sexual situations

physical violence

disturbing

male nudity

extremist

hanging

hate symbols

nazi party

revealing clothes

weapon violence

female swimwear or underwear

male swimwear or underwear

partial nudity

white supremacy

adult toys

graphic male nudity

illustrated explicit nudity

nudity

self injury

graphic violence or gore

graphic female nudity

corpses

wide hips

convenient censoring

peeing

oral invitation

emaciated bodies

exposed female nipple

blowjob

female nudity

sexual activity

sexual intent

undressed

male underwear

female swimwear

genitals

female underwear

thick thighs

breasts out

strapless leotard

vore

bestiality

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

sexy

nsfw

suggestive

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

Claudia Photodrommaka Busty Claudia / Claudia / Claudia E / Claudia F / NinaModel works good in 0.7-1.1 strength range.For SD1.5 Loras I recommend Westmix v1, nextG, endlessReality, epicrealism and photon models. It works with anime and other models too, with interesting results.For Pony Lora I recommend using Pony Realism and vividPDXL_Real models.For Flux regular Flux 1.DPlease share feedback so I can improve it

First try with Hunyuan video, trained on 160 images for 20 epochs

Hunyuan Video V1

Flux v1.0

Pony model, was having issues creating SDXL models, but Pony is working pretty good.Recommended to use with vividPDXL_Real checkpoint, I am getting the best likeness. Other Pony models except the original can get weird artifacts.Training set was updated: added more high res images, updated taggingFor training I used the "SDXL - LoRA AI_characters standard v1.1" preset from kohya_ss, about 1500 steps did the job, anything over ended up overtraining.I have tried Prodigy, Dadaptation and Adafactor dynamic optimizers, the results were not as good as AdamW optimizer.

Pony v2.0

Changes since v1<ol><li>Trained on all the published Claudia Photodromm image sets. This resulted in 285 images, which I had a hard time training a Lora on, poses were weird and it looked overtrained.I split the dataset into two halves, trained them separately. After I merged the two resulting Loras, and updated the metadata to reflect the image count and tags. If you have a better suggestion for large datasets please share</li><li>Cleaned up the dataset tagging, and made it more consistent, added poses, hand positions, etc. LMK if you see weird things.</li><li>Re-uploaded model with fixed metadata, where Lora name in prompt shows up the same as filename. Tensors are the same, model behaves exactly that same, as one v1.5 I uploaded few days ago</li></ol>

v1.5

v1 of the model internal name - clphd6_DA_captioned3-000080.safetensors

v1.0

Claudia Photodromm (SD 1.5, Pony, Flux)

Type	LoRA
Stats	109 0
Reviews	Positive (8)
Published	Jan 28, 2025
Base Model	Hunyuan Video
Trigger Words	claudia photodromm clphd
Hash	AutoV2 ED03447945