted colors" and upscale one of them. You want a blob of colors or textures you like. Then, use that as the base image and add pretty much any prompt you'd like. I've gotten amazing results, especially with portraits. The best thing is that the color blobs serve as templates - I have amassed a collection from abstract colors to specific stone textures.
I've gotten this idea from another video on here but I can't find it 😔
Nice. I’ve seen other people do it to. Definitely will do a video on it, so people can try that out. Thank you for your request / suggestion! 🙏
awesome resource, thank you
Thank you so much. Glad you like it. I really appreciate it!
Thank you
You’re very welcome. Thanks for watching🙌
Great info. TFS
Thank you kindly, @evefavorse5939 - Glad you liked it!🙌
You are the best!
Thank you kindly Brite🙌 and thanks for watching!
Thanks Levende for a great video! I am using Midjourney and tried Blue Willow. I tried to create my own server like I did on MJ but couldn’t find the bot so I could add the / imagine prompt. Does it work in a different way from MJ for that?
I don’t think you can add their bot, because it’s still a beta test. But you should be able to DM the bot, I think.
I have tried the blend feature both ways and I cannot get my images to look anything like the person in my reference photo. 😫 what am I doing wrong? I need help please.
I don’t think you are doing anything wrong. It’s difficult with the blend command. Maybe try to weigh you image. Like this: “image weight parameter --iw to adjust the importance of the image URLs vs. the text. --iw 0.25 is the default and is used when no --iw is specified. Higher --iw values mean the image prompt will have more impact on the finished job.” Read more on: docs.midjourney.com/docs/image-prompts
Dope Content🤘🏼😎💯💧
Thank you so much! I really appreciate it! 🙏🔥
But your videos are a great help
Is there an alternative for the blending option, f.e.: in stable diffusion?
Yes there is - and no not exactly. Try this one: huggingface.co/spaces/lambdalabs/image-mixer-demo - hope it works out for you!
Hello, do we have a private mode with the 10 dollars subscription ?
Nope, unfortunately not with MJ. 🙌
U r the best
Thank you kindly JustJerryPodcast! I’m glad you like my videos!
Anyone else having problem with the /imagine prompt today ?? Actually, it's the command matching feature that's not working at all.. help !!?!
Yes, on Midjourney's channel on Discord they're saying this: Discord is undergoing an incident discordstatus.com/incidents/dr5kywl9dwg9. Slash commands will not show up until this is fixed. Go follow that channel to stay updated. They'll try to fix it as soon at possible.
@@LevendeStreg thank you so much!!
@@vanessahuneault31 You're very welcome.🙌
you should see,, but i think midjourney now really has an option blend, instead of /imagine, you put /blend
Correct - you can write /blend to the same effect! Thank you for reminding me of that.
@@LevendeStreg glad to help :)
Thank you for this video! 😊
The blend feature seems interesting. Probably not super useful for comics, but still interesting.
It’s good that we are getting some competitors to Midjourney, such as BlueWillow.
It’s nice that BlueWillow is being offered for free right now, because hopefully this will attract more users, which will help train the AI to become better and eventually improve to reach or exceed the level of Midjourney.
However, I hope BlueWillow offers better privacy options than Midjourney. What I really dislike about Midjourney is that there’s no privacy in what you create, unless you pay a hefty price for it in addition to the monthly subscription. So, other users can see & use what you create, which I consider unacceptable. This is one thing that’s a dealbreaker for me when it comes to Midjourney. Hopefully, BlueWillow will make privacy the default setting for users, without making users pay just to have privacy over what they create.
Hopefully, Midjourney will improve in this area too. I would use Midjourney if they fix the privacy problem, without making users pay extra to keep their images private. But since Midjourney has this problem, I prefer to find alternatives to it.
I totally agree with you. It needs to be private! What do you use instead of Midjourney? Stable diffusion? I switch between the two myself. I’ve really come to like SD!
@@LevendeStreg Sorry, TH-cam didn’t really notify me that you responded to my comment. 🤔
I’ve tried both Midjourney and Stable Diffusion. I’m annoyed by Midjourney though, because users are paying to generate these images for their own projects, but Midjourney lets everyone to have access to other people’s creations. The whole point of using AI art is to create something unique that no one else is using. Imagine creating a comic, or some kind of book, and other people are using the same images as you. I consider that unacceptable, and I don’t care how good the results in Midjourney are if they can’t get this basic thing right. I think Midjourney should at least allow privacy in their $30 plan, without users having to pay an extra $20 just for privacy.
@@LevendeStreg I think ‘Stable Diffusion’ is the better option for now. 😊
@@chariots8x230 I agree !
@@chariots8x230 I hear you - and I absolutely agree. It's a basic thing you want as a creator. To have your prompt results private is a must. I absolutely agree with you! Did you see the new episode I did? There I show how you can use Cloud GPU with Stable Diffusion - and still keep your creations private. Of course you can do that on your own computer too. But I'm on a m1 mac - so external GPU is a bit tricky. And for training my local install simply does not have enough GPU. So I need cloud GPU for that.
Is it possible to use two separate images of two people and ask MidJourney to make a photo using those two people in a situation? Like for instance, taking a selfie together or walking by the hand... Whenever I use two pictures, it blends them in one single person. I want two separate ones. Is that possible to do?
Thank you for your question, Martin. Yes, it's probably possible. But it will take a LOT of tries. So maybe you should look into doing something with Stable Diffusion in stead. There you can train a model on that. But - you'll probably need photoshop for it too.
@@LevendeStreg I did a little trick with photoshop, yes. I basically took two photos of the poeple I wanted to make art of, mixed them in one single image, and then used that image on MidJourney and wrote a prompt with it. Worked pretty well.
@@marrrrrrrrrrr09 that’s exactly what I meant. Great job!
Short and sweet. Midjourney is still better. And I'm willing to bet that it will stay better since people are funding it.
I agree Mr. Prez. Midjourney is way better at the moment. And yes, I think Midjourney will stay on top as one of the best AI engines for art generation!
@@LevendeStreg Here here! Thank you for your videos! I've learned a lot thanks to you ☺️🤙
@@Great.AnotherChristian I’m glad you like my video! I learn so much about AI and the different solutions. It’s just all moving really fast at the moment. It’s pretty amazing!
isn't --v 4 standard now? I thought that you no longer had to add it
Yes, it’s standard, but sometimes MJ Switches back to v3 if you switch settings or add new suffixes…
@@LevendeStreg okay, thank you. I'm really enjoying your videos, insight, and knowledge. Thank you!
@@RussWilgus thank you so much! I really appreciate it 🙌
I was on Bluewillow and they prominently posted that NSFW content creation should be reported. So I did report it. And they banned me right after reporting it. So, if you go there, don't report anything. Apparently it's a bannable offense.
Dang, don’t know what that was about. Heard they were pretty strict with NSFW, but then your story makes no sense. Sorry to hear it!
That sucks. Maybe it was a mistake?
You are a cheerful shine of light in the middle of the creative darkness. Great work! 😁
Thank you so much, @DrB. I really appreciate it- and so glad you like my videos!
It's a program for kids, if you want to get serious Stable Diffusion is the only option you have to choose from.
Hahaha! Well that’s a way of seeing it. I do prefer Stable Diffusion myself. But a lot of people find it hard to install or use, because the code is often broken or updates in a manner, why the code is broken. So Midjourney is convenient and stable… where Stable Diffusion is not so stable. Hehe. My upcoming video is on that🙌
I swear you're definitely one of the best AI Art tutorial creators on here. I had to turn on my notification for your channel 😇 btw, are you available for freelance work?
Thank you kindly. I really appreciate it! 👏Depending on the type of work we are open to new projects. I run a small creative (visual) agency in Copenhagen. See my website for contact information🙌🔥
lol, i got like 5 invites in discord for blue willow and i was like why i a, getting all this invites and all
Haha… did you check it out?
🤩🤩🎉🥳👏👏
Thank you so much! 🙌
This BlueWillow isn't a Midjourney alternative, it's even close to that :(
It’s an alternative for people who don’t want to pay for Midjourney, I guess. Some people are getting good results with it. I stick to MJ and SD myself!👏
boooo
why i can not download the style reference spreadsheet you shared @levende streg
Go to the Web address - it’s a page with videos. Click the button under the video!