How to Create Multiple Consistent Characters in Midjourney V6!

[@taoprompts]

🫵 This video is outdated, here's link to a new tutorial that shows how to create multiple consistent characters in Midjourney: kzbin.info/www/bejne/hoTKlqZmg8R3n6c If you want to learn more about prompting for separate characters inside the same image (clothing, background, colors, etc), here's a video guide: kzbin.info/www/bejne/fGaWpZxoqKlqgas

[@AItechIsBeautiful]

Tao. Unfortunately, my subscription for midjourney is over and I can't afford 30 dollars a month. could you please make the same awesome tutorials about consistent characters, consistent style and good promoting but in Dalle 3 inside Microsoft Bing chat which is free because I couldn't find any KZbinr teach about this and there are millions like me who can't afford expensive tools. thank you.

[@taoprompts]

Hey, I think Midjourney has a cheaper plan at $10 a month. Do you find that you need more GPU time than that plan provides?@@AItechIsBeautiful

[@AItechIsBeautiful]

@@taoprompts yeah , I took the 10 dollars plan it lasted with me only 10 days.

[@taoprompts]

I've seen people do consistent characters with DallE + Chatgpt, but I haven't seen anything that lets you do it with just DallE and the bing image creator unfortunately.@@AItechIsBeautiful

[@AItechIsBeautiful]

@@taoprompts yeah. thank you Tao.

[@evan-ezquer]

Great video! I've been saying this for several months now, AI-powered storytelling is the new gold rush for creatives! I think everyone who has a story in their heads should at least give it a go. You owe yourself that much!

[@taoprompts]

Absolutely, with image, video, and audio Ai, a lot is possible nowadays 👍

[@sarahreynolds1430]

I agree! I’ve had a story that three illustrators agreed to work on and after a short time they got too busy and backed out! I’m ready for my book to get published and AI gives me the tools to illustrate it myself!!

[@BibiTheLinkBuilder]

it takes a lot of time and effort to explain it so structured and simple! well done and thank you :)

[@taoprompts]

Thanks Bibi, these do take sometime, but I have a lot of fun making them. I'm glad you find them helpful👍

[@theseanwardshow]

Thanks for breaking this down so clearly!! Exactly what I was looking for.

[@taoprompts]

Thanks man 🙏, happy to be of service.

[@suzannecarter445]

Wonderful! You accepted the challenge. You are the Midjourney Maestro, Tao. Hopefully, they'll make it easier in the near future.

[@taoprompts]

Thank you! I just spend a lot of time testing stuff out. They've been really responsive to community feedback, so if we make a lot of noise about multiple characters, I'm sure they will consider adding in a feature to make it easier.

[@evan-ezquer]

Easier? It's already easy af. Perhaps I could help if you're having issues with the --cref process

[@BabylonBaller]

Appreciate the walkthrough. I originally came up with a process that cuts this in half. Just prompt for Lisa (or whoever has the more difficult hairstyle) and an Asian Man in blue shirt etc, then just only inpaint kim. This worked as well but if they are opposite skin tones as in your examples, it may become an issue with extra inpainting being needed.

[@taoprompts]

That would certainly save some time, but yeah if you use a single character reference for 2 people, they usually both get the same skin tone and facial features as the character reference, so you'll need to do some more inpainting. But on the other hand you can get higher quality for the first character reference, since inpainting often gives slightly lower quality as far as I can tell.

[@BabylonBaller]

@@taoprompts yes I agree. I usually prompt for the woman as that's the one most people are looking lol and then in paint the man

[@taoprompts]

That's a good strategy, I do wish they would gives us an option to increase the inpainting quality though.@@BabylonBaller

[@crdiazmunoz]

Thank you for your chill and knowledgeable insight.

[@taoprompts]

Sending chill vibes your way 👍

[@Claire_Multipassion_Creative]

Midjourney always felt really intimating and out of my wheelhouse but your tutorials have me really excited to try itnout! TYSM! Also already shipping Lisa & Kim they so adorbs together 🥰🙌🙏

[@taoprompts]

It's definitely something you can learn, these Ai tools are getting easier to use all the time. By the way here's an updated version to this tutorial that works right now: kzbin.info/www/bejne/hoTKlqZmg8R3n6c

[@Claire_Multipassion_Creative]

@ thank you so much! I actually binged all your playlist this morning 😂🙏 very engaging and helpful keep up the great work

[@MoJamal-e8q]

as usual, epic share & very clear descriptions of the steps

[@taoprompts]

Thank you, multiple consistent characters still needs some work, but the potential is definitely there.

