generative-models
orbstack
generative-models | orbstack | |
---|---|---|
21 | 36 | |
22,508 | 4,382 | |
4.4% | 3.5% | |
7.3 | 6.2 | |
29 days ago | 6 months ago | |
Python | Shell | |
MIT License | MIT License |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
generative-models
-
Creating Videos with Stable Video Diffusion
git clone https://github.com/Stability-AI/generative-models.git && cd generative-models
- Show HN: I have created a free text-to-image website that supports SDXL Turbo
- How To Increase Performance Time on MacOS
-
Introducing Stable Video Diffusion: Stability AI's New AI Research Tool for Image-to-Video Synthesis
Generative Models by Stability AI Github Repository
-
image-to-video tutorial
# clone SD repo !git clone https://github.com/Stability-AI/generative-models.git # cd into working directory # the % sets the pwd globally as usually each command is run in a subshell in google colab %cd /content/generative-models/ # installing dependencies !pip install -r requirements/pt2.txt !pip install . # HACK # I was getting ModuleNotFoundError: No module named 'scripts' # This is what ChatGPT suggested (let me know if there is a better way) file_path = '/content/generative-models/scripts/sampling/simple_video_sample.py' new_text = "import sys\nsys.path.append('/content/generative-models')\n\n" with open(file_path, 'r') as file: original_content = file.read() updated_content = new_text + original_content with open(file_path, 'w') as file: file.write(updated_content) # Need to create a checkpoints/ folder - that is where the system looks for weights import os dir_name = 'checkpoints' if not os.path.exists(dir_name): os.makedirs(dir_name) print(f"Directory '{dir_name}' created") else: print(f"Directory '{dir_name}' already exists") # Download weights into checkpoints/ folder from huggingface_hub import hf_hub_download hf_hub_download(repo_id="stabilityai/stable-video-diffusion-img2vid", filename="svd.safetensors", local_dir="checkpoints", local_dir_use_symlinks=False) # I can't remember if this step is needed but it aims to reduce the memory footprint of pytorch # I kept getting CUDA out of memory # I got these instructions from the out of memory error message os.environ['PYTORCH_CUDA_ALLOC_CONF'] = 'max_split_size_mb:512' print(os.environ['PYTORCH_CUDA_ALLOC_CONF']) # Inside of scripts/sampling/simple_video_sample.py you need to make 2 updates 1. input_path (line 26): update to the location of your file (I attached Gdrive so mine was "/content/drive/MyDrive/examples/car.jpeg" 2. decoding_t (line 34): update it to 5. you need to do this for memory preservation (CUDA out of memory). I'm not sure if 5 is the best value but it worked for me # Finally generate the video (output will be in the outputs/ folder) !python scripts/sampling/simple_video_sample.py
-
Stable Video Diffusion
It looks like the huggingface page links their github that seems to have python scripts to run these: https://github.com/Stability-AI/generative-models
- GitHub - Stability-AI/generative-models: Generative Models by Stability AI
-
How does ComfyUI load SDXL 1.0 so VRAM-efficiently? How do I do the same in vanilla python code?
However, when using the example code from HuggingFace or setting up stuff from the StabilityAI/generative-models repo in a jupyter notebook, I end up using 21 GB of VRAM just for running the default pipeline (with no base model output). If I try to run the extra `base.vae.decode(base_latents)` after generation to get unrefined outputs, I get a CUDA out of memory error as it blows past the 24GB of my NVIDIA RTX 3090.
- SDXL 1.0 is out!
-
SDXL 0.9 Anyone having luck NOT centering subjects?
SDXL uses cropping information as part of the conditioning. Images were randomly cropped during training and the coordinates of the crop were included as two integers at the end of the conditioning vector. If you're using ComfyUI you can use the CLIPTextEncodeSDXL node to specify where the upper left corner of the image should appear to be in relation to some hypothetical uncropped image. Here's a figure with examples from the report on SDXL:
orbstack
-
Show HN: OpenOrb, a curated search engine for Atom and RSS feeds
For a brief moment, I thought this was related to https://orbstack.dev
-
Ask HN: Tips to get started on my own server
If you use a Mac and just want to mess around with linux try something like Orbstack(https://orbstack.dev/) to start up VMs and mess around. The benefit of this is you're going to break things a bunch as you get started. Going from there I'd start looking automating the deployment of the various components the 'old fashioned' way aka writing shell scripts/using SSH. Once you do that then go to using things like Ansible or Terraform etc.
- Orbstack can destroy your Time Machine backups
-
NoSQL Postgres: Add MongoDB compatibility to your Supabase projects with FerretDB
FerretDB provides a Docker image allowing us to run it locally, for example via Orbstack, with a couple of simple commands.
-
Ask HN: Who is hiring? (February 2024)
OrbStack | Founding Engineer | US/Europe REMOTE | Full-time | https://orbstack.dev
OrbStack is making Docker containers & development environments delightful. Our app replaces Docker Desktop and makes containers faster, lighter, and easier to work with. It's the tool of choice for PlanetScale, Replicate, and other hot companies.
Containers should be a joy to use, not something you have to put up with. Let's build the future of dev envs.
As a founding engineer, you'll mainly work on breaking high-level ideas down into tough systems problems, solving them, and taking ownership of projects. If https://cpu.land and https://docs.orbstack.dev/architecture excite you, you'll be right in place.
Email: jobs orbstack dev
-
How Virtualisation came to Apple Silicon Macs
Before you give up, give OrbStack a try: https://orbstack.dev/
It’s significantly faster than Docker and some users in the Discord community have been able to use it to run hand-built Linux x86 VMs on Apple Silicon.
It’s a paid product though, but you can download it for free and try it out before paying.
-
Install Craft CMS v5 (alpha) with one command via DDEV
If you haven't installed a Docker runtime, you might be happy with Orbstack. Other alternatives: DDEV docs: Docker installation.
- Windows is now an app for iPhones, iPads, Macs, and PCs
-
Podman Desktop v1.5 with Compose onboarding and enhanced Kubernetes pod data
For MacOS I can really recommend https://orbstack.dev
It integrates very nicely, has very low CPU idle usage and also lets you quickly spawn VMs with bidirectional file sharing set up.
Since I switched I haven't looked back.
- Any idea what this icon is in the menu bar on my Mac? I've got the spinning beach ball every time I hover over it and it's been like that for weeks. What is it and process do I need to kill?
What are some alternatives?
background-removal-js - Remove backgrounds from images directly in the browser environment with ease and no additional costs or privacy concerns. Explore an interactive demo.
colima - Container runtimes on macOS (and Linux) with minimal setup
wizmap - Explore and interpret large embeddings in your browser with interactive visualization! 📍
Podman Desktop - Podman Desktop - A graphical tool for developing on containers and Kubernetes
evernote-ai-chatbot
UTM - Virtual machines for iOS and macOS
gping - Ping, but with a graph
multipass - Multipass orchestrates virtual Ubuntu instances
graphic-walker - An open source alternative to Tableau. Embeddable visual analytic
lima - Linux virtual machines, with a focus on running containers
xgen - Salesforce open-source LLMs with 8k sequence length.
Proxyman - Modern. Native. Delightful Web Debugging Proxy for macOS, iOS, and Android ⚡️