ComfyUI installs with an empty models folder. Nothing runs until you fill it, and nothing tells you what to put in there. Here is the whole file set for Flux.1 Schnell GGUF: which four files, where each one goes, the custom node Manager does not install for you, and the one file that is gated and fails until you accept the terms. https://www.youtube.com/watch?v=40HC-M4QeuY The four files, about 12 GB total: - flux1-schnell-Q4_K_S.gguf, 6.8 GB, into models/diffusion_models/FLUX1 - t5xxl_fp8_e4m3fn.safetensors, 4.9 GB, into models/text_encoders/t5 - clip_l.safetensors, 0.2 GB, into models/text_encoders - ae.safetensors, 0.3 GB, into models/vae/FLUX1 8 GB of VRAM runs this. The full precision version of the same model is 23.8 GB and makes pictures you cannot tell apart. Three things that will cost you an hour if nobody tells you: 1. Manager will not install the VAE. Gated repository, so the install just errors. Accept the terms on Hugging Face once, grab the file yourself, and create models/vae/FLUX1, which does not exist yet. 2. Restart ComfyUI after every model install, and do a real browser refresh. A file on disk that has not been imported does not exist as far as the loader is concerned. 3. Manager's Save Path column says "default" for clip_l and never tells you where that resolves to. Only the install log says. Check Filter: Installed afterwards, every time. This is one of four ComfyUI workflow packages in Studio, and they overlap. clip_l and the VAE are shared across all three Schnell builds, so adding a package later is usually one new file, not a fresh start. All four installed comes to roughly 92 GB of weights. At the end the video runs a faceless video workflow on these files. Fifteen images, generated locally, no API call and no per image charge. Commands and the full checklist are in the video description. Questions, drop them below. Cheers

Welcome to Self-Host Hub. This is the free community built around Studio, a self-hosted AI workflow platform with no per-run fees, no subscription tax, and no limits. Browse the Start Here classroom first. It covers what Studio is, what you can build with it, and how to get running fast. Then, checkout Self-Host Studio - Getting Started it walks you through installing Studio. Then come back and answer the poll below. Your answers help me prioritize the content and guides that matter most to you. How will you run Studio?

Welcome to Self-Host Hub. This community is for people building automation infrastructure they own: self-hosted workflows, local AI, and systems you run for yourself or your clients. WHAT IS STUDIO Self-hosted workflow automation platform for AI content pipelines. You own the infrastructure, pick your providers, keep your keys. Four pieces: • App (API + web UI) • Workers (general, video, audio, ComfyUI/GPU), as Docker images or pip install studio-workers for native GPU, Apple Silicon included • Community Catalog (free providers and workflows) • Plus Catalog (advanced production workflows for members) Deploy however you want: single Docker container, Docker Compose, Kubernetes, GPU Host, or hybrid GPU setups. 📋 ROADMAP ✅ MVP: faceless video pipeline (OpenAI, Leonardo, JSON2Video) ✅ Self-hosted video rendering (replaces JSON2Video) ✅ Self-hosted image generation via ComfyUI (replaces Leonardo): Flux.1 Schnell and Flux 2 Klein, generation and image editing ✅ Self-hosted TTS voice cloning (Chatterbox, replaces OpenAI TTS): clone a voice from a ~10 second clip ✅ Bring your own ComfyUI workflows: upload a package, test it privately, publish it to your users 🔜 Self-hosted video generation via ComfyUI Every stage so far eliminated an API bill. The pipeline runs on your own hardware. 📅 UPDATES • 8/21/26 Studio 1.8.0: the video worker is half the size, runs without a GPU, and transcribes subtitles about 2.3x quicker. • 8/17/26 Studio 1.7.0: ComfyUI packages find your models wherever ComfyUI Manager installed them, and your provider API keys carry across upgrades. • 8/11/26 New walkthrough: the complete Studio install on Windows. App plus workers on Windows 11 running WSL, start to finish. Another foundational video every other walkthrough builds on. • 8/9/26 New walkthrough: the complete Studio install on a Mac. App plus native workers on Apple Silicon, start to finish. The foundation video every other walkthrough builds on. • 8/4/26 Studio 1.3.0: pick ComfyUI workflows from a dropdown (no more model field), upload your own ComfyUI packages, one worker serves multiple queues.