[@MoJamal-e8q]

@@taoprompts for me, I didn't realize you can inject cref when doing inpainting -- that's really useful '-)

[@RobbScottVideos]

Thank for the info of changing the faces. I've never seen it done this way. Appreciate the knowledge!!

[@RobbScottVideos]

and subbed!

[@taoprompts]

Glad to help Robb! I need to make a follow up guide for this with the new Midjourney features

[@lamboaga]

Tao, thank You so much for all videos ! Your explanation is always very clear and simple :) really appreciate that

[@taoprompts]

Of course! Midjourney is complicated so I try to make it as simple as possible.

[@chariots8x230]

Your tutorials are great as always. I hope Midjourney will make it easier to pose multiple consistent characters together, without inpainting being needed. Hopefully, Midjourney will not only create consistent faces, but also consistent hair & clothing. Also, I wish I could upload an image of a pose in Midjourney, and ask Midjourney to put my consistent character in that pose. When it comes to character posing, I’d also like Midjourney to copy more complex poses of characters interacting with each other (e.g., a pose of two of my consistent characters hugging each other).

[@taoprompts]

Thanks 👍. To get really fine-grained control over the pose you need to use something like ControlNet. Midjourney doesn't have that available but Leonardo Ai does and it's worth trying out.

[@piggywahwah]

Also fooocus, u can download on it on your computer. Its not that difficult and once set up its quite good

[@hartefakto3784]

great video! im learning a lot with your content. im using this for my meme page. greetings from Peru

[@taoprompts]

That's awesome! I've been seeing a lot of Ai memes nowadays. Hello to Peru🖐️.

[@dR33x]

Very good video, carefully explained and demonstrated. Subscribed 👍🏾

[@taoprompts]

Thanks for subbing! I've got a lot more guides coming soon.

[@dR33x]

@@taoprompts more niji stuff would be great 👍🏾

[@thewebstylist]

Yessss The MJ prompt master schools us Again!! 🎉✨👏🏻💯

[@taoprompts]

Thanks Stylist 👊, it's always great to see you enjoying these videos!

[@OiLoikes2Party]

Fabulous!!! Why do you not have 100,000 likes and comments!!

[@taoprompts]

Thank you! I hope that happens someday 👍

[@O-ZONE-b8i]

Very useful! What prompts can be used to adjust the direction of gaze and body orientation of the two people?

[@taoprompts]

I would add in camera angles to the start of the prompts like: "side angle shot from the side" "side profile shots" Or prompt for specific activities where people would have different orientations like: "playing a board game" It is hard to control the direction they are looking and body orientation though.

[@vishalsinha7223]

I m getting SyntaxError: Unexpected token 'I', "Internal S"... is not valid JSON When i write --cref character name or Link. Plz Hlp me in this

[@arkantos4444]

the /prefer_option_set short cut is broken in the vary region prompt box right now. A workaround is to just use --cref with image_url so "your prompt --cref image_url"

[@aresleoric7455]

Dude, thank you for everything.

[@3alemneUp]

I get this error when submitting the change: Submission Error! SyntaxError: Unexpected token 'I', "Internal S"... is not valid JSON

[@taoprompts]

here's an updated video that shows how to do this with the new Midjourney website: kzbin.info/www/bejne/hoTKlqZmg8R3n6c

[@EUMAK4U]

Great Video - all clear and well done explained! thank you so much for making it and making our life’s in MDj better ❤

[@taoprompts]

Thanks! Midjourney 6.1 should be just around the corner so a lot of exciting updates coming soon 🙏

[@frankbeltran]

Don't know what's happening, I can --cref the character in a normal prompt, but I can't vary region from another image and try inpainting with the --cref. It says SyntaxError, unexpekted token "I",

[@taoprompts]

Hey, the /prefer_option_set short cut is broken in the vary region prompt box right now. A workaround is to just use --cref with image_url so "your prompt --cref image_url"

[@uche_patrick]

Exactly what I was looking for. Love it

[@taoprompts]

💯Have fun creating characters 👍

[@kisukeurahara007]

thanks bro man...ur a gem.......just what im looking for..!!!😀.but it looks like we are little more close to our goal.............very good work.

[@taoprompts]

Thanks man 👍. Midjourney is getting really good, I'm honestly very surprised it was able to get all the different camera angles and face directions correct.

[@Nipahc]

I liked the advanced nature and tips! The Anime looked like a good match to me but missing those green triangles on dudes face, IDK. Anyways was looking to see what you thought on Multi-Characters, predicted right but enjoyed a good amount of tips in your workflow! Nice work!

