![]() Doing this by hand would likely take an incredible amount of time, but we can edit it all pretty quickly using either a combination of awk, sed, and grep or writing scripts to do it for us in Python We’ll probably be working with a massive amount of data, so we’ll need to be able to edit it all. All we need to do is set them with these linesĬode: pip install -r requirements.txt Part 2: Training Dataįrom here we can train, the repo includes sample data from the works of Shakespeare to train on. In my experience installing a specific version of CUDA doesn’t do that automatically. Now that CUDA is installed we probably have to set the environment variables for it. Wget /compute/cuda/11.7.1/local_installers/cuda-repo-wsl-ubuntu-11-7-local_11.7.1-1_b for WSL Ubuntu Sudo apt -y install cuda-11-7 cuda-toolkit-11-7If you’re using WSL you should replace Sudo cp /var/cuda-repo-ubuntu-local/cuda-*-keyring.gpg /usr/share/keyrings/ Sudo mv cuda-ubuntu2204.pin /etc/apt/preferences.d/cuda-repository-pin-600 ![]() It's truly remarkable and I hope more and more people realize this.Ĭode: wget /compute/cuda/repos/ubuntu2204/x86_64/cuda-ubuntu2204.pin Never before has visual art been so liquid and able to be morphed, molded and changed. Take a picture of yourself even doing whatever pose you want and use that. Mirror it, flip it, bring it into a photo editor and roughly cut out parts you don't want or draw pointy ears. You can also just take real actual images already out there, and not just photos but drawings, digital art, movie stills, whatever, and wring them through and get something that looks totally different, even if you used an already-made image to get there. I did that for all my Shadowrun images I've done so far, because Midjourney is much better at coherence without need to put a whole lot in. There is no shame either in getting outputs and running them through SD to guide it to whatever you want. There is negative prompts, framing issues (which are all but eliminated with ControlNet and the posing options), deep rabbit holes that are lined with porn and anime and anime porn, all mixed with cargo culting weirdness as we are all throwing bones and claiming we see something in the summoning procedure. Right yeah, and when you do get SD going it still won't guide you like Midjourney. I had to use anna kendrick on MJ to get something close. BUT, it still had a better idea of the actual person I want to use as a reference. ![]() I put a photoreal MJ prompt in and it looked all messed up.
0 Comments
Leave a Reply. |
Details
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |