This model is designed for use with the embedding, it has been trained using OneTrainer with pivotal tuning.

Trained on high quality portraits in black and white.

During my tests I noticed that depending on checkpoints the total absence of color is not always consistent - especially when colors are present in prompts (i.e.: adding blue eyes will likely produce a monochrome image with the character having blue eyes).

Notes

• ComfyUI workflow for the samples generation should be embedded in the images, in case you want to check more settings.

• It seems to still be flexible enough even at 1.0.

• It's intended to use with this embedding, it's been trained with OneTrainer with pivotal tuning!