[@taoprompts]

Thanks man! Anime is so stylized, there's so many different ways you can draw an anime face. I can see how the inpainted man is same as the original character.

[@chariots8x230]

It’s not just the green triangles that are missing. The body types of the generated images just don’t match the original character references. Based on the reference image, the male character’s shoulders should be a lot broader than they are on the generated images. The female character also seems to have a different body type if you look more closely.

[@BrandonPlantz]

Thank you so much! Much appreciated and needed!

[@taoprompts]

I'm happy to help man!

[@jonahzehani]

Amazing tutorial Tao!😀

[@AiTechRealm]

Great Tutorial Tao, will use this method.

[@taoprompts]

Thanks Dani!

[@RegnaSaturna]

Very well explained. Love it!

[@mykelbankz]

Exactly what I was looking for. Thanks

[@taoprompts]

Glad to help man 👍

[@safetyhomeloans950]

glad to be the 1st comment! I like to thank you for your material really has been helping me a lot. what do you recommend for building a comic book style using MJ. and its new consistent characters. thanks

[@taoprompts]

Thanks man! Do you mean how to create comic strips? There's a channel called tokenized ai that has a great video on creating comics called "I Created a Midjourney COMIC BOOK: "Treasures Beyond Gold" You could combine what he did with the --cref feature to get comics with consistent characters.

[@safetyhomeloans950]

1st off thank you for the "Prompt" response,,U see what I did there ;) "Prompt"ok so yeah I will most deft. be checking that out...thanks and keep them coming! I know your channel will blow up ....trust me it will :)@@taoprompts

[@taoprompts]

Haha, thanks man. I will test out some cartoon and anime prompts myself also.@@safetyhomeloans950

[@BigNewsNorman]

Dude you're a lifesaver!

[@taoprompts]

I got you man!

[@steviemac1737]

Amazing tutorial as always ❤

[@taoprompts]

Thanks Stevie 👍

[@PietvH97]

Hi Tao Thanks for this video, but when i want to inject the reference picture with --cref --(Name) i got error: Submission Error! SyntaxError: Unexpected token 'I', "Internal S"... is not valid JSON I'm using V6. do you know what this error is?

[@taoprompts]

Hey, the /prefer_option_set short cut is broken in the vary region prompt box right now. A workaround is to just use --cref with image_url so "your prompt --cref image_url"

[@christianswavito2420]

@@taoprompts Thank you :) I subscribed. Keep making more prompt videos.

[@taoprompts]

@@christianswavito2420 Thanks for the sub! Great to hear you enjoy these vids.

[@jerryworm]

Great tutorial. I am scratching my head these days 😁

[@taoprompts]

Thanks man! I will try to make it easy to understand 👍

[@S.H.A.W.Q.I_d-e-s-i-g-n]

Thanks Tao, very informative. Is this applicable in the Midjourney website?

[@taoprompts]

Yeah you can use the same process in the website inside the editor feature.

[@gunnstark3681]

As usual your video is excellent!

[@taoprompts]

Thanks man! This was an exciting update.

[@gunnstark3681]

@@taoprompts Yes! What the best for your channel for the future

[@luckymaria]

Can I reference an object in the same way? For example if I want them to have the same type of guitar or the same dog with them in "the photo shoot" consistently? Should i generate the primary reference photo with those objects?

[@taoprompts]

You can reference objects, however the results won't be as good as for people. You'll need to be pretty specific in the prompts about the exact appearence

[@vitroeye]

Thank you so much for your guide..🙏 learnt a lot..I have small problem when I using "Region button"...:as you told(--cref --kim)i did every thing..but there is a error msg..(Submission Error: Syntax Error: ,Unexpected token 'I', "Internal s"-- is not valid json) please solve this problem ..

[@taoprompts]

Hey, the /prefer_option_set short cut is broken in the vary region prompt box right now. A workaround is to just use --cref with image_url so "your prompt --cref image_url"

[@jasonohr6995]

Your videos are great. Tons of information without needless filler! I did run into an issue using preferred options inside the vary(Region) and wondered if you'd run into it before. I receive a 'Error Unrecognized parameter(s):' when trying to submit a new vary(Region) prompt, but the parameter works everywhere else. I've tried several different parameters, but get the same error. Unfortunately, haven't found an answer yet on the web. Thanks!

[@taoprompts]

Hey, Midjourney made some changes to the vary region feature and it looks like /prefer_option_set doesn't work the same way. A lot of people are having this issue. A temporary work around is to just use the image links directly after --cref. so "your prompt --cref image_url1 image_url2"

[@jasonohr6995]

@@taoprompts Thanks! I'll continue to use that. Unfortunate Midjourney changed things since your method was much more convenient lol

[@ChristineBoucher-h1w]

Thank you! This was incredibly helpful!

