Create Multiple Consistent Characters in FLUX! - Ai Images

[@RichardmpayiTnway]

You really are one of the best ai producers with clear workflows. Keep up the good work and wish you an exponential growth 🙏🏾🔥

[@taoprompts]

Thank you 🙏. I'll keep you updated on the latest tech!

[@dreamstorm84]

I'm really enjoying the tutorials lately. You're a great teacher!

[@taoprompts]

Thanks! I hope this was helpful, I want to make more Ai character guides soon

[@AIdevelopsyou]

This video delivers such valuable insights with a clear explanation. It’s engaging and very well-structured. Thank you for sharing this amazing content!

[@taoprompts]

Thanks, I'm glad you found this helpful!

[@ProUser0777]

Wow! Tao you’re the best! Hands down. Thanks for the research and the help.👍🏾

[@taoprompts]

Thanks! I was using this method recently and thought I'd share

[@Loveyogaanatomy]

I'm really enjoying your videos, they are very clear and well-thought-out. Thanks for all the time and effort you put into these. I'm thinking of trying to create a travel vlog with myself and companions. I would like to create videos as well as images. From your point of view would the applications in this video be the best combination to use or something else? Thanks Stu

[@taoprompts]

Hey glad you like these vids! I think the method I showed is probably the best right now, but the tools and platforms themselves can always be swapped

[@Loveyogaanatomy]

@@taoprompts Thanks

[@mubasherhassan6135]

bro you didn't teach us how to put yourself to creat vdo like 0:14 and 0:18 pls make a tutorial on it i'm so excited

[@FahadZahr]

Can you please mention the pricing as well in your videos, Thanks

[@LofiVibesCorner123]

this so nice !!! Can u do a video about omnigen AI image

[@nicdisan]

Beautiful tutorial, very clear and then you are very good at explaining all the steps. thank you I really admire your generosity in giving all this precious information. I wish you immense luck

[@taoprompts]

thanks! I thought a guide like this needed to be made since people kept asking about multiple characters 👍

[@FahadZahr]

The models is also only generating photos based on the background in the trainer, regardless of the given prompt, why?

[@spiritualrealm555]

Great tutorial! Could you plz make another one how to train a model on two real life characters and use them together in one composition? I watch these viral reels with multiple celebrities characters in in one frame. A tutorial on that would be awesome 😇✨

[@Mubasherhassan-b5f]

bro same qn 😢 you mean like this one huhh!! 0:18

[@jdcmsigma47]

good one mate!! im in awe

[@taoprompts]

Thanks man!

[@alexbon_com]

Man, we need more videos of you exploring enchanted forests, encountering mythical creatures, and rescuing beautiful princesses 😊❤

[@taoprompts]

I may need to slay some dragons also 🔥

[@MilesBellas]

Inside the colours of the glitch, with the mask at 5:35, there are indications of the how the model is internally functioning ? AI glitches = unrecognised artform ? 😃

[@taoprompts]

Yeah probably, it looks like the diffusion process isn't being done at all in those cases

[@ErvNoelProduction]

Do I always need to train new models in order to generate consistent characters together? What if I already have a ton of loras created of my characters? Is there a specific replicate repo I can go to that will allow me to just upload the image I'm trying to inpaint on, upload the mask, and then use my character lora to input my trained character lora?

[@taoprompts]

It depends on if the LoRA is compatible with the specific setup they have. I don't know how you'd use a Lora from somewhere else in replicate

[@ErvNoelProduction]

​@@taoprompts i was actually able to figure it out. Thanks for the reply!

[@Mubashar783]

Dear pls tell us how we can do this i think you forgot to teach this 0:18 ❤

[@sonythabeast]

Can you do full body with Leonardo ai?

[@taoprompts]

you can, but the smaller the face is the less accurate the details will be

[@mrhmakes]

will these flux dev loras work in flux Schnell?

[@taoprompts]

I don't think so

[@planetofshireen]

can we do this in Openart ?

[@taoprompts]

Not right now, I hear they are planning to roll out some big character features soon though

[@past_is_my_present]

Great video!!

[@taoprompts]

www.photopea.com/ , it's free to use!

[@sologost0207]

Recently i studied charater consistancy outputs! I usually midjourney for this workflower But sometime i heard flux is more useful for making same character maintaing consistancy quility than midjourney How do you think flux is more useful tan midjourney for maintaining consistancy character making? Please tell me your advice!

[@taoprompts]

Flux works withy our own photos, Midjourney only works well with Midjourney images

[@marzom-musica]

does the clothes trick work on tattoos too? i am struckling with it

[@taoprompts]

if you're training data all show the exact tattoo, it should be able to generate something pretty close, although it won't get all the details correct

[@gajulapallimaheswarareddy114]

Please let me how lipsync one frame if multiple characters

[@taoprompts]

you need to use runway multi character lip sync

[@bcraigcraig4796]

Question what are some of your clients ask for mostly you to do so I can start developing my skills Thanks

[@taoprompts]

mostly Ai video generation. Consistent characters, lip sync, etc.

[@chariots8x230]

Your tutorials are very good. Hopefully, soon AI will develop so that we’ll get easier, quicker and more natural-looking results when working with consistent characters & scenes.

[@YouUsAndAI]

This is TERRIFIC Tao!! Thank you!!

[@taoprompts]

Thanks! Hope you're having a good holiday season 👍

[@YouUsAndAI]

@@taoprompts thank you and you too. I used your advise for on Knights video i did recently. THANK YOU Tao!!

[@AliKhan-cj6zl]

I created a AI, now i love her❤❤❤❤ True Love

[@marcs7847]

Awesome job! I really what to try this. Could you please give a Replicate link that where there is a Mask ... for a person that already has a model trained?

[@marzom-musica]

i trained this model and the images arent always the same, first few were, after that it gives me random broad

[@HaggisWildlifeFoundation]

lovely

[@BabyFish4Music]

Woooah,dream come true!

[@taoprompts]

This was a highly requested video! I think it's pretty amazing to be able to combine yourself with Ai characters like this

[@vrynstudios]

Excellent.

[@lilith2754]

Amazing! Is it possible to only do a faceswap with this method? If yes would you be opposed to make a demonstration please 🙏?

[@taoprompts]

yeah: take the photo you want to face swap, add a mask for the face, and inpaint using the trained model. You can use the same method shown in this video

[@lilith2754]

@taoprompts perfect, thanks for your response ♥️

[@themikematrix]

great video! quick question though. When training the second character model (in your case its images of you), should i pick the same destination model as the one I trained the first character in or should i create a new model for it with a new name? Thanks man, keep up the great work

[@taoprompts]

Hey, I created a new model destination

[@themikematrix]

@taoprompts thank you I appreciate the help!

[@Mubasherhassan-b5f]

Bro i came for 8:33 to learn how i can do the same but you didn't teach this pls teach us

[@AmAsif7]

Very informative

[@truepilgrimm]

Thanks

[@Sean43322]

That was awesome. Thanks Toa, you created female images in Midjourney, is it possible to use another AI like Freepik for create different images of person for training?

[@taoprompts]

yeah definitely if Freepik has a character consistency feature. i'm pretty sure Free pik also trains a LoRA on a flux model though

[@adrianmunevar654]

There must be a faster way to get it done. An inpainting workflow in ComfyUI with LoRA loader or so

[@pandamanou]

thank you bro for the info, can you suggest a good tuto ?

[@adrianmunevar654]

@@pandamanou I haven't find something like that so I started modifying an inpainting workflow yesterday, it looks promising

[@taoprompts]

yeah that would be possible. Although you'll still need the same steps of training multiple character Lora's and using masking/inpainting

[@aura7117]

This is great, thank you! Do you know if it works for anime style images?

[@taoprompts]

Thanks! You can use this on any types of characters, although anime won't be as accurate as real people

[@aura7117]

@taoprompts Awesome, thank you!

[@AthallaNaufal-yo2xt]

am i tripping or you've never showed which tool you used in rerplicate nor link it

[@taoprompts]

I said in the beginning, replicate.com/ostris/flux-dev-lora-trainer/train

[@planetofshireen]

Hello Tao. I wanted to ask - Would you now consider FLUX over MIDJOURNEY ? Or MIDJOURNEY still is good according to u? and also, does Flux have an editor like MJ ?

