Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

FLUX1.1 [pro] – New SotA text-to-image model from Black Forest Labs

replicate.com

Post reply on HN
Print view View original

111–120 of 159 posts

Re: FLUX1.1 [pro] – New SotA text-to-image model from Black Forest Labs

#111

Post by davidbarker »

spython wrote: post #106
davidbarker wrote: post #87

Earlier quoted context omitted.

I'm curious to give this a go. I've been training a lot of LoRAs for FLUX dev recently (purely for fun). I'm sure there must be a way to get this working. Here are a few I've recently trained: https://civitai.com/user/dvyio

This looks really good! What is your process to get this kind of high quality LoRAs?

Thank you!

A reasonable amount of training images (50 or so), and then I train for 2,000-ish steps for a new style.

Many of them work well with Flux, particularly if they're illustration-based. Some don't seem to work at all, so I didn't upload those!

Re: FLUX1.1 [pro] – New SotA text-to-image model from Black Forest Labs

#112

Post by kindkang2024 »

I really enjoy its service. It's promising for UI design. My advocacy website pages' UI design was bootstrapped using it. It is quite good for developers without much design ability.

Ironically, I am afraid to type the website out and will keep it unknown here. My account could be suspended because of this. It had already reached -1 karma. It's better to keep my account alive.

Re: FLUX1.1 [pro] – New SotA text-to-image model from Black Forest Labs

#113

Post by stavros »

davidbarker wrote: post #111
spython wrote: post #106

Earlier quoted context omitted.

This looks really good! What is your process to get this kind of high quality LoRAs?

Thank you! A reasonable amount of training images (50 or so), and then I train for 2,000-ish steps for a new style. Many of them work well with Flux, particularly if they're illustration-based. Some don't seem to work at all, so I didn't upload those!

How long does this take, and on what equipment? It's amazing to me that you can do this from just 50 images, I would have thought tens of thousands.

Re: FLUX1.1 [pro] – New SotA text-to-image model from Black Forest Labs

#114

Post by fortran77 »

I've been playing with Flux.Dev and such a big step forward from Stable Diffusion and all the other Generative AIs that could run on consumer GPUs.

I just tried this Flux1.1 pro page (prompt: "A sad Macintosh user who is upset because his computer can't play games") and was very impressed by the detail and "understanding" this model has.

Re: FLUX1.1 [pro] – New SotA text-to-image model from Black Forest Labs

#115

Post by davidbarker »

stavros wrote: post #113
davidbarker wrote: post #111

Earlier quoted context omitted.

Thank you! A reasonable amount of training images (50 or so), and then I train for 2,000-ish steps for a new style. Many of them work well with Flux, particularly if they're illustration-based. Some don't seem to work at all, so I didn't upload those!

How long does this take, and on what equipment? It's amazing to me that you can do this from just 50 images, I would have thought tens of thousands.

It's very impressive. I aim for around 50 images if I'm training a style, but only 10 to 20 if training a concept (like an object or a face).

I have a MacBook Air so I train using the various API providers.

For training a style, I use Replicate: https://replicate.com/ostris/flux-dev-lora-trainer/train

For training a concept/person, I use fal: https://fal.ai/models/fal-ai/flux-lora-fast-training

With fal, you can train a concept in around 2 minutes and only pay $2. Incredibly cheap. (You could also use it for training a style if you wanted to. I just found I seem to get slightly better results using Replicate's trainer for a style.)

Re: FLUX1.1 [pro] – New SotA text-to-image model from Black Forest Labs

#116

Post by stavros »

davidbarker wrote: post #115
stavros wrote: post #113

Earlier quoted context omitted.

How long does this take, and on what equipment? It's amazing to me that you can do this from just 50 images, I would have thought tens of thousands.

It's very impressive. I aim for around 50 images if I'm training a style, but only 10 to 20 if training a concept (like an object or a face). I have a MacBook Air so I train using the various API providers. For training a style, I use Replicate: https://replicate.com/ostris/flux-dev-lora-trainer/train For training a concept/person, I use fal: https://fal.ai/models/fal-ai/flux-lora-fast-training With fal, you can trai…

Wow, fantastic, thanks! I thought it would be much, much more expensive than this. Thanks for the info!