[@taoprompts]

You're welcome 🙏! Glad to hear this was helpful.

[@carlosbenitez6438]

great video thank you for creating this, my only question is when you are creating the character are you assigning -cw within that master prompt before you create the prefix? Or no?

[@taoprompts]

I'm not adding --cw in there since by default whenever you use --cref the character weight. --cw is set to 100. But you can certainly try adding that in and changing the weight if you want.

[@taoprompts]

By default whenever you use --cref the character weight --cw is automatically set to 100. I didn't add that into the prompt, but you can try changing up the character weight to something less than 100 though.

[@carlellistration]

Hi Tao Prompts, thanks a lot for the tutorial! I keep getting this error message: Error ('cref', 'expected at least one argument') no matter what I do, the syntax appears to be wrong, I've tried everything from putting --cref --bob before and after the prompt (and everywhere else) and can't find any help online with this. Please help?

[@breakinfogap]

Me too! I have created lots of pictures using this method two days ago, but I can't use --cref --name today

[@carlellistration]

@@breakinfogap hey, thankfully I fixed it. For some reason, it only works with --cref (URL) it doesn't work when you type --cref -- (URL). It's the '--' before the URL that needs to be removed. A moderator told me in discord. Maybe they updated it to work this way since this video? Who knows

[@taoprompts]

I'm also having trouble getting it to work correctly. For now, a workaround is to just directly use the character reference image url, instead of prefer option set inside the vary region box. --cref image_url

[@Yusuf729_]

Fantastic video my man.

[@heisenbergww1957]

can we have 5 + different unique characters in one scene, is that possible?

[@matthewlowe2648]

Thank you for this video, it helped a lot what I am stuck on is when I use the lasso tool in vary region, and I insert --cref and --character name I notice it gives me an error saying Syntax Error: The string did not match the expected pattern.....what am I doing wrong?

[@taoprompts]

Hey, the /prefer_option_set short cut is broken in the vary region prompt box right now. A workaround is to just use --cref with image_url so "your prompt --cref image_url"

[@iyalcinkonuk]

Hi, I'm constantly getting this message: "SyntaxError: Unexpected token 'I', 'Internal S'... is not valid JSON" once I submit the vary region with the --cref --name command included in the prompt. Thanks for your help.

[@taoprompts]

Hey, the /prefer_option_set short cut is broken in the vary region prompt box right now. A workaround is to just use --cref with image_url so "your prompt --cref image_url"

[@AngelaHeyun]

Awesome method!!

[@chronoxx]

Very informative, thanks! Do you know if you can use the cref vary region fill in the website version?

[@taoprompts]

Yes, you can use vary region on images in the web version and it works the same as the discord version.

[@jonahzehani]

Hello Tao, Do you have any idea how we can perform the 'prefer option set' operation directly on the MidJourney website?

[@taoprompts]

I'm not sure if that's possible with the website, I haven't seen how to do that yet.

[@orreedboije9780]

When i try to add cref into photos - it says ('cref', 'expected at least one argument'), when i just try to do my prefered option value "lulu" it also tells me off. Maybe Midjourney have a issue with Vary Region at the moment.

[@taoprompts]

Hey, Midjourney made some changes to the vary region feature and it looks like /prefer_option_set doesn't work the same way. A lot of people are having this issue. A temporary work around is to just use the image links directly after --cref. so "your prompt --cref image_url1 image_url2"

[@runawayboyy]

Hello! Thank you for you video. I’ve got a problem, please help me. After applying -cref -my_character I’m getting this message “X SUBMISSION ERROR! Syntax Error: The string did not match the expected pattern” How can I solve this??? Thank you

[@taoprompts]

Hey, the /prefer_option_set short cut is broken in the vary region prompt box right now. A workaround is to just use --cref with image_url so "your prompt --cref image_url"

[@runawayboyy]

@@taoprompts thanks for your reply! 🤙🏻👍🏻

[@gumvue.studio]

thanks, so . question, I need to create diferent ages, like 10 year old 20 year old 40 year old.. how can I do' I try view but do not work, maybe have to low the CW?

[@taoprompts]

You could try using a base prompt like this one: "a photo of three people in a restaurant. on the left is a 10 year old boy, in the middle is a 20 year old college student, and on the right is a 40 year old man --ar 2:1 --style raw" And then inpaint each of their faces with reference photos, each with a different age person.

