Pamela Anderson

Name: Pamela Anderson
Rating: 4.89 (9 reviews)
Author: iolmstead23

233

Updated: Feb 22, 2024

celebrity

photorealistic woman pamela anderson

Download (19.01 KB)

Verified: a year ago

PickleTensor

This asset is only available as a PickleTensor which is an insecure format. We've taken precautions to ensure the safety of these files but please be aware that some may harbor malicious code.

Details

Type	Embedding
Stats	233 0
Reviews	Positive (19)
Published	Feb 22, 2024
Base Model	SD 1.5
Training	Steps: 5,000
Trigger Words	Pamela_Anderson_512v1-5000
Hash	AutoV2 F00A01F463

1 File

default creator card background decoration

iolmstead23

This resource is intended to reproduce the likeness of a real person. Out of respect for this individual and in accordance with our Content Rules, only work-safe images and non-commercial use is permitted.

If you are this person or a legal representative of this person, and would like to request the removal of this resource, you can do so here.

Notes: I will no longer be flipping the images horizontally as this “muddies the mirror”. Also I am training on modified PT that has had byteorder and .data/serialization_id removed. This allows it to pass the safety checker!

Pre Training

I gathered 19 images of Pamela Anderson. I am only using Birme to crop the HD photos instead of using Faceswap to align the faces. Some of the images were full body as I wanted to retain her face even when zoomed out. I used Blip captioning to generate the filewords and edited each individually to reduce potential hallucinations.

Training

I used 0.005:100,0.0025:250,0.001:500,0.0005 for my learning rate. I am going for 5K training steps total. I am using a batch size of 1 with Gradient Accumulation Steps set to 3. I am running locally on a RTX 4090. I am using 12.5 out of 24 GB. The estimated time of completion is 2 hours. For the embedding I am using 8 vectors per token. I switched to SD 1.5 EMA Only model for training.

Things that I could have done better

I could have upscaled the images before extracting the faces so I could reduce blur.