FLUX.2: Frontier Visual Intelligence
1–10 of 124 posts
Re: FLUX.2: Frontier Visual Intelligence
#2Yes yes very impressive.
But can it still turn my screen orange?
Re: FLUX.2: Frontier Visual Intelligence
#3Good to see there's some competition to Nano Banana Pro. Other players are important for keeping the price of the leaders in check.
Re: FLUX.2: Frontier Visual Intelligence
#4Text 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 Pro variant is...weird:
> Input: We charge $0.015 for each megapixel on the input (i.e. reference images for editing)
> Output: The first megapixel is charged $0.03 and then each subsequent MP will be charged $0.015
Re: FLUX.2: Frontier Visual Intelligence
#5> 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 forward to the distill version.
Re: FLUX.2: Frontier Visual Intelligence
#6Oh, looks like someone had to release something very quickly after Google came for their lunch. Their little 15 mins is over already for BFL as it seems.
Re: FLUX.2: Frontier Visual Intelligence
#7Text 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…
Nice catch. Looks like engineers tried to take care of the GTM part as well and (surprise!) messed it up. In any case, the biggest loser here is Europe once again.
Re: FLUX.2: Frontier Visual Intelligence
#8Oh, looks like someone had to release something very quickly after Google came for their lunch. Their little 15 mins is over already for BFL as it seems.
comparing a closed image model to an open one is like comparing a compiled closed source app to raw source code.
it's pointless to compare in pure output when one is set in stone and the other can be built upon.
Re: FLUX.2: Frontier Visual Intelligence
#9Oh, looks like someone had to release something very quickly after Google came for their lunch. Their little 15 mins is over already for BFL as it seems.
yeah except I can download this and run it on my computer, whereas Nano Banana is a service that Google will suddenly discontinue the instant they get bored with it
Re: FLUX.2: Frontier Visual Intelligence
#10Text 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
This method was used in tons of image generation models. Not saying it's superior or even a good idea, but it definitely wasn't "weird".