Install anaconda ubuntu local8/9/2023 ![]() Have you installed any customization with the game, e.g. What do you expect to see? A painting in my inventory What happens when the bug occurs? The sketch pad will charge me for the design but then will never finish it and when I try to sell to build mode. Steps: How can we find the bug ourselves? Use the sketch pad for the freelancer career What expansions, game packs, and stuff packs do you have installed? All I mean all. What is your current game version number? 4 How often does the bug occur? Every time (100%) ![]() ![]() Find something interesting, and copy the prompt used, then try modifying it.Which language are you playing the game in? English The best place to start, I’ve found, the Lexica.art site. If you’re like me, you will need ideas for prompts. More details, including how to use an image as a starting prompt, can be found in the README. You can use flags like -n5 to generate multiple images, -s for number of steps, and -g to generate a grid. Type -help at the dream> prompt to see a list of options. You can then use the -G flag as shown in the Dream Script Stable Diffusion repo. And be sure to download the pre-trained model as shown. Follow its installation instructions here, clone the GFPGAN directory alongside the stable-diffusion directory. The module for face restoration is called GFPGAN. It’s really simple to install, while in the conda ldm environment, run: pip install realesrganĪfter it’s installed, go back into the dream script, generate an image, and this time add the -U flag at the end of the prompt (either 2 or 4) dream> butterfly -U 4 There is a separate module you can use to upscale the output, called Real-ESRGAN. Mountains and river, output re-fed multiple times Generating larger imagesīy default the output is 512x512 pixels. You can take the output from one step and re-feed it as the input again, and come up with some interesting results. dream> mountains and river, Artstation, Golden Hour, Sunlight, detailed, elegant, ornate, rocky mountains, Illustration, by Weta Digital, Painting, Saturated, Sun rays -init_img=/home/mendhak/Desktop/rough_drawing.png You can also use a crude image as a source for the prompt with the -init_img flag. dream> photograph of highly detailed closeup of victoria sponge cake -S2420237860 This allows you to regenerate the exact same image by specifying the seed with your text prompt. Against each line, you will also see a seed number that looks something like this: -S2420237860. Wait a few seconds, and an image gets generated in the outputs/img-sample folder.Ĭonveniently, a dream_log.txt file shows you all the prompts you’ve run in case you want to refer back to something. * Initialization done ! Awaiting your command (-h for help, 'q' to quit )Īs an example, try dream> photograph of highly detailed closeup of victoria sponge cake conda activate ldmĪ prompt will appear where you can enter some natural language text. Activate the conda environment, preload models, and run the dream script. Once the setup is done, these are the steps to run Stable Diffusion. The first time this step runs, it will take a long time, due to the numerous dependencies involved. While still in the Stable Diffusion repo, create the conda environment in which the scripts will run. Mv ~/Downloads/sd-v1-4.ckpt models/ldm/stable-diffusion-v1/model.ckpt Create the conda environment Next, move the model file downloaded previously, into this repo, renaming it to model.ckpt mkdir -p models/ldm/stable-diffusion-v1/ The Dream Script Stable Diffusion repo is a fork of Stable Diffusion, it comes with some convenience functions to accept a text prompt, as well as a web interface. Get the Dream Script Stable Diffusion repository Under the ‘files and versions’ tab, download the checkpoint file, sd-v1-4.ckpt. Once registered, head to the latest model repository, which at the time of writing is stable-diffusion-v-1-4-original. ![]() ![]() You will need to register with any email address. The model file needed by Stable Diffusion is hosted on Hugging Face. ~/anaconda3/bin/conda init Get the model file ~/anaconda3/bin/conda config -set auto_activate_base false Once installation is finished, initialise conda, but tell it not to activate each time the shell starts. The download URL may change over time, so replace it.: wget Ĭhmod +x Anaconda3-2022.05-Linux-x86_64.sh Setup Install Anacondaĭownload the Anaconda installer script from their website and install it. The simplest and best way of running Stable Diffusion is through the Dream Script Stable Diffusion fork, which comes with some convenience functions. Because it’s open source, it’s also easy to run it locally, which makes it very convenient to experiment with in your own time. Stable Diffusion is a machine learning model that can generate images from natural language descriptions. The simplest way to get started with Stable Diffusion on Ubuntu Mendhak / Code The simplest way to get started with Stable Diffusion on Ubuntu ![]()
0 Comments
Leave a Reply.AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |