dugemwae
Hi, This is my Attempt at making an CKPT for a kpop Girl Group T*ice, IYKYK.
Training Data :
Trained using HQ picture from Twitter Fanbase
Cropped to 512x512 image
Handpicked image at my liking (trying to cover all possible angle and expression)
Each Person has 45 Image equal, so thats 9*45 Images
Trained on dreambooth local without EMA using nonpruned 1,5 SD base model, fp16, Xformers
using 100 Epoch
Uploaded the best CKPT IMO at 88210 Steps. i'll try to upload a lower steps CKPT or higher.
This model Seems to generate subpar image of J*ong, D*hyun and J*hyo, but it produce great result for the other members. ( for j*hyo i find using the restore face really fix her eye bag by alot)
This model is bad to be used As is, but will produce great result if you merge it with your own model (i suspect because my training data have limited full body image) ill upload an merger and unmerged example
Sample #1 is X/Y Plot using the base CKPT without Merge
Sample #2 is X/Y Plot using the base CKPT Merged with Analogdiffusion
Sample #3 is X/Y Plot using the base CKPT Merged with Anything 3.0
Sample #4 is X/Y Plot using the base CKPT Merged with URPM
What is All Twice SD 1,5?
All Twice SD 1,5 is a highly specialized Image generation AI Model of type Safetensors / Checkpoint AI Model created by AI community user dugemwae. Derived from the powerful Stable Diffusion (SD 1.5) model, All Twice SD 1,5 has undergone an extensive fine-tuning process, leveraging the power of a dataset consisting of images generated by other AI models or user-contributed data. This fine-tuning process ensures that All Twice SD 1,5 is capable of generating images that are highly relevant to the specific use-cases it was designed for, such as kpop, twice, real person.
With a rating of 0 and over 0 ratings, All Twice SD 1,5 is a popular choice among users for generating high-quality images from text prompts.
Can I download All Twice SD 1,5?
Yes! You can download the latest version of All Twice SD 1,5 from here.
How to use All Twice SD 1,5?
To use All Twice SD 1,5, download the model checkpoint file and set up an UI for running Stable Diffusion models (for example, AUTOMATIC1111). Then, provide the model with a detailed text prompt to generate an image. Experiment with different prompts and settings to achieve the desired results. If this sounds a bit complicated, check out our initial guide to Stable Diffusion – it might be of help. And if you really want to dive deep into AI image generation and understand how set up AUTOMATIC1111 to use Safetensors / Checkpoint AI Models like All Twice SD 1,5, check out our crash course in AI image generation.
Popularity
Info
Latest version (Base): 1 File
About this version: Base
Base
