--- license: mit --- ### mia from [lost nova](https://store.steampowered.com/app/1603410) on Stable Diffusion via Dreambooth #### model by no3 This your the Stable Diffusion model fine-tuned the mia-sd-1.5-beta1 concept taught to Stable Diffusion with Dreambooth. It can be used by modifying the `instance_prompt`: **sks_mia** You can also train your own concepts and upload them to the library by using [this notebook](https://colab.research.google.com/github/huggingface/notebooks/blob/main/diffusers/sd_dreambooth_training.ipynb). And you can run your new concept via `diffusers`: [Colab Notebook for Inference](https://colab.research.google.com/github/huggingface/notebooks/blob/main/diffusers/sd_dreambooth_inference.ipynb), [Spaces with the Public Concepts loaded](https://huggingface.co/spaces/sd-dreambooth-library/stable-diffusion-dreambooth-concepts). ### note If the output is real girl or a woman instead of mia just add **tow parentheses** in the instance_prompt, example `((sks_mia))`. If you want to convert diffusers to checkpoint ".ckpt" to use in UI like [AUTOMATIC1111](https://github.com/AUTOMATIC1111/stable-diffusion-webui) or any UI that's uses .ckpt file, Use this [script](https://gist.github.com/Christopher-Hayes/636ba25e0ae2e7020722d5386ac2571b) If you have issues or questions feel free to visit the Community Tab and start discussion about it. Here are some images used for training this concept: ![image 1](https://huggingface.co/no3/mia-sd-1.5-beta1/resolve/main/concept_images/1t.png) ![image 2](https://huggingface.co/no3/mia-sd-1.5-beta1/resolve/main/concept_images/2.png) ![image 3](https://huggingface.co/no3/mia-sd-1.5-beta1/resolve/main/concept_images/3.png) ![image 4](https://huggingface.co/no3/mia-sd-1.5-beta1/resolve/main/concept_images/4.png) ![image 5](https://huggingface.co/no3/mia-sd-1.5-beta1/resolve/main/concept_images/7.png) ![image 6](https://huggingface.co/no3/mia-sd-1.5-beta1/resolve/main/concept_images/6.png) Non included images my be removed next model for minimizing learning confusion, but you can view them in [concept_images](https://huggingface.co/no3/mia-sd-1.5-beta1/tree/main/concept_images) folder.