Maanav

Developer Relations @bfl_ai.
I like morning coffee, writing, and kinesthetic sports.

[Maanav @maanavdalal]

@krishnavadithy1 @bfl_ai @ComfyUI 😂 top 5 replies to my thread: https://t.co/brSJE8LkcI

get free FLUX credits!

[Maanav @maanavdalal]

@bfl_ai @ComfyUI this guy has had a weird week...

reply with an edit and I'll run the best ones on him (FLUX 3 Image Klein in Comfy)

winners get FLUX credits!

[Maanav @maanavdalal]

@bfl_ai @ComfyUI this guy has had a weird week...

reply with an edit and I'll run the best ones on him (FLUX 3 Image Klein in Comfy)

winners get FLUX credits!

[Maanav @maanavdalal]

@JohnJenocide @bfl_ai @ComfyUI Anything FLUX 3 related! we've got partner nodes and API works too.

[Maanav @maanavdalal]

@makeitrad1 Hella rad!

[Maanav @maanavdalal]

The wall between cheap and quality upscaling just... caved.

SOTA upscaling, cheaper prices.

[Black Forest Labs @bfl_ai]

The FLUX Video Upscaler received a full upgrade.

It’s now the best video upscaler on the market, while costing less than Topaz Astra 2 and being twice as fast.

Upscale any video up to 4K.

Link to try it in the comments.

[Maanav @maanavdalal]

@Zygomatic03 @theo have you taken your daily T3?

[Maanav @maanavdalal]

It's spooky season and if you've met me before, you know I'm not a fan of spiders.

FLUX 3 Max came out today, and it's a SOTA video model that lets you generate a 10s video in 12s, so you can friend-ify your fears at lightspeed.

Listen to my new buddy:

[Maanav @maanavdalal]

I2v gens on this model are absolutely bananas, creativity is off the (AA) charts ;)

[Artificial Analysis @ArtificialAnlys]

FLUX 3 Max from @fal, a post-trained version of @bfl_ai's FLUX 3, ranks #2 on AA-Video-I2V v1.1 (statistically tied for #1) and #4 on AA-Video-T2V v2.1, ahead of the base FLUX 3 on both

FLUX 3 Max generates 5 to 20 second, 720p videos with native audio from a text prompt or a starting image. fal reports that it generates a 10 second video in under 12 seconds. We benchmarked it at the high reasoning level.

FLUX 3 Max ranks #2 on AA-Video-I2V v1.1 and #4 on AA-Video-T2V v2.1, statistically tied with Dreamina Seedance 2.5 and MiniMax H3 (768p) on both, and ahead of its base model FLUX 3. On AA-Video-T2V v2.1, it scores highest of any model in the Physics capability, and in the Marketing & Advertising and Live-Action Film use cases.

fal prices FLUX 3 Max at $10.20/min for 720p video, compared to $17.40/min for FLUX 3, and $24.60/min for Dreamina Seedance 2.5 and $5.40/min for MiniMax H3 (768p) on Image to Video. For the first three weeks of launch, fal is offering 75% off, at $2.55/min.

Congratulations to @fal on the release!

See below for our detailed analysis and comparisons between FLUX 3 Max and other leading models on AA-Video-T2V v2.1 and AA-Video-I2V v1.1 🧵

[Maanav @maanavdalal]

@bfl_ai @fal Me now that this model is released

[Maanav @maanavdalal]

@fal @bfl_ai Absolute cookage from our friends @fal

[Maanav @maanavdalal]

@JustinAngel @fal @bfl_ai Honestly, quality feels way better. Gens are so great imo

[Maanav @maanavdalal]

@glitchcandies Your creatures are out of this world, this morph is so damn cool

[Maanav @maanavdalal]

Last one I swear, but it's just so cute. Get creating with FLUX 3 Max, and make your dreams a reality!

[Maanav @maanavdalal]

I can't stop using FLUX 3 Max. This model has been a delight to test with and use in what feels like realtime 🧵

[fal @fal]

Introducing FLUX 3 Max, the latest post-trained video model from fal Research in partnership with @bfl_ai.

FLUX 3 Max is tied for #1 in image-to-video quality on independent third-party benchmarks, generating a 10-second, 720/768p video in ~12 seconds.

For the next three weeks, FLUX 3 Max is 75% off, making it the most affordable frontier video model at its quality level.

[Maanav @maanavdalal]

Different styles are also incredible. The future feels really bright for creators

[Maanav @maanavdalal]

@fal Wonder what else this could mean 👀

[Maanav @maanavdalal]

Ty for having me! Here's a "where's waldo" we generated live, can you find him?

[ComfyUI @ComfyUI]

Inside FLUX 3 Image: How Black Forest Labs Built It https://t.co/FJqiKqhUYS

[Maanav @maanavdalal]

@yuvalav Thanks for your testing and support with this release :) So cool to finally be here

[Maanav @maanavdalal]

Unlock wonderful stuff for your work with as little as 8GB VRAM thanks to our wonderful community including @ComfyUI! Can't wait to see the LoRAs and crazy modifications everyone makes :)

[Maanav @maanavdalal]

FLUX 3 Image Klein is the model release we've all been waiting for! 5.6B, open weights, and you can run it with as little as 8GB VRAM. Text-to-image, image editing, 10 image multi reference.

[Black Forest Labs @bfl_ai]

FLUX 3 Image Klein is here.

Open Weights with the quality of a large frontier model. Customizable and fast.

5.6B parameters and runs on a single consumer GPU.

Native 4K, bounding boxes, and pixel-perfect editing.

[Maanav @maanavdalal]

Create worlds of your own, taking image references (which I think of as inspiration) from everywhere you like and turn them into a beautiful composition: