It's nice as well for location that are banned to use private US models. Like here in Hong Kong, Google doesn't allow us to subscribe to Gemini Pro. (Same for OpenAI and Claude too actually).
Text 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
> 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.
Oh, 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.
Wow, the Krea relationship soured? These are both a16z companies and they've worked on private model development before. Krea.1 was supposed to be something to compete with Midjourney aesthetics and get away from the plastic-y Flux models with artificial skin tones, weird chins, etc.
This list of partners includes all of Krea's competitors: HiggsField (current aggregator leader), Freepik, "Open"Art, ElevenLabs (which now has an aggregator product), Leonardo.ai, Lightricks, etc. but Krea is absent. Really strange omission.
I ran "family guy themed cyberpunk 2077 ingame screenshot, peter griffin as main character, third person view, view of character from the back" on both nano banana pro and bfl flux 2 pro. The results were staggering. The google model aligned better with the cyberpunk ingame scene, flux was too "realistic"
i think they focus their dataset on photography. flux 1 dev one was never really great at artistic style, mostly locking you into a somewhat generic style. my little flux 2 pro testing does seem to verify that. but with lora ecosystem and enough time to fiddle flux 1 dev is probably still the best if you want creative stylistic results.
Great, 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/
There is no reason to believe Gemini Image is not diffusion model. In fact, generated result suggests it at least have VAE and very likely is a diffusion model variant. (Most likely a transfusion model).
Their 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.
You can run it with a 5090 and the standard ComfyUI template, it just offloads some parts to RAM. Image generation takes about a minute for sizes like 1024x1024.
The 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.
I just finished my Flux 2 testing (focusing on the Pro variant here: https://replicate.com/black-forest-labs/flux-2-pro). Overall, it's a tough sell to use Flux 2 over Nano Banana for the same use cases, but even if Nano Banana didn't exist it's only an iterative improvement over Flux 1.1 Pro.
Some notes:
- Running my nuanced Nano Banana prompts though Flux 2, Flux 2 definitely has better prompt adherence than Flux 1.1, but in all cases the image quality was worse/more obviously AI generated.
- The prompting guide for Flux 2 (https://docs.bfl.ai/guides/prompting_guide_flux2) encourages JSON prompting by default, which is new for an image generation model that has the text encoder to support it. It also encourages hex color prompting, which I've verified works.
- The Flux 2 API will flag anything tangently related to IP as sensentive even at its lowest sensitivity level, which is different from Flux 1.1 API. If you enable prompt upsampling, it won't get flagged, but the results are...unexpected. https://x.com/minimaxir/status/1993365968605864010
- Costwise and generation-speed-wise, Flux 2 Pro is on par with Nano Banana, and adding an image as an input pushes the cost of Flux 2 Pro higher than Nano Banana. The cost discrepancy increases if you try to utilize the advertised multi-image reference feature.
- Testing Flux 1.1 vs. Flux 2 generations does not result in objective winners, particularly around more abstract generations.
The fact that you have the possibility of running Flux locally might be enough of an argument to sway the balance for some cases. For example, if you've already set up a workflow and Google jacks up the price, or changes the API, you have no choice but to go along. If BFL does the same, you at least have the option of running locally.
Updating the GenAI comparison website is starting to feel a bit Sisyphean with all the new models coming out lately, but the results are in for the Flux 2 Pro Editing model!
Note: It should be called out that BFL seems to support a more formalized JSON structure for more granular edits so I'm wondering if accuracy would improve using it.
How much energy does BFL have to keep playing this game against Google and ByteDance (SeeDream)?
If their new fancy model is only middle of the pack, and they're not as open source as the Chinese Qwen image models (or ByteDance / Alibaba / Lightricks video models), what's the point?
It's not just prompt adherence, the image quality of Flux models has been pretty bad. Plastic skin, inhumanely chiseled chins, that general faux "AI" aura.
Indeed, the Flux samples in your test suite that "pass" look God-awful. It might "pass" from a technical standpoint, but there's no way I'd choose Flux to solve my workflows. It looks bad.
(I wonder if they lack people on their data team with good aesthetic taste. It may be as simple as that.)
I think this company is struggling. They're pinned between Google and the Chinese. It's a tough, unenviable spot to be in.
I think a lot of the foundation model companies in media are having a really hard time: RunwayML, PikaLabs, LumaLabs. Some of them have pivoted hard away from solving media for everyone. I don't think they can beat the deep-pocketed hyperscalers or the Chinese ecosystem.
BFL just raised a massive round, so what do I know? I just can't help but feel that even though Runway raised similar money, they're struggling really hard now. And I would really not want to be fighting against Google who is already ahead in the game.
The comparison are very useful but also quite limited in terms of styles. Models tend to have extremely diverse abilities in following a given style against steering to its own.
It's pretty obvious that OpenAI is terrible at it -- it is known for its unmissable touch. However, for Flux it really depends on the style. They already posted at some point that they changed their training to avoid averaging different styles together, which is the ultimate AI look. But this is at odds with the goal to directly generate images that are visually appealing, so the style matching is going to be a problem for a while, at least.
Hey I hope you see this. The scoring needs to be a 0-10 or something with a range rather than pass or fail. Flux one getting the same score for the surfer as Gemini pro 3 reduces the quality of the benchmark.
Genuine question, does anyone use any of these text to image models regularly for non trivial tasks? I am curious to know how they get used. It literally seems like there is a new model reaching the top 3 every week
38 comments
[ 2.6 ms ] story [ 57.8 ms ] threadBut can it still turn my screen orange?
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
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.
Wow, the Krea relationship soured? These are both a16z companies and they've worked on private model development before. Krea.1 was supposed to be something to compete with Midjourney aesthetics and get away from the plastic-y Flux models with artificial skin tones, weird chins, etc.
This list of partners includes all of Krea's competitors: HiggsField (current aggregator leader), Freepik, "Open"Art, ElevenLabs (which now has an aggregator product), Leonardo.ai, Lightricks, etc. but Krea is absent. Really strange omission.
I wonder what happened.
They put our logo after we pointed it out.
Nice eye!
anyone found this? To me the link doesn't lead to the model
See my third comparison in Nano Banana blog post: https://quesma.com/blog/nano-banana-pro-intelligence-with-to...
Some notes:
- Running my nuanced Nano Banana prompts though Flux 2, Flux 2 definitely has better prompt adherence than Flux 1.1, but in all cases the image quality was worse/more obviously AI generated.
- The prompting guide for Flux 2 (https://docs.bfl.ai/guides/prompting_guide_flux2) encourages JSON prompting by default, which is new for an image generation model that has the text encoder to support it. It also encourages hex color prompting, which I've verified works.
- Prompt upsampling is an option, but it's one that's pushed in the documentation (https://github.com/black-forest-labs/flux2/blob/main/docs/fl...). This does allow the model to deductively reason, e.g. if asked to generate an image of a Fibonacci implementation in Python it will fail hilariously if prompt sampling is disabled, but get somewhere if it's enabled: https://x.com/minimaxir/status/1993361220595044793
- The Flux 2 API will flag anything tangently related to IP as sensentive even at its lowest sensitivity level, which is different from Flux 1.1 API. If you enable prompt upsampling, it won't get flagged, but the results are...unexpected. https://x.com/minimaxir/status/1993365968605864010
- Costwise and generation-speed-wise, Flux 2 Pro is on par with Nano Banana, and adding an image as an input pushes the cost of Flux 2 Pro higher than Nano Banana. The cost discrepancy increases if you try to utilize the advertised multi-image reference feature.
- Testing Flux 1.1 vs. Flux 2 generations does not result in objective winners, particularly around more abstract generations.
https://genai-showdown.specr.net/image-editing
It scored slightly higher than BFL's Kontext model, coming in around the middle of the pack at 6 / 12 points.
I’ll also be introducing an additional numerical metric soon, so we can add more nuance to how we evaluate model quality as they continue to improve.
If you're solely interested in seeing how Flux 2 Pro stacks up against the Nano Banana Pro, and another Black Forest model (Kontext), see here:
https://genai-showdown.specr.net/image-editing?models=km,nbp...
Note: It should be called out that BFL seems to support a more formalized JSON structure for more granular edits so I'm wondering if accuracy would improve using it.
If their new fancy model is only middle of the pack, and they're not as open source as the Chinese Qwen image models (or ByteDance / Alibaba / Lightricks video models), what's the point?
It's not just prompt adherence, the image quality of Flux models has been pretty bad. Plastic skin, inhumanely chiseled chins, that general faux "AI" aura.
Indeed, the Flux samples in your test suite that "pass" look God-awful. It might "pass" from a technical standpoint, but there's no way I'd choose Flux to solve my workflows. It looks bad.
(I wonder if they lack people on their data team with good aesthetic taste. It may be as simple as that.)
I think this company is struggling. They're pinned between Google and the Chinese. It's a tough, unenviable spot to be in.
I think a lot of the foundation model companies in media are having a really hard time: RunwayML, PikaLabs, LumaLabs. Some of them have pivoted hard away from solving media for everyone. I don't think they can beat the deep-pocketed hyperscalers or the Chinese ecosystem.
BFL just raised a massive round, so what do I know? I just can't help but feel that even though Runway raised similar money, they're struggling really hard now. And I would really not want to be fighting against Google who is already ahead in the game.
It's pretty obvious that OpenAI is terrible at it -- it is known for its unmissable touch. However, for Flux it really depends on the style. They already posted at some point that they changed their training to avoid averaging different styles together, which is the ultimate AI look. But this is at odds with the goal to directly generate images that are visually appealing, so the style matching is going to be a problem for a while, at least.
Seedream is also very good and makes me think the next version will challenge Google for SOTA image gen
Increasingly feels like image gen is a solved problem
You jinxed yourself: https://huggingface.co/Tongyi-MAI/Z-Image-Turbo
https://huggingface.co/black-forest-labs/FLUX.2-dev/blob/mai...
So, it’s not open source.