Sign In
homemodelsimagesvideospostsarticlesbountieschallengeseventsupdatesshop

upsc8l3

33

596

7

Updated: Jul 4, 2025

styledenoisedeblur

Download (164 MB)

Verified:

SafeTensor

Type

LoRA

Stats

254

0

Reviews

(15)

Published

Jul 2, 2025

Base Model

Flux.1 Kontext

Training

Steps: 800

Usage Tips

Strength: 1.2

Trigger Words

upsc8l3

Hash

AutoV2
741085CDFD
default creator card background decoration
IngniteX's Avatar

IngniteX

The FLUX.1 [dev] Model is licensed by Black Forest Labs. Inc. under the FLUX.1 [dev] Non-Commercial License. Copyright Black Forest Labs. Inc.

IN NO EVENT SHALL BLACK FOREST LABS, INC. BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH USE OF THIS MODEL.

"Upscale" the image deblurring and denoising to restore some sharpness, reduce noise, and enhance fine details.

Atleast what this lora is supposed todo. Its highly experimental, and I would need further build out the lora. At the moment that are some 4k images scaled down to 1024 ( due to flux.kontext limitation? ). This lora does not magically fix bad images but it can enhance it a bit. Eitherway its an experimentation lora and should be seen as that.

In its experimental state trained on ai-toolkit with resolution of 512 due to vram issues atm.

It sometimes works on some images with subtle adjustments. But its highly experimental.

Version 0.2

Trigger words remove due to some minor issues.

Use this lora as some sort style. IT DOES NOT MAGIC FIX IMAGES yet.

  • make the composition clear using deblur and denoise

  • make the composition clear using deblur

  • make the composition clear using denoise

Version 0.1
Trigger words used, testing out stuff

  • upsc8l3 the image using deblur

  • upsc8l3 the image using denoise

  • upsc8l3 the image using deblur and denoise