[@gumvue.studio]

I have same guy , so need to show him aging @@taoprompts

[@introvertedboi6095]

it keeps coming up with an error when i try to replace the face after putting in the prompts --cref and --lisa e.g.

[@taoprompts]

here is an updated guide: kzbin.info/www/bejne/hoTKlqZmg8R3n6c

[@julliekatesilvano8826]

Can you please help? I'm getting this error after editing the photo in Vary Region. "SyntaxError: Unexpected token 'I', "Internal S"... is not valid JSON" It doesn't seem to be working.

[@taoprompts]

Hey, the /prefer_option_set short cut is broken in the vary region prompt box right now. A workaround is to just use --cref with image_url so "your prompt --cref image_url"

[@edwassermann8368]

very useful. thanks very much!

[@MatthewJettHall]

Well done. Great work.

[@taoprompts]

Thanks man, these videos are lots of fun for me.

[@vallyazz]

Thanks for this video. I tried to do this with illustrated characters and it didn't work, the characters look different every time. Have you managed to solve it with anime characters?

[@taoprompts]

It works best with photos or 3D pixar style characters. For anime characters it does better if you use close up shots, the more you zoom out the worse the characters look.

[@chariots8x230]

After posing multiple consistent characters together in Midjourney, can we then change the characters’ facial expressions & gaze?

[@taoprompts]

I think you could probably try, although I'm not sure how well that would work. For controlling the gaze, you'd probably want to have that already done in the base image prompt before injecting the consistent characters into it.

[@strangematterfilms7313]

Great tutorials! Thank you! When I try using 'vary region' with my saved character reference shortcut, I get the message ('cref', 'expected at least one argument') do you know what this might be? It works in a straight prompt.

[@taoprompts]

Not sure what the problem is but I'm also having trouble getting it to work correctly. For now, a workaround is to just directly use the character reference image url, instead of prefer option set inside the vary region box. --cref image_url

[@strangematterfilms7313]

@@taoprompts got it. And thanks again for your tutorials. Best I’ve found!

[@lilith2754]

Impressive, could adding the cw command increase even more the consistency of the characters ? Can you make a video with the command? Thanks!

[@taoprompts]

Hey, when you're using consistent characters, the cw feature is by default set to the maximum value of 100. So, for this video all prompts by default also have --cw 100 added to them.

[@lilith2754]

@@taoprompts oh I didn't know it was added by default ! Thanks

[@JamesBrown-jl1um]

I'm getting an error when doing the vary region - submission error unexpected token I, internal s, not valid JSON

[@taoprompts]

Hey, Midjourney made some changes to the vary region feature and it looks like /prefer_option_set doesn't work the same way. A lot of people are having this issue. A temporary work around is to just use the image links directly after --cref. so "your prompt --cref image_url1 image_url2"

[@dallasbryan2484]

Do you ever get a "submission error"? Everytime I try the vary region it gives me the following: SyntaxError: Unexpected token 'I', "Internal S"... is not valid JSON

[@taoprompts]

Hey, the /prefer_option_set short cut is broken in the vary region prompt box right now. A workaround is to just use --cref with image_url so "your prompt --cref image_url"

[@sergil.f6987]

​@@taoprompts do you know if this option (direct url) is broken too? Nothing seems to work right now? Thx!

[@artishdesign]

Needed this! So you have to use --cref every time you use the saved character?

[@taoprompts]

Yes, you'll need to use --cref whenever you want to use the consistent character feature. A lot of people have been having issues with the --cref and vary region box recently. A workaround for now is to just directly use the reference image url instead of /prefer_option_set. "--cref image_url"

[@artishdesign]

@@taoprompts Ahhh, okay. I've been playing around with doing it that way (adding reference image + cref) and it's working great. Thank you sooo much. 🙏🏾

[@tienhainguyen6521]

Hi, I tried to /prefer option set but it don't pop up on my midjourney. how to enable this ?

[@taoprompts]

It only works in discord. Just type /prefer and you should see it

[@BoxingQ]

thank you so much , Tutor! does it work well for 3D characters ?

[@taoprompts]

Yup, this should also work for 3D characters, although the results will be best for realistic photos

[@yuuser]

Amazing! thank you so much. I was about to give up on Midjourney but this helps a lot!! Do you have any tips for creating semi nudes. Nothing inappropriate, just artistic. For instance, there are statues draped with thin fabric that sticks to their skin, revealing the contours of their features. It's very beautiful and delicate craftmanship. I was wondering if I could create a book cover with a male in a specific pose, as I cannot find statues of him simply reclining. Thank you.