Re: FLUX1.1 [pro] – New SotA text-to-image model from Black Forest Labs

#117

Post by SV_BubbleTime »

GaggiX wrote: post #102
SV_BubbleTime wrote: post #100

Earlier quoted context omitted.

No, only a dozen Flux Dev models different distillations, quantizations, and fine-tunes with LORAs. But you keep pretending that close source AI is a sustainable comparison.

Flux Pro (v1 and v1.1) is a close source model.

Yea thanks.

That’s why I said I run Flux Dev.

Re: FLUX1.1 [pro] – New SotA text-to-image model from Black Forest Labs

#118

Post by davidbarker »

stavros wrote: post #116
davidbarker wrote: post #115

Earlier quoted context omitted.

It's very impressive. I aim for around 50 images if I'm training a style, but only 10 to 20 if training a concept (like an object or a face). I have a MacBook Air so I train using the various API providers. For training a style, I use Replicate: https://replicate.com/ostris/flux-dev-lora-trainer/train For training a concept/person, I use fal: https://fal.ai/models/fal-ai/flux-lora-fast-training With fal, you can trai…

Wow, fantastic, thanks! I thought it would be much, much more expensive than this. Thanks for the info!

Happy to help! It's a lot of fun. And it becomes even more fun when you combine LoRAs. So you could train one on your face, and then use that with a style LoRA, giving you a stylised version of your face.

If you do end up training one on yourself with fal, it should ultimately take you here (https://fal.ai/models/fal-ai/flux-lora) with your new LoRA pre-filled.

Then:

1. Click 'Add item' to add another LoRA and enter the URL of a style LoRA's SafeTensor file (with Civitai, go to any style you like and copy the URL from the download button) (you can also find LoRAs on Hugging Face)

2. Paste that SafeTensor URL as the second LoRA, remembering to include the trigger word for yourself (you set this when you start the training) and the trigger word for the style (it tells you on the Civitai page)

3. Play with the strength for the LoRAs if you want it to look more like you or more like the style, etc.

-----

If you want a style LoRA to try, this one of SNL title cards I trained actually makes some great photographic images. https://civitai.com/models/773477/flux-lora-snl-portrait (the download link would be https://civitai.com/api/download/models/865105?type=Model&fo...)

-----

There's a lot of trial and error to get the best combinations. Have fun!

Re: FLUX1.1 [pro] – New SotA text-to-image model from Black Forest Labs

#119

Post by stavros »

davidbarker wrote: post #118
stavros wrote: post #116

Earlier quoted context omitted.

Wow, fantastic, thanks! I thought it would be much, much more expensive than this. Thanks for the info!

Happy to help! It's a lot of fun. And it becomes even more fun when you combine LoRAs. So you could train one on your face, and then use that with a style LoRA, giving you a stylised version of your face. If you do end up training one on yourself with fal, it should ultimately take you here ( https://fal.ai/models/fal-ai/flux-lora ) with your new LoRA pre-filled. Then: 1. Click 'Add item' to add another LoRA and ente…

Thanks for all this! I had created a SD LoRA of my face back in the day, time for another one!

Re: FLUX1.1 [pro] – New SotA text-to-image model from Black Forest Labs

#120

Post by davidbarker »

stavros wrote: post #119
davidbarker wrote: post #118

Earlier quoted context omitted.

Happy to help! It's a lot of fun. And it becomes even more fun when you combine LoRAs. So you could train one on your face, and then use that with a style LoRA, giving you a stylised version of your face. If you do end up training one on yourself with fal, it should ultimately take you here ( https://fal.ai/models/fal-ai/flux-lora ) with your new LoRA pre-filled. Then: 1. Click 'Add item' to add another LoRA and ente…

Thanks for all this! I had created a SD LoRA of my face back in the day, time for another one!

Awesome! :)
Post reply on HN