FLUX Deblur: 4 MP input vs Sume's 1-4x image upscale
FLUX Deblur sharpens a blurry image with no prompt or mask, up to 4 MP. Sume has no deblur endpoint; its image upscaler takes a factor of 1 to 4.

FLUX Deblur takes one blurry image, up to 4 MP, and returns a sharper version of the same scene with no prompt or mask. Sume has no deblur endpoint. It offers Image Upscale 1.0, which takes a public HTTPS image_url and an upscale_factor from 1 to 4 (default 2); that changes size, and the Sume spec does not describe it as a blur remover.
BFL facts are from its FLUX Deblur page and the June 25, 2026 release note; Sume facts from its OpenAPI spec, read 2026-09-30.
What does FLUX Deblur take?
POST /v1/flux-tools/deblur-v1 with image as base64 or an HTTP(S) URL; the maximum image area is 4 MP. It is built on FLUX.2 Klein 9B, applies to the full frame, and does not support region masks. BFL advises running deblur before later steps such as upscaling, outpainting or export.
What does Sume's upscaler take?
The route is POST /v1/image-upscale-1.0/upscale and the public model id is sume/image-upscale-1.0. The request needs image_url; upscale_factor is 1 to 4 (default 2) and output_format is png, jpg or webp (default png). The default mode is async, which returns the job id and polling URLs; sync waits at most 30 seconds.
| Item | FLUX Deblur | Sume Image Upscale 1.0 |
|---|---|---|
| Purpose per docs | Sharpen a blurry image | Upscale an image |
| Input | Base64 or URL, up to 4 MP | Public HTTPS image_url |
| Controls | None (no prompt, no mask) | upscale_factor 1-4, output_format |
| Result handling | Async job, poll for the result | Job: async by default, bounded sync wait |
Will upscaling fix a blurry photo?
The Sume spec only says the model upscales; it makes no claim about restoring focus. If the source is soft, test a sample before batching, and treat a larger output as larger, not necessarily sharper. For damaged scans see restore old photos with AI.
How should I use the factor?
Pick the smallest factor that reaches your target size, since the default is 2 and the ceiling is 4. For an exact pixel target, see upscale to an exact pixel size, and for the endpoint overview, the image upscale API.
Sources
Related posts
More in Use cases
- FLUX Erase: mask rules and dilate_pixels vs a Sume mask edit
FLUX Erase removes a masked object with no prompt and a dilate_pixels setting. Sume has no erase endpoint; masked edits use mask_url with a prompt.
- FLUX Outpainting: 4 MP canvas cap vs Sume's image size options
FLUX Outpainting extends an image onto a canvas of up to 4 megapixels with offsets. Sume documents no outpainting mode; use image_size or aspect_ratio.
- GivingTuesday 2026 video ideas: a captioned 3-scene ask
GivingTuesday is December 1, 2026. Build a short nonprofit ask as three avatar scenes (hook, impact, CTA) with burned-in captions and a music bed.
- Google Ads AI label setting: a label inside the video
Google now allows an AI label inside AI video ad creatives without tripping text-overlay policy. Burn your own label line as the last step with Sume.
Written by Sume