[@taoprompts]

You could try using a reference image as a style reference, and then describe in the prompt what you mentioned here

[@Yakiraw]

I did as you said, except i only have one charachter. i get a error message: Submission Error! SyntaxError: Unexpected token 'I', "Internal S"... is not valid JSON What can i do to fix this?

[@taoprompts]

Hey, the /prefer_option_set short cut is broken in the vary region prompt box right now. A workaround is to just use --cref with image_url so "your prompt --cref image_url"

[@ramoncomico]

Minute 01:32 How does the VALUE BOX menu appears, please?

[@taoprompts]

Hey, the /prefer_option_set short cut is broken in the vary region prompt box right now. I would just ignore the part about using /prefer_option_set. A workaround is to just use --cref with image_url so "your prompt --cref image_url"

[@ofermali2]

Hi igot this error whan tried to do vary region : what is SyntaxError: Unexpected token 'I', "Internal S"... is not valid JSON: any sulotion?

[@taoprompts]

Hey, the /prefer_option_set short cut is broken in the vary region prompt box right now. A workaround is to just use --cref with image_url so "your prompt --cref image_url"

[@ofermali2]

@@taoprompts thanks!!

[@jponsillo]

Hello, i keep getting, "SyntaxError: Unexpected token 'I', "Internal S"... is not valid JSON". Can anyone advise please?

[@taoprompts]

Hey, the /prefer_option_set short cut is broken in the vary region prompt box right now. A workaround is to just use --cref with image_url so "your prompt --cref image_url"

[@tomasburian6550]

The missing link here is to let us provide our own photos/pictures for the references. In the documentation it says that the AI will always vary and distort provided materials that weren't generated by AI but it stops us from delivering storytelling assets like my paintings of characters from my books and having them be in places doing things. I'm eagerly waiting for that change to come and finally give us more control.

[@taoprompts]

So for using your own photos as references, it's unlikely Midjourney will be able to do that anytime soon. That's because the Ai model needs to make small updates to the model parameters themselves (called finetuning) to embed your own character into it. To achieve that you'll want to use some combination of Stable Diffusion + Lora. Here's an old video from Matt Wolfe that breaks down the general process: kzbin.info/www/bejne/laqomZaZYtdmd9k

[@tomasburian6550]

@@taoprompts Thank you so much. It definitely helps. As of now I let MJ give me some basic image to work off of and then combine different variations to get closer to my idea, then paint over it with my tablet until I fits my vision. It's a tough process, but still faster and gets better results than painting from scratch. I'll definitely check SD, tho.

[@francescosiro]

hi! at this time this technique is not working! ❌ Submission Error! SyntaxError: Unexpected token 'I', "Internal S"... is not valid JSON appear this message, do you know something about it? thank you

[@taoprompts]

Hey, the /prefer_option_set short cut is broken in the vary region prompt box right now. A workaround is to just use --cref with image_url so "your prompt --cref image_url"

[@v.dickson]

Does Mid journey have monthly plans? All i saw was weekly and yearly on their site.

[@taoprompts]

Yes, the basic plan is $10 monthly. Make sure you have monthly subscription selected and not annual subscription.

[@EnglishListeningwithFrankandTK]

Is this possible in Leonardo?

[@taoprompts]

I don't think so

[@hannashamla]

Thnaks for the video, I reciev this error when I use vary (region) to change the face with --cref --the name i gave - do you know why? "❌ Submission Error! SyntaxError: Unexpected token 'I', "Internal S"... is not valid JSON" I do exactky like you/

[@taoprompts]

Hey, Midjourney made some changes to the vary region feature and it looks like /prefer_option_set doesn't work the same way. A lot of people are having this issue. A temporary work around is to just use the image links directly after --cref. so "your prompt --cref image_url1 image_url2"

[@Kim-hd8nt]

love this. thank you :)

[@AlquimistaALAC]

Im trying to do the process, but I always receive the message: "Submission Error! SyntaxError: Unexpected token 'I', "Internal S"... is not valid JSON" When I try to follow the "---cref --name"

[@taoprompts]

Hey, Midjourney made some changes to the vary region feature and it looks like /prefer_option_set doesn't work the same way. A lot of people are having this issue. A temporary work around is to just use the image links directly after --cref. so "your prompt --cref image_url1 image_url2"

[@aespaillat15]

I don't see a copy link option when I click on the photo. I see a copy image address. Is this the same thing? Also after you add their name and copy paste image link do you press enter? Or is it all one prompt

[@taoprompts]

Yes, copy image address seems to work fine.

