On August 20, Black Forest Labs shipped a seemingly quiet new tool on its official blog: FLUX Video Upscale. What it does can be described in one sentence — regenerate a video of up to 20 seconds into a deliverable at up to native 4K resolution. But for anyone who has actually worked with video generation tools, this step is precisely the most painful link in the whole pipeline: however stunning the model output looks, it always remains one upscaling pass away from "deliverable."

Generation Resolution Is Not Delivery Resolution

The official announcement states the problem plainly: a shot generated in hd still needs another step before it is ready for delivery. Broadcast, campaign, and big-screen formats all demand more pixels, and local upscalers tend to struggle at those resolutions.

The spec sheet for FLUX Video Upscale is restrained:

  • Input: starting from 480p, up to 20 seconds, no more than 50MB, source resolution capped at 2560×1440
  • Upscaling: upscale_factor supports 1.5×, 2×, and 3×; from an hd input that lands at roughly 1080p, 2K, and 4K
  • Ceiling: about 14.4 megapixels per frame, with output keeping the source aspect ratio
  • Audio: preserved as-is
  • Billing: you pay only for delivered output; rejected clips are not charged

Two Modes: A Line Between Fidelity and Creativity

What is really worth chewing on is the dual-mode design.

Precise mode runs 4 steps at $0.07/megapixel-second — faster and cheaper, and the better choice when you need to keep identity or reference details consistent. Creative mode runs 8 steps at $0.10/megapixel-second, using more steps to push repair and detail generation — at the cost that it may change or even replace the identity in the frame, so reference consistency is lower than Precise.

In other words, BFL has split "faithful restoration" and "invented detail" into two explicit product options, and it even allows attaching a prompt in Creative mode to steer the direction of detail generation. Upscaling has gone from a technical parameter to a creative decision.

Generative Super-Resolution, Not Interpolation

The official product page puts it well: FLUX Video Upscale regenerates the video at a higher resolution rather than interpolating between the pixels already there. It understands FLUX 3 output natively and fixes issues a general-purpose upscaler can miss — smudged faces, or gridded artifacts on textures like water and grass.

The logic tracks with FLUX 3 itself: a model jointly trained across image, video, and audio, announced on July 23, with video generation going live on August 4 (up to 20 seconds per request, FHD, 24fps, synchronized audio), MCP integration on August 11, and upscaling filling the gap on August 20. In a bit over a month, BFL assembled the full "generate — repair — deliver" pipeline.

Video Model Competition Enters the Toolchain Phase

My take: the value of this news is not "yet another upscaler," but that it marks a shift in where video generation competition is heading. When every model can generate 20-second clips with audio, what keeps users around is no longer raw generation quality but whether the delivery chain is complete — can it reach 4K, can it keep characters consistent, and how is it priced.

FLUX Video Upscale is available through the BFL API and playground, and has also landed on Replicate. For content teams, pricing starting at $0.07/megapixel-second gives 4K delivery a clear cost accounting formula.

So the question becomes: when generation is no longer the bottleneck, which link is your workflow stuck on?

Reference: FLUX Upscale: 2K and 4K for Video (official announcement)