Here’s how to train your face into the new AI models. Here’s the link for $10 free at Replicate: (NOT Sponsored)
Discover More From Me:
🛠️ Explore thousands of AI Tools:
📰 Weekly Newsletter:
🎙️ The Next Wave Podcast:
❌ Follow me on X:
🧵 Follow me on Instagram:
Resources From Today’s Video:
Train on Replicate:
Train on Fal:
Train on Collab:
Let’s work together!
– For brand & sponsorship inquiries:
– For other business inquiries: mattwolfe@smoothmedia.co
#AINews #AITools #ArtificialIntelligence
[ad_2]
source
Update #2: I've just gotten word from Replicate that they have re-opened the $10 link! It should be working again. 🙂
Update #1: Apparently the link expired for Replicate. I was not told that the link would expire. I apologize for this. I honestly had no idea. I reached out to them and asked what happened and they told me that their finance team decided to turn it off because too many people were using it. I'm going to do what I can to rectify the situation, even if it means finding a different method people can follow to do it for free. Once again, I sincerely apologize. This decision was made my Replicate and they did not inform me that they would turn the link off if it got too much traffic.
Great video!! Is this same workflow capable of training and producing product photos. Like shirts and glasses?
Random question
Is there a way to see previously generated images?
Hey, I'm getting this error in replicate site after the training ends Training failed.
Error while uploading 'flux_train_replicate.safetensors' to the Hub.
Any idea why?
500 subscribers completed ❤❤❤… Thanks ❤❤❤
I get this error when training is at 100% – Error while uploading 'optimizer.pt' to the Hub
Thank you 🙏
Hi thabks for the tutorial. Question: Why we need to connect the token from Huggingface to Replicate? From my understanding it's because we will export the model to HF. But than why we can't do everything inside HF? I'm new to ML so it's quite confusing. Thanks.
Thanks for the video tutorial! the best I've ever seen! question, does anyone know how we can use the model generated with control net?
You get better results because the first sentences of the prompt have more importance than the last ones. It works always like that! Basically I always try to use the prompt related to my lora as the first or last.
Amazing tutorial! Thank you so much. What if I want to fine tune another person face on to the fine tuned model with my face
How can this be done using ideogram?
Thank you for the clear instructions as well as the $10 credit.
Am I able to train multiple models on replicate, and then use them together to make an image with multiple trained subjects?
It worked like a charm…. but I want to use the model I created on hugging face on my local ComfyUI. Can you make a short tutorial on how to do this please!! Love your videos… keep up the good work!!
Great tutorial and it's working great. However my images are appearing grainy. Not sure what's causing this as I've matched all the settings shown in the video. Anyone else having this issue and resolved?
Is there a way to take this to stable diffusion local install?
Hey, thanks for a great video ! where can I see the usage amount of money?
Hey Matt, great video. I don't know if you can help, but I've been following along with this tutorial, and for some reason Replicate is not sending my trained model when it is finished to Huggingface. Any advice?
"Myself" lol 😈 🦹♂️
Ok, there were a couple of things that I've learned from other vids that may have gotten missed with this one. 1. It must be set to public (which I think he was later addressed) and the other way I've learned and now do with no issues is 2. When creating your TOKEN you have three options – Fine-grained, Read, Write – you want to set it to WRITE and that solved all my problems. I hope it solves yours. Good Luck.
It says "NSFW Content detected" every time
Great stuff! //Marketing Team at the bank
If you train model in 1000 steps, is there a way to save file every 200 steps?
And can i write captions like this "man, upper body, blue eyes, hat" or do I have to write it in sentences like "picture of a man with blue eyes wearing a hat" ??
Btw: any ideas how to train lora locally? I think my GPU would handle.
Thank you Matt for the clear instructions. I managed to follow along and create some amazing images.
the token part is where I became very confused
Thank you so much for this video. It was very easy to follow along and get a working model. Cost me $3.10. It does realism very well but I'm struggling to make an illustrated version of myself. It seems like the Lora is squashing any stylization from the prompt. When I stylize with another Lora, the realism is still prominent in the image. Running locally in Comfy.
0:49 This is Matt at the 2024 Paris Olympic Ceremonies! 🙂
Thanks for sharing this! The link worked perfectly for me, and I successfully trained the model on my first try! 🎉 I was pleasantly surprised and so grateful for the smooth process including Claude image prompt optimizer. Matt, you consistently deliver great content on the AI world—keep up the awesome work! 🙌
The credit really helped. I can generated 3000 schnell images with it
Flux is really a heavy weight model ,24 gb V Ram ,32gb or More Ram core i7 or i9 unlocked processor it sucks every thing but result is not remarkably different from other models like SD v1.5 ,Myslr ,dream shaper, absolute reality or juggernaut etc ..
Using hi res checked add some loras ( just one is enough too) , Euler a ,karras ,12 to 16 steps, cfg 3 to 6 you can create stunning photo realistic images in Automatic 1111. If you use flux locally each generation force the unlocked processor to overclocking, reducing its life ….
On civitai it consumes 44 buzzs and many times generation is not successful after waiting for long time it is really frustrating…think before you use flux dev or pro😊
Yo, is there any other free way to do this? I wanna train a new model in Flux, but it's not letting me. I made a new GitHub account and it flagged me as spam. And that $10 link you sent, it says it's expired. Is there any other free way to do it and get the same awesome results?
I’m looking for a way to train a flux model without all the third party sites. I need to python program script it to auto train.
he credit has expired,
Can I download the Lora and use in with Flux in Forge UI?
Didn’t even watch the video and I was provided the free $10 code
Sad it’s expired now though lol
thanks, question, is there point to train and sell the loras?
Replicate: "It looks like that invite has expired. Please ask whoever sent it to you to send a new one."
Does anyone have a new link please?