license: creativeml-openrail-m
tags:
- stable-diffusion
- text-to-image
datasets:
- ProGamerGov/StableDiffusion-v1-5-Regularization-Images
Min-Illust-Background-Diffusion
This fine-tuned Stable Diffusion v1.5 model was trained for 2000 iterations with a batch size of 4, on a selection of photos of things taped to wall. Training was performed using ShivamShrirao/diffusers with full precision, prior-preservation loss, the train-text-encoder feature, and the new 1.5 MSE VAE from Stability AI. A total of 2100 regularization / class images were used from here. Regularization images were generated using the prompt "artwork style" with 50 DPM++ 2S a Karras steps and a CFG of 7, using the MSE VAE. A negative prompt of "text" was also used for this dataset.
Use the tokens ttw style in your prompts for the effect. Note that the effect also appears to occur at a much weaker strength on prompts that steer the output towards specific artistic styles.
This model will likely not perform well on taping objects that are not traditionally able to be taped to walls.
Example images were generated with the v1 2000 iteration model using:
ttw style, <object> taped to wall