[@taoprompts]

yeah Midjourney is still good. The thing with FLux is the ability to train your own characters into it. Here are some new editing features in FLUX: blackforestlabs.ai/flux-1-tools/

[@ApexArtistX]

SDXL lightning

[@planetofshireen]

@@taoprompts Thanks. Have you tried freepik and krea image editors ? Midjourney doesn't allow editing uploaded images.

[@taoprompts]

@@planetofshireen I use Midjourney & Photoshop. You can edit your own images in midjourney now with the editor tab

[@lineardrift]

Love your videos!!! Question on this one: After you trained your model in replicate it and its done, it give you the option to Run the Trained Model. If I click on that, what Engine does it run? Is it still going to use Flux? What if I want to use another version of Flux - there are like three now! LOL Or can you only use what ever the button takes you to?

[@taoprompts]

Thank you! What the training does is add a small customized component (for your dataset) to the existing Flux model. With the trained models, they are only meant to work with the specific version of Flux they are trained with.

[@lineardrift]

@@taoprompts Cab you choose which model you want it to train with?

[@taoprompts]

@@lineardrift right now on replicate you can choose between flux-dev or flux-schnell. On other platforms you maybe able to use a newer model

[@lineardrift]

@@taoprompts Got it! Thanks!

[@chariots8x230]

I see all of the training images are images of the character’s upper body. I guess AI still cannot maintain consistency when it comes to the character’s body type & entire outfit. It seems like it can’t do full-body shots or shots that involve part of the lower body. Also, in your training images, I noticed that you didn’t include any images of the back of your head, so I wonder if the AI would struggle with generating images that show the back of the head. Lastly, your training images seem to be shot from the same camera angle, so I wonder how the AI would do at generating the same characters from different camera angles.

[@taoprompts]

You can do the entire body, however the smaller the face is in the image, the harder it will be for the Ai to learn the details of the face. It does a decent job of generating different camera angles, including the back of the head. Although it may not look like the exact person since it hasn't seen that data

[@elcrgr3844]

Am I finally getting a girlfriend ?

[@taoprompts]

you might be!

[@danielvalleduarte]

Good news and bad news....

[@lokesh-ny1hx]

yeah but at a cost

[@jmg9509]

@lokesh the more things change, the more they stay the same.

[@shadowfightfanclub6588]

Do you have a free one ? This one is paid

[@taoprompts]

there's a $10 coupon in the description

[@gaspardmon]

@@taoprompts Hi, the coupon in the description doesn't work anymore, do you have another one ?

[@taoprompts]

@@gaspardmon I didn't realize it was expired, I don't have another one

[@gaspardmon]

@@taoprompts Ok, thanks

[@gumvue.studio]

thanks, for a music video would be a perfect workflow

[@taoprompts]

definitely if you need multiple characters, something like this makes sense to use

[@gumvue.studio]

@@taoprompts 2 characters, I upload fiew music videos, but they are all text to video, so not much good as what you have now..

[@taoprompts]

@@gumvue.studio I'd definitely recommend using image-to-video for the best results

[@bcraigcraig4796]

What is the best way to make some money with AI that actually works ?

[@zap0p3rr0tr3inta]

why don't you train those 2 characters in the same lora, the trigger word would be something like this (anyword), toprt (anyword), flmcw and the prompt something like this: (anyword) Frontal shot photo of an flmcw woman hiking outdoors next to an toprt asian man. The woman is wearing an orange linen shirt. The man is wearing a black suit. In the background is machu picchu. It's a bright, happy, summer day try it and make a video about it, you will see that it works!

[@taoprompts]

How do you train both of them in the same LoRA? Do you mean train 2 separate LoRA's for each character and them prompt for both of them at the same time, that is a possible way to get the same result

[@Thesmoothhouse]

She needs a brush

[@Lenus-w5u]

not working at all. dislike

[@praiseandworship_com]

Anyone out there who can help (paid gig) with a 6 minute music video? Good cause! bradmorehouse yahoooooo