├── SSD_1B_colab.ipynb └── README.md /SSD_1B_colab.ipynb: -------------------------------------------------------------------------------- 1 | { 2 | "cells": [ 3 | { 4 | "cell_type": "markdown", 5 | "metadata": { 6 | "id": "view-in-github" 7 | }, 8 | "source": [ 9 | "[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/camenduru/SSD-1B-colab/blob/main/SSD_1B_colab.ipynb)" 10 | ] 11 | }, 12 | { 13 | "cell_type": "code", 14 | "execution_count": null, 15 | "metadata": { 16 | "id": "VjYy0F2gZIPR" 17 | }, 18 | "outputs": [], 19 | "source": [ 20 | "%cd /content\n", 21 | "!git clone -b dev https://github.com/camenduru/Segmind-Stable-Diffusion-hf\n", 22 | "\n", 23 | "!pip install -q git+https://github.com/huggingface/diffusers transformers accelerate safetensors gradio\n", 24 | "!pip install -q https://download.pytorch.org/whl/cu121/xformers-0.0.22.post7-cp310-cp310-manylinux2014_x86_64.whl\n", 25 | "\n", 26 | "%cd /content/Segmind-Stable-Diffusion-hf\n", 27 | "!python app.py" 28 | ] 29 | } 30 | ], 31 | "metadata": { 32 | "accelerator": "GPU", 33 | "colab": { 34 | "gpuType": "T4", 35 | "provenance": [] 36 | }, 37 | "kernelspec": { 38 | "display_name": "Python 3", 39 | "name": "python3" 40 | }, 41 | "language_info": { 42 | "name": "python" 43 | } 44 | }, 45 | "nbformat": 4, 46 | "nbformat_minor": 0 47 | } 48 | -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | 🐣 Please follow me for new updates https://twitter.com/camenduru
2 | 🔥 Please join our discord server https://discord.gg/k5BwmmvJJU
3 | 🥳 Please join my patreon community https://patreon.com/camenduru
4 | 5 | ## 🦒 Colab 6 | 7 | | Colab | Info 8 | | --- | --- | 9 | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/camenduru/SSD-1B-colab/blob/main/SSD_1B_colab.ipynb) | SSD_1B_colab 10 | 11 | ## Main Repo 12 | https://github.com/segmind/distill-sd
13 | https://github.com/Nota-NetsPresso/BK-SDM
14 | 15 | ## Paper 16 | https://arxiv.org/abs/2305.15798
17 | https://openreview.net/forum?id=bOVydU0XKC
18 | 19 | ## Model 20 | https://huggingface.co/segmind/SSD-1B 21 | 22 | ## Dataset 23 | https://huggingface.co/datasets/zzliang/GRIT
24 | https://huggingface.co/datasets/wanng/midjourney-v5-202304-clean
25 | 26 | ## Output 27 | 28 | ![Screenshot 2023-10-24 153135](https://github.com/camenduru/SSD-1B-colab/assets/54370274/76b4c4e5-e2c1-485f-9d0d-9b583de02278) 29 | 30 | 31 | 32 | ## segmind/SSD-1B vs stabilityai/stable-diffusion-xl-base-1.0 33 | 34 | #### Test 1 35 | 36 | 1.29 it/s 13.8GB VRAM to 2.07 it/s 8.3GB VRAM (60% Speed 🚀 -39% VRAM Usage With T4) 37 | 38 | https://github.com/camenduru/SSD-1B-colab/assets/54370274/499175b9-0742-4d94-8961-e2ca00bd6684 39 | 40 | 41 | #### Test 2 Without CPU Offload 42 | 43 | 1.29 it/s 13.8GB VRAM to 2.07 it/s 11.4GB VRAM (60% Speed 🚀 -17% VRAM Usage With T4) 44 | 45 | https://github.com/camenduru/SSD-1B-colab/assets/54370274/924ca0db-0e00-4a5c-8194-759f23bbe294 46 | 47 | --------------------------------------------------------------------------------