If this is still a diffusion model, I wonder how well does it compare with NanoBanana.
FLUX.2: Frontier Visual Intelligence
21–30 of 124 posts
Re: FLUX.2: Frontier Visual Intelligence
#22Text encoder is Mistral-Small-3.2-24B-Instruct-2506 (which is multimodal) as opposed to the weird choice to use CLIP and T5 in the original FLUX, so that's a good start albeit kinda big for a model intended to be open weight. BFL likely should have held off the release until their Apache 2.0 distilled model was released in order to better differentiate from Nano Banana/Nano Banana Pro. The pricing structure on the Pr…
> as opposed to the weird choice to use CLIP and T5 in the original FLUX
Yeah, CLIP here was essentially useless. You can even completely zero the weights through which the CLIP input is ingested by the model and it barely changes anything.
Re: FLUX.2: Frontier Visual Intelligence
#23Their published benchmarks leave a lot to be desired. I would be interested in seeing their multi-image performance vs. Nano Banana. I just finished up benchmarking Image Editing models and while Nano Banana is the clear winner for one-shot editing its not great at few-shot.
Re: FLUX.2: Frontier Visual Intelligence
#24> Run FLUX.2 [dev] on GeForce RTX GPUs for local experimentation with an optimized fp8 reference implementation of FLUX.2 [dev], created in collaboration with NVIDIA and ComfyUI. Glad to see that they're sticking with open weights. That said, Flux 1.x was 12B params, right? So this is about 3x as large plus a 24B text encoder (unless I'm misunderstanding), so it might be a significant challenge for local use. I'll be…
Looking at the file sizes on the open weights version ( https://huggingface.co/black-forest-labs/FLUX.2-dev/tree/mai... ), the 24B text encoder is 48GB, the generation model itself is 64GB, which roughly tracks with it being the 32B parameters mentioned. Downloading over 100GB of model weights is a tough sell for the local-only hobbyists.
Never mind the download size. Who has the VRAM to run it?
Re: FLUX.2: Frontier Visual Intelligence
#25> Run FLUX.2 [dev] on GeForce RTX GPUs for local experimentation with an optimized fp8 reference implementation of FLUX.2 [dev], created in collaboration with NVIDIA and ComfyUI. Glad to see that they're sticking with open weights. That said, Flux 1.x was 12B params, right? So this is about 3x as large plus a 24B text encoder (unless I'm misunderstanding), so it might be a significant challenge for local use. I'll be…
Looking at the file sizes on the open weights version ( https://huggingface.co/black-forest-labs/FLUX.2-dev/tree/mai... ), the 24B text encoder is 48GB, the generation model itself is 64GB, which roughly tracks with it being the 32B parameters mentioned. Downloading over 100GB of model weights is a tough sell for the local-only hobbyists.
Even a 5090 can handle that. You have to use multiple GPUs.
So the only option will be [klein] on a single GPU... maybe? Since we don't have much information.
Re: FLUX.2: Frontier Visual Intelligence
#26Their published benchmarks leave a lot to be desired. I would be interested in seeing their multi-image performance vs. Nano Banana. I just finished up benchmarking Image Editing models and while Nano Banana is the clear winner for one-shot editing its not great at few-shot.
The issue with testing multi-image with Flux is that it's expensive due to its pricing scheme ($0.015 per input image for Flux 2 Pro, $0.06 per input image for Flux 2 Flex: https://bfl.ai/pricing?category=flux.2) while the cost of adding additional images is neligible in Nano Banana ($0.000387 per image).
In the case of Flux 2 Pro, adding just one image increases the total cost to be greater than a Nano Banana generation.
Re: FLUX.2: Frontier Visual Intelligence
#27We probably won't be able to run it on regular PCs, even with a 5090. So I am curious how good the results will be using a quntized version.
Re: FLUX.2: Frontier Visual Intelligence
#28The model looks good for an open source model. I want to see how these models are trained. may be they have a base model from academic datasets and quickly fine-tune with models like nano banana pro or something? That could be the game for such models. But great to see an open source model competing with the big players.
Re: FLUX.2: Frontier Visual Intelligence
#29Great, especially that they still have an open-weight variant of this new model too. But what happened to their work on their unreleased SOTA video model? did it stop being SOTA, others got ahead, and they folded the project, or what? YT video about it: https://youtu.be/svIHNnM1Pa0?t=208 They even removed the page of that: https://bfl.ai/up-next/
As a startup, they pivoted and focused on image models (they are model providers, and image models often have more use cases than video models, not to mention they continue to have bigger image dataset moat, not video).
Re: FLUX.2: Frontier Visual Intelligence
#30Good to see there's some competition to Nano Banana Pro. Other players are important for keeping the price of the leaders in check.
Also happy to see European players doing it.