thick thighs

sexual situations

physical violence

disturbing

extremist

hanging

hate symbols

nazi party

breasts out

strapless leotard

revealing clothes

weapon violence

female swimwear or underwear

male swimwear or underwear

partial nudity

self injury

white supremacy

adult toys

graphic male nudity

illustrated explicit nudity

nudity

sexual activity

graphic violence or gore

graphic female nudity

vore

bestiality

corpses

breast out

one breast out

huge breasts

gigantic breasts

huge butt

wide hips

covered nipples

hair over breasts

no panties

sitting on face

convenient censoring

anal

dildo riding

downblouse

peeing

oral

oral invitation

emaciated bodies

hentai

porn

bukkake

cumshot

cumdrip

cum in pussy

cum on face

cum on hair

cum on body

cum on tongue

cum on hands

cum in mouth

cum on pussy

eat_cum

fellatio

implied fellatio

after fellatio

triple fellatio

autofellatio

pov fellatio

fucked silly

presenting ass

presenting pussy

spreading legs

spread legs

swimwear

lingerie

bikini

latex clothing

TRPCError

READ EACH VERSION DESCRIPTIONRecommended settings:<ul><li>1024 x 1024 resolution (most consistent)</li><li>Juggernaut XL (or similar photorealistic model)<ul><li>Use Natural Language prompts</li></ul></li><li>0.8 Strength</li><li>No refiner</li><li>DPM++ 2M Karras<ul><li>&gt;30 steps</li></ul></li></ul>Note: upscaling may degrade film grainTrained on many high-resolution 35mm and medium format film imagesThe produced film grain may look bad if files are stored as .jpg, so .png is recommendedMost training images were shot with Portra, Ektar, or Superia X-TRA filmstock

Version 1.0 is finally here! I have worked very hard to ensure that I trained on high-quality, well captioned images, but I still am not an expert! If anyone has any SDXL LORA Training tips, let me know!!! I am trying to reduce the bias in my model, but it's been very difficult (for example, asking for a "handyman" will produce mostly white men).

v1.0

Better response to prompts, more coherent lines, and less jpeg artifacting than Alpha v0.2. Trained on a photorealistic model, not SDXL 1.0 base.Use the following prompting template:"film photography style" [your prompt], [modifiers], [shot type], [shot angle], [grain level]<ul><li>[modifiers] - still a WIP, optional<ul><li>nothing, bokeh, bloom, god rays, moody, etc.</li></ul></li><li>[shot type] - only use for portraits or pictures with people<ul><li>nothing, Extreme Close Up, Close Up, Medium Close Up, Medium Shot, Medium Full Shot, Full Shot</li></ul></li><li>[shot angle] - describes the camera angle<ul><li>nothing, bokeh, bloom, god rays, moody, etc.</li></ul></li><li>[grain level] - important to reduce Jpeg artifacts<ul><li>nothing, light grain, medium grain, heavy grain</li></ul></li></ul>** Note: nothing means "", so DO NOT type "nothing" **

beta v0.4

This version is slightly undertrainedCurrent weak points include portraits, adherence to prompt descriptors (close-up, low angle), and occasional lack of grain

alpha v0.2

SDXL Film Photography Style

Type	LoRA
Stats	4,412 12,041
Reviews	Very Positive (232)
Published	May 20, 2024
Base Model	SDXL 1.0
Usage Tips	Clip Skip: 1 Strength: 0.8
Trigger Words	film photography style light grain medium grain heavy grain
Hash	AutoV2 9E2A98E1F2