[@MrBengarabbit]

Is it possible to use the custom character names as references in the Alpha mode (the direct midjourney ux)?

[@taoprompts]

I'm not sure, I haven't used alpha mode before.

[@delilahwatson745]

I'm not able to replace someone's face. When I input the --cref --(character name), in the Vary Region prompt, I get an error message: Submission Error! SyntaxError: Unexpected token 'I', "Internal S"... is not valid JSON Do you know what this means?

[@taoprompts]

Hey, the /prefer_option_set short cut is broken in the vary region prompt box right now. A workaround is to just use --cref with image_url so "your prompt --cref image_url"

[@delilahwatson745]

@@taoprompts Hey thanks for your response. It worked once today, but now it's giving me the same error message :(

[@similpaci]

Why can't I do it? I can only change the face of one character, but when I change the face of another character, the result is that this character is directly eliminated.

[@taoprompts]

here is a new updated guide for this: kzbin.info/www/bejne/hoTKlqZmg8R3n6c

[@LesleyKimFilms]

hmm.. noticed that in vary region I get an error... ❌ Submission Error! SyntaxError: Unexpected token 'I', "Internal S"... is not valid JSON.,, wonder what I'm doing wrong...any ideas?

[@taoprompts]

Hey, the /prefer_option_set short cut is broken in the vary region prompt box right now. A workaround is to just use --cref with image_url so "your prompt --cref image_url"

[@LesleyKimFilms]

appreciate it... your videos are great! Thanks for all of the hard work!@@taoprompts

[@KayLyda]

How do you do this on the latest version?

[@taoprompts]

New tutorial here kzbin.info/www/bejne/hoTKlqZmg8R3n6c

[@fi_ferrari]

thank you so much for your videos

[@taoprompts]

Absolutely man, I'm glad you like them 🫵

[@Cserror1]

Hi:) It it is not working bro. I get syntax error.J.parse unexpected character at line 1 column 1. Pls help. Thx if you no the rror

[@taoprompts]

Hey, Midjourney made some changes to the vary region feature and it looks like /prefer_option_set doesn't work the same way. A lot of people are having this issue. A temporary work around is to just use the image links directly after --cref. so "your prompt --cref image_url1 image_url2"

[@LinaK-rz4nb]

Hi and thank you for this great video! I have a problem when it comes to the point where you change the characters with "vary region" (03:20). I created the characters with „/prefer option set“ as you said before. I gave them a name with "option" and used a image-link with "value". But when it comes to the point where i want to change the characters with "vary (region)" I get an error message which says "Request cancelled due to image filters". Can you tell me about the problem I have here? I used exactly the prompt you used (just with different characters) and the parameters "--cref --Eva --ar 16:9 --style raw" Thank you in advance!

[@taoprompts]

Hey, it sounds like Midjourney is generating images that are NSFW with your prompt & reference combinations. Sometimes this can occur even when trying to generate regular images. You could try using different character reference photos or switch up the prompt slightly add see if that fixes things.

[@LinaK-rz4nb]

​@@taoprompts thanks for your message, i don't know what would be NSFW generating my prompt, due it's just showing regular people :D But i will try again with a new one. thank you!

[@SamhainBaucogna]

super!!!

[@RiseDefiant]

Why I get this error : Submission Error! SyntaxError: Unexpected token 'I', "Internal S"... is not valid JSON "?

[@taoprompts]

Hey, the /prefer_option_set short cut is broken in the vary region prompt box right now. A workaround is to just use --cref with image_url so "your prompt --cref image_url"

[@sergil.f6987]

@@taoprompts do you know if this option (direct url) is broken too? Nothing seems to work right now? Thx!

[@steviemac1737]

I had no idea I could name characters and was just playing with --cref

[@taoprompts]

/prefer_option_set is super useful, you can save custom parameters in addition to an image link.

[@cb4329]

It appears that the reference image you use has to be from the same version of Midjourney. When I was using v5 after generating images I switched to v6 to try the --cref feature. The images produced had none of the key features of the referenced character. When I stayed in v6 and generated the images and then referenced them in different scenes you could see the consistency. Has anyone else experienced this?

[@taoprompts]

Yes that would make sense, it's designed to work with images generated with the same model.

