Midjourney Consistent Character Tutorial: Breakthrough Method

Рет қаралды 4,772

2 ай бұрын

Struggling to maintain consistency with your Midjourney characters? In this tutorial I show you how you can easily create and modify your characters AND keep them consistent using the VariPose Connect Method.
Read my article on Medium for more detail: / how-to-create-consiste...
Tracks played:
Onda Norte / Hey Should Have Been Me / courtesy of www.epidemicsound.com
www.epidemicsound.com/track/R...
Onda Norte / Vegas / courtesy of www.epidemicsound.com
www.epidemicsound.com/track/Z...
7-day free trial Epidemic Sound here*:
share.epidemicsound.com/24pjkd
*I may receive a small commission if you end up paying for a subscription after your trial at no additional cost to you.
Structure of a basic prompt to create 3 images on a blank background:
3 different images of [character name], [age] + [ethnicity] + [gender] + [hair] + [eyes] + [emotion] + [pose], isolated on blank white background --ar 3:1 --v 6 --style raw [--sref +url]
Example:
3 different images of Jessica, a 20-year old Hawaiian female surfer with long brown hair, bright green eyes and freckles, isolated on blank white background --no vignetting --ar 3:1 --v 6.0 --style raw
More example prompts below. Use these after you've clicked on the Vary (Region) button and selected some of the images you generated from your initial prompt above. Always leave at least one original image intact until you've modified the prompt.
Different-coloured eyes:
3 different images of Jessica, a 20-year old Hawaiian female surfer with long brown hair, different-coloured eyes and freckles, isolated on blank white background --no vignetting --ar 16:9 --style raw
Different-coloured eyes and braids:
3 different images of Jessica, a 20-year old Hawaiian female surfer with long braided brown hair, different-coloured eyes and freckles, isolated on blank white background --no vignetting --ar 16:9 --style raw
Surprised:
Eyebrows raised, wide eyes with enlarged pupils, mouth open in a slight O shape, and a slight tilt of the head, capturing a moment of astonishment or unexpected surprise. isolated on blank white background --ar 16:9
Angry:
Eyebrows drawn down and together, narrowing of the eyes, a tight set to the mouth, and a tense jawline, with the neck muscles possibly tensed, indicating a state of anger or frustration. isolated on blank white background --ar 16:9
Sad:
Close up of Jessica crying, feeling emotional while watching a sad movie and using tissues to dry her face, isolated on blank white background --ar 16:9
Winter clothing:
3 different images of Jessica, a 20-year old Hawaiian female surfer with long brown hair, bright green eyes and freckles, wearing winter clothing, isolated on blank white background --no vignetting --ar 16:9 --style raw
Fast food worker:
Jessica sports a vibrant red and yellow uniform, serving customers with a smile behind the fast-food counter.
Doctor:
Dressed in teal scrubs and a white lab coat, Jessica exudes professionalism and empathy as a dedicated doctor.
Artist:
Wearing a paint-splattered shirt, Jessica channels her creativity in a sunlit studio, surrounded by canvases.
Environmental Scientist:
Clad in field gear, Jessica conducts research in the forest, her vest and boots ready for environmental exploration.
Office Worker:
Jessica, in smart casual attire, tackles tasks at her office desk, embodying efficiency and focus.
Airline Pilot:
Jessica commands the cockpit in her pilot's uniform, confidently navigating the skies in a light aircraft.
Software Developer:
Jessica codes away in a hoodie and jeans, surrounded by dual monitors in the dynamic tech hub where she develops software.
Tags: midjourney v6, midjourney tutorial, consistent characters, midjourney consistent style, midjourney character design, consistent characters in midjourney, same character design, midjourney character consistency, character design tutorial, ai art generation, digital art creation, creative ai techniques, breakthrough midjourney method, artistic consistency in ai, midjourney niji 6

Пікірлер: 34

@murraymorison3924 2 ай бұрын

So creative. So useful. Well done!

@TheBlessingReport 2 ай бұрын

You are smart this is genius thank you

@1GoodWoman 2 ай бұрын

Thank you. Subscribed. More please. 😊

@AIChallengeQuest 2 ай бұрын

Thanks for subbing! There's more coming soon.

@Bruno_Borja 2 ай бұрын

Wow! This is really useful! Thank you!

@AIChallengeQuest 2 ай бұрын

You're welcome!

@silversurfer4195 Ай бұрын

Great video!

@AIChallengeQuest Ай бұрын

Thanks!

@callofduty3807 5 күн бұрын

0:28-0:34 That lady has a very busy life, doesn't she?

@AIChallengeQuest 4 күн бұрын

Yes, she's definitely an overachiever :)

@adarwinterdror7245 2 ай бұрын

This seems ALMOST useful. There is a jump between your coherent explanation on how to create the character on white background to how to create it in a specific scenario with complex background the action. Say i can get 3 images of Jessica on white background, but i want her sitting on a bus and reading a book - how do I create this image if I have three images of her on white background? This wasnt clear.

@AIChallengeQuest 2 ай бұрын

At about the 2 min mark in this video I cover the process of painting over a couple of those images and then I change the prompt. At this point you would modify the prompt to: "Jessica on a bus reading a book". If she doesn't appear in the new image you will need to add the starter image in again at the start of the prompt. I cover this in more detail in my latest video at the 3m 20s mark. Open the starter image (with 3 different poses), open that image in a browser and copy the URL, then paste it into the start of your prompt (after you've painted over a couple of the poses) and then modify the prompt with "Jessica on a bus reading a book". It will update with a new image of Jessica reading a book on a bus. I also cover another method of changing the background, in my article on Medium (there's a link to it in this video's description) that you could try.

@Antow. 2 ай бұрын

Hello I have follow your video and article on medium (really thank !!) but there is something I can't figure out. Everytime I applied the Vary region and selected the second two images, He keeps generating two images in the vary region and not like your examples one image. Did I did something wrong ? ty

@AIChallengeQuest 2 ай бұрын

It can vary - sometimes you'll get two new images and sometimes you'll get a merged image. The main thing is that the new images should be consistent with the original image. You can then select one of the new images and extend it by painting over the other images (make sure to overlap the body/face of the character you've chosen). If you change the prompt to "blank white background" it will paint over the other images with an extension of your chosen image. You can then change the size of the image using aspect ratio or zoom out. Hope that helps and thanks for your feedback.

@Antow. 2 ай бұрын

@@AIChallengeQuest thank you

@pattyzajac4737 2 ай бұрын

Hello, the website keeps directing me to discord, how do you do all of these things on discord, or how do you get to the website?

@AIChallengeQuest 2 ай бұрын

@@pattyzajac4737 Currently the website is only open to Midjourney users who have created at least 1000 images - they will open it up to everyone progressively over time. In the meantime, you can do everything in Discord. Have a look at the article I linked in the description of this video, I show you how to use Discord to do the same things.

@neilho3523 Ай бұрын

Hi, may I ask why do you particularly add '--no vignetting'?

@AIChallengeQuest Ай бұрын

I used that in my prompts to stop Midjourney from producing darkened edges around the image. It's not necessary if you're going to replace the background with another setting for your character though.

@neilho3523 Ай бұрын

Thanks and appreciate the awesome tutorial! @@AIChallengeQuest

@danielstevenacker 2 ай бұрын

Well, Jeeze, I don't have access to those features as I still have under 1K images. FYI for other folks in the same boat. "Creation is coming soon: Creation is in alpha and being tested with advanced users who have made more than 1000 images. We will make an announcement when it is available to everyone."

@AIChallengeQuest 2 ай бұрын

Everything you see here can also be done directly in Discord. If you check my article on Medium (link in the description) it might be easier to follow. Thanks for the feedback.

@adarwinterdror7245 2 ай бұрын

What is creation? The alpha website?

@AIChallengeQuest 2 ай бұрын

Yes, the alpha website is currently open to anyone who has created 1000+ images on Midjourney. It's an alternative to using Discord to create and view your Midjourney images. They're working on making it more user-friendly for new users to Midjourney before they open it to everyone.

@adarwinterdror7245 2 ай бұрын

@@AIChallengeQuest aaaaaaaand Boom! Today Midjourney came out with the Character reference feature (--cref) and we're good to go! I just tested this and it works well enough :)

@AIChallengeQuest 2 ай бұрын

Yes I've been checking it out too. It will be interesting to see how well it handles different scenarios. It doesn't look like it can handle multiple characters at once though. I think that will come in time.

@trafferz 2 ай бұрын

any way to have 2 consistent characters in the same shot, so Jessica and Bob?

@AIChallengeQuest 2 ай бұрын

It's more difficult to get consistent results when you have two characters, but you can try a prompt like this: "3 different poses of a couple: Jessica and Bob --ar 3:1 --style raw" However, Midjourney seems to resist when you add extra elements into your prompt after using Vary (Region) and painting out a couple of those images. Updating your prompt to: "Jessica and Bob together in various poses --ar 3:1 --style raw" seems to be fine, but if you change the prompt to say that they're standing in front of a vintage car it will often show only the vintage car on its own. Either that or the couple looks a bit distorted. It may take a lot of rerolling to get what you want. When Midjourney introduces their consistent character feature this may become a lot easier.

@trafferz 2 ай бұрын

@@AIChallengeQuestTook some playing around. Got the best results by creating two separate characters with /prefer option set. Then creating a random image with two people. Pick the best of that lot and Vary (Region) their face with the Lasso Tool, and assigning the first character. Then using that produced image, Vary (Region) and using the Lasso tool to select the second face, then assigning the second character. A bit of work, but the results came out well enough. Thanks for the response and video!

@AIChallengeQuest 2 ай бұрын

Nice work!

@AIChallengeQuest 2 ай бұрын

Hi @trafferz. I've loaded a new video that covers my method for achieving multiple consistent characters. Hope it helps.

@trafferz 2 ай бұрын

@@AIChallengeQuestexcellent. trying now

@Cysecsg 2 ай бұрын

How about consistent character from a real photo of a person?

@AIChallengeQuest 2 ай бұрын

I think it depends whether you're trying to achieve an exact likeness of that person. If you're just trying to create a character that resembles that person then you could use the photo as a reference image. In that case you could upload the image and use that in your prompt.