sexual situations

physical violence

disturbing

male nudity

hanging

hate symbols

nazi party

revealing clothes

graphic violence or gore

pg-13

corpses

peeing

oral invitation

emaciated bodies

exposed female nipple

undressed

male underwear

female swimwear

genitals

female underwear

thick thighs

breasts out

strapless leotard

vore

breast out

one breast out

huge breasts

gigantic breasts

huge butt

covered nipples

hair over breasts

no panties

sitting on face

anal

dildo riding

downblouse

oral

porn

futanari

hentai

nude

lingerie

nsfw

suggestive

self injury

extremist

hate speech

diapers

urine

sexy

weapon violence

female swimwear or underwear

male swimwear or underwear

partial nudity

white supremacy

adult toys

graphic male nudity

illustrated explicit nudity

nudity

convenient censoring

blowjob

female nudity

scat

graphic female nudity

wide hips

sexual activity

sexual intent

child on child

incest

latex clothing

swimwear

bukkake

fellatio

cumshot

implied fellatio

eat_cum

cumdrip

cum in pussy

cum on face

after fellatio

cum on hair

cum on body

cum on tongue

cum on hands

cum in mouth

triple fellatio

autofellatio

fucked silly

cum on pussy

pov fellatio

■This is the testing ground for the color conversion I’ve been wanting.■The description for each LoRA is provided within its respective tab.■If you're new to Kontext, try installing it using the instructions at the URL below.It's well-documented and easy to set up.<a target="_blank" rel="ugc" href="https://docs.comfy.org/tutorials/flux/flux-1-kontext-dev">https://docs.comfy.org/tutorials/flux/flux-1-kontext-dev</a>■I used AI Toolkit to train this LoRA.If you're interested in training, the developer has provided a tutorial at the URL below — give it a try!<div data-youtube-video><iframe width="640" height="480" allowfullscreen="true" autoplay="false" disablekbcontrols="false" enableiframeapi="false" endtime="0" ivloadpolicy="0" loop="false" modestbranding="false" origin playlist src="https://www.youtube.com/embed/WSWubJ4eFqI?rel=1" start="0"></iframe></div>

Training Data (3.9 MB):natron_log_to_HDR_sample■This LoRA converts normal images into low-contrast images similar to ARRI_LogC4. This has made it possible to turn regular images into HDR images.■This is a bit more specialized, so color conversion is required. If you simply wish to reduce overexposure or color saturation, please use the ACEScg_look LoRA instead.■Please use the prompt suggested in the trigger tag—this is the same prompt I used when training the LoRA.■When converting from ARRI_LogC4 to linear sRGB or ACEScg, the following OCIO configuration supports it:studio-config-v1.0.0_aces-v1.3_ocio-v2.1.ocioIt can be downloaded here:<a target="_blank" rel="ugc" href="https://github.com/AcademySoftwareFoundation/OpenColorIO-Config-ACES/releases/tag/v1.0.0">https://github.com/AcademySoftwareFoundation/OpenColorIO-Config-ACES/releases/tag/v1.0.0</a>■Any software that supports OCIO should be able to handle the conversion.The following software are good candidates:After Effects, DaVinci Resolve, Natron, NukeIn some cases, it may also be possible in ComfyUI if OCIO support is enabled via an extension.I have uploaded an example of the conversion done in Natron in the sample images, so please use it as a reference.■However, this is not a perfect ARRI_LogC4 conversion, and negative values often appear in the shadows.If the artifacts are unacceptable, setting the mix to around 0.6 during linear conversion will retain some of the low contrast from the log, resulting in better balance. This will also preserve richer gradation when performing tone mapping.As a side note, in Natron the OCIO colorspace mix doesn’t seem to work, so I used merge-copy mix 0.4 to partially blend the log image and get the same result.For the OCIO display node, I set gain to 1.5 to match sRGB brightness, but you can also do this by adding a Grade node above it—adjust as you prefer. If you have any questions about the conversion, feel free to ask; I’ll share any info I can, though it may take some time.

ARRI_LogC4

This LoRA mimics the ACES tone mapping to suppress overexposure and overly saturated colors. These factors are often what give images a distinctly digital look, so the result should feel more subdued and refined.Vivid colors, especially red, tend to saturate easily, so the effect is more noticeable. However, on the flip side, overexposure and high saturation can sometimes create a sense of flair or “sizzle,” so which you prefer is entirely up to you. It should be effective for images that feel a bit too saturated and leave you wishing for a more balanced look. Please use the prompt suggested in the trigger tag—this is the same prompt I used when training the LoRA.

ACEScg_look

Color_Convert_Lab

キャプチャ.JPG

Type	LoRA
Stats	55 0
Reviews	Positive (5)
Published	Aug 12, 2025
Base Model	Flux.1 Kontext
Training	Steps: 5,000 Epochs: 60
Trigger Words	Convert the image to an ACES-like appearance, preserving highlight detail and avoiding overexposure. Maintain a smooth tonal roll-off in the brightest areas, extend the dynamic range, and ensure natural color rendering without channel saturation. Shadows should retain subtle detail, and midtones should remain balanced for a filmic, cinematic look. Avoid clipping in both highlights and shadows.
Hash	AutoV2 35F5D21429