[@marcopineda9507]

Hi, I need help at 3:30 , mine didn't worked. It says: "unexpected token "I", "Internal S"... is not valid JSON I have no clue on what's going on

[@taoprompts]

Hey, Midjourney made some changes to the vary region feature and it looks like /prefer_option_set doesn't work the same way. A lot of people are having this issue. A temporary work around is to just use the image links directly after --cref. so "your prompt --cref image_url1 image_url2"

[@marcopineda9507]

@@taoprompts I will try this, thank you for the tip 😎

[@marcopineda9507]

@@taoprompts image_url means to drag the photo to the web browser right? I think I still get the same error

[@taoprompts]

@@marcopineda9507 Right click on the image to get the image url link

[@leandro5406]

why when i try i have an error saying cref need at least one argument ? i correctly added --cref --"nameofmycharacter"

[@taoprompts]

The vary region box has changed and doesn't work with /prefer_option_set and --cref right now. A temporary work around is to just attach the image_url directly after --cref. "your prompt --cref image_url"

[@lorenzosyquia4769]

After I lasso and type the "--cref --[name]" prompt, I get this message "Error ('cref', 'expected at least one argument')". What does this mean, and how do I fix this?

[@taoprompts]

I think a lot of people have had trouble with the vary region tool recently. For now a work around is to just directly paste in the image url link instead of using /prefer_option_set. s So "--cref image_url_for_character"

[@PhilWilliam-hx6xh]

Me to…that’s a good fix. Thanks

[@lorenzosyquia4769]

@@taoprompts Yeah I tried that, and it works! But it does not work as well as the one you showed us in the video though. Thanks anyway!

[@TuneTangleApex]

First of, props to your tutorials, appreciate it, brother. Could you please look in to this and provide me a solution, Error ('cref', expected at least one argument), please let me know how to fix this error. Thanks in advance.

[@taoprompts]

I'm glad you like my tutorials 👍 A lot of people have had issues with this recently. It looks like they made some changes the interface. If you are trying to use /prefer_option_set & cref with vary region it may have problems. A temporary workaround is to just link the image url directly. So inside the vary region prompt box "--cref image_url_1 image_url_2"

[@TuneTangleApex]

@@taoprompts Thanks a lot bro, that helps! Appreciate it.

[@ppimentell]

should this also work with real people portraits? i've been trying for a bit but it's never accurate

[@taoprompts]

This feature works best with photos generated inside Midjourney. You won't get the same quality of results with your own photos.

[@fgarcia975]

@taoprompts ... I pay for second tier Midjourney ($24/month). I'm familiar with --cref and --sref, etc. but when i try this method you're showing on this video i get "--cref expected at least one argument" notification and nothing happens. Do you know why this is? I'm in the "vary region", i mask her face (and hair, I've tried both), type --cref --(my ai models name) after the camera type and before the --s 750 --v 6.0... just like you did in the video. I get nothing. 💁🏽‍♂️🤷🏽‍♂️

[@taoprompts]

Hey, a lot of people have been having issues with the --cref and vary region box recently. A workaround for now is to just directly use the reference image url instead of prefer option set. "--cref image_url"

[@Limitless1717]

Thanks for sharing! Worth mentioning... No Ai company (MidJourney included) has figured out how to do this well for our OWN faces. Every time I do it, I get this weird looking dude (he always looks the same), and he definitely does not look like me. Faceswapper wasn't much better either.

[@taoprompts]

To get the best results for generating your own faces you would need to finetune (train) a custom model. It can be done with Stable Diffusion + Lora/Easyphoto/InstantID, I've done it myself. Although that does require some extra setup on your end.

[@Limitless1717]

@@taoprompts Thanks man. Feels like a good future video for you...!

[@jamesjones6212]

Thanks for this. can you update this info for the alpha site they now have? I love NOT being on discord.

[@taoprompts]

That's a good suggestion, I will probably post an updated version of this guide somewhere down the line with the Midjourney website.

[@Alex4youtube2024]

I'm illustrating a charity book written by a young girl with brain cancer, where the characters are animals. The challenge is creating consistent AI-generated characters (using MidJourney), but when combining them (even with vary-region), the animals blend into each other. This makes it hard to depict 3-5 characters in one image. Any tips or advice would be greatly appreciated!

[@taoprompts]

You can use the editor tool to drag a portion of the image outside of the frame (with the 1st animal). Then inpaint the remainig space with the new animal. You can do this a few times and combine the pictures in a photo editor like photoshop

[@Alex4youtube2024]

@@taoprompts Thank you very much - cool trick indeed. At then end I use a workflow that involves chars generation in MJ and final composing in Leonardo AI. Now I'm trying to make the characters look at each other. I tried specifying the segment where they should look, drawing an object they should focus on, and using image references with different weights - all in vain. Some positions just won't render in any way. Any ideas/suggestions would be greatly appreciated.