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

121–130 of 159 posts

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

#121

Post by vessenes »

davidbarker wrote: post #110
vessenes wrote: post #88

Earlier quoted context omitted.

@davidbarker -- please do, that sounds awesome! I did not have good results.

It's trickier than I thought it would be. Here are a few in Degar style I made after training for 2,500 steps. I'd love to hear what you think of them. To my (untrained) eye, they seem a little too defined, perhaps? https://imgur.com/a/sqsQLPg

Yep absolutely nothing like degas well I take that back. I think it picked up some favorite colors/tones. But it has no concept of the materials or poses or composition. So plasticky! Compare to https://images.app.goo.gl/JiDRYNNKUP9tczkQ7

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

#122

Post by vessenes »

skort wrote: post #101
vessenes wrote: post #82

Earlier quoted context omitted.

We may differ on our take about the usefulness of diffusion models, but I'd say it's a loss in that many of the visuals humans will see in the next ten years are going to be generated by these models, and I for one wish they weren't just trained on weeb shit.

You'll still be able to ask a person to create art in a specific style if you'd like.

Unfortunately we will have a generation of young artists who learn to draw based on models like flux, unless they get classical training..

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

#123

Post by davidbarker »

vessenes wrote: post #121
davidbarker wrote: post #110

Earlier quoted context omitted.

It's trickier than I thought it would be. Here are a few in Degar style I made after training for 2,500 steps. I'd love to hear what you think of them. To my (untrained) eye, they seem a little too defined, perhaps? https://imgur.com/a/sqsQLPg

Yep absolutely nothing like degas well I take that back. I think it picked up some favorite colors/tones. But it has no concept of the materials or poses or composition. So plasticky! Compare to https://images.app.goo.gl/JiDRYNNKUP9tczkQ7

I suspect it really needs more training examples. The problem I found when I looked for images to use was that 60% were of dancers, and from past experience, it will end up trying to fit a dancer into every image you create. But of course, there are only a (small) finite number of Degas images that you can train with.

A possible solution may be to incorporate artificial images in the training data. So, create an initial LoRA with the original Degas images and generate 500 images. From those generated images, pick the ones that most resemble Degas. Add those to the training set and train again. Repeat until (hopefully) it learns the correct style.

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

#124

Post by davidbarker »

vessenes wrote: post #121
davidbarker wrote: post #110

Earlier quoted context omitted.

It's trickier than I thought it would be. Here are a few in Degar style I made after training for 2,500 steps. I'd love to hear what you think of them. To my (untrained) eye, they seem a little too defined, perhaps? https://imgur.com/a/sqsQLPg

Yep absolutely nothing like degas well I take that back. I think it picked up some favorite colors/tones. But it has no concept of the materials or poses or composition. So plasticky! Compare to https://images.app.goo.gl/JiDRYNNKUP9tczkQ7

Out of curiosity, what do you think of these? https://imgur.com/a/8p7RlMe

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

#125

Post by throwup238 »

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…

Have you tried img2text when training a style?

I want to make a LoRA of Peokudin-Gorskii photographs from the Library of Congress collection and they have thousands of photos, so I’m curious whether that’s effective for autogenerating the caption for images.

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

#126

Post by davidbarker »

throwup238 wrote: post #125
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…

Have you tried img2text when training a style? I want to make a LoRA of Peokudin-Gorskii photographs from the Library of Congress collection and they have thousands of photos, so I’m curious whether that’s effective for autogenerating the caption for images.

It's funny you should ask. I recently released a plugin (https://community-en.eagle.cool/plugin/4B56113D-EB3E-4020-A8...) for Eagle (an asset library management app) that allows you to write rules to caption/tag images and videos using various AI models.

I have a preset in there that I sometimes use to generate captions using GPT-4o.

If you use Replicate, they'll also generate captions for you automatically if you wish. (I think they use LLaVA behind the scenes.) I typically use this just because it's easier, and seems to work well enough.

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

#127

Post by vessenes »

davidbarker wrote: post #124
vessenes wrote: post #121

Earlier quoted context omitted.

Yep absolutely nothing like degas well I take that back. I think it picked up some favorite colors/tones. But it has no concept of the materials or poses or composition. So plasticky! Compare to https://images.app.goo.gl/JiDRYNNKUP9tczkQ7

Out of curiosity, what do you think of these? https://imgur.com/a/8p7RlMe

Significantly better - they feel like watercolor more than degas but if that’s flux I am impressed!

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

#128

Post by throwup238 »

davidbarker wrote: post #126
throwup238 wrote: post #125

Earlier quoted context omitted.

Have you tried img2text when training a style? I want to make a LoRA of Peokudin-Gorskii photographs from the Library of Congress collection and they have thousands of photos, so I’m curious whether that’s effective for autogenerating the caption for images.

It's funny you should ask. I recently released a plugin ( https://community-en.eagle.cool/plugin/4B56113D-EB3E-4020-A8... ) for Eagle (an asset library management app) that allows you to write rules to caption/tag images and videos using various AI models. I have a preset in there that I sometimes use to generate captions using GPT-4o. If you use Replicate, they'll also generate captions for you automatically if you…

That’s awesome! Thank you for the replicate link too. I didn’t know they also did LoRA training. They’ve been kind of hitting it lit the park lately.

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

#129

Post by Kerbonut »

SV_BubbleTime wrote: post #117
GaggiX wrote: post #102

Earlier quoted context omitted.

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

Yea thanks. That’s why I said I run Flux Dev.

Flux dev is also closed _source_ but at least weights available. Schnell is open weight.

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

#130

Post by throw14082020 »

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…

$2 for 2 minutes? Can't you get less than $2 for 1 hour using GPU machines from providers like runpod or AirGPU? I found it a bit expensive to use replicate and fal after 10 minutes of prompting.

I have not used runpod or airgpu, and not affiliated.

Post reply on HN