Instructions to use sangoi-exe/sd-webui-codex with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- llama-cpp-python
How to use sangoi-exe/sd-webui-codex with llama-cpp-python:
# !pip install llama-cpp-python from llama_cpp import Llama llm = Llama.from_pretrained( repo_id="sangoi-exe/sd-webui-codex", filename="flux-tenc/t5xxl.gguf", )
output = llm( "Once upon a time,", max_tokens=512, echo=True ) print(output)
- Notebooks
- Google Colab
- Kaggle
- Local Apps
- llama.cpp
How to use sangoi-exe/sd-webui-codex with llama.cpp:
Install from brew
brew install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama-server -hf sangoi-exe/sd-webui-codex:Q4_K_M # Run inference directly in the terminal: llama-cli -hf sangoi-exe/sd-webui-codex:Q4_K_M
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama-server -hf sangoi-exe/sd-webui-codex:Q4_K_M # Run inference directly in the terminal: llama-cli -hf sangoi-exe/sd-webui-codex:Q4_K_M
Use pre-built binary
# Download pre-built binary from: # https://github.com/ggerganov/llama.cpp/releases # Start a local OpenAI-compatible server with a web UI: ./llama-server -hf sangoi-exe/sd-webui-codex:Q4_K_M # Run inference directly in the terminal: ./llama-cli -hf sangoi-exe/sd-webui-codex:Q4_K_M
Build from source code
git clone https://github.com/ggerganov/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-server llama-cli # Start a local OpenAI-compatible server with a web UI: ./build/bin/llama-server -hf sangoi-exe/sd-webui-codex:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama-cli -hf sangoi-exe/sd-webui-codex:Q4_K_M
Use Docker
docker model run hf.co/sangoi-exe/sd-webui-codex:Q4_K_M
- LM Studio
- Jan
- Ollama
How to use sangoi-exe/sd-webui-codex with Ollama:
ollama run hf.co/sangoi-exe/sd-webui-codex:Q4_K_M
- Unsloth Studio new
How to use sangoi-exe/sd-webui-codex with Unsloth Studio:
Install Unsloth Studio (macOS, Linux, WSL)
curl -fsSL https://unsloth.ai/install.sh | sh # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for sangoi-exe/sd-webui-codex to start chatting
Install Unsloth Studio (Windows)
irm https://unsloth.ai/install.ps1 | iex # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for sangoi-exe/sd-webui-codex to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for sangoi-exe/sd-webui-codex to start chatting
- Docker Model Runner
How to use sangoi-exe/sd-webui-codex with Docker Model Runner:
docker model run hf.co/sangoi-exe/sd-webui-codex:Q4_K_M
- Lemonade
How to use sangoi-exe/sd-webui-codex with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull sangoi-exe/sd-webui-codex:Q4_K_M
Run and chat with the model
lemonade run user.sd-webui-codex-Q4_K_M
List all available models
lemonade list
sangoi-exe/sd-webui-codex β Official model hub for Codex WebUI
This Hugging Face repository is the official companion model hub for Codex WebUI β it exists so Codex WebUI users can download the right model files quickly, in a layout that matches the WebUI.
- Codex WebUI (GitHub): https://github.com/sangoi-exe/stable-diffusion-webui-codex
- Codex WebUI license (code): PolyForm Noncommercial License 1.0.0 (noncommercial only)
- Codex WebUI required notice: Copyright (c) 2025-2026 Lucas Freire Sangoi (https://github.com/sangoi-exe/stable-diffusion-webui-codex)
- This repo is not the WebUI code. It only stores model files to make downloads easier for users.
What this is (and what it is not)
This is:
- A curated set of model files (checkpoints / LoRAs / VAEs / text encoders, depending on the folder).
- Organized to plug directly into Codex WebUI's default
models/layout (as configured byapps/paths.jsonin the WebUI repo).
This is not:
- An official upstream distribution of third-party models by their authors.
- A claim of authorship or ownership over any model here.
- Legal advice.
Ownership, licensing, and attribution (read this)
- I did not create or train the models stored here. All model names, files, and trademarks remain the property of their respective owners.
- Each model keeps its own license/terms. This repository does not change those terms. Always check the original model card/license and comply with it.
- Codex WebUI's license applies to the WebUI code, not the model weights. Codex WebUI is licensed under the PolyForm Noncommercial License 1.0.0 (noncommercial only). For commercial use, see the WebUI repository documentation.
- Removal / rights-holder requests: open a Discussion on this Hugging Face repo (title: βRemoval requestβ) or a GitHub issue on the Codex WebUI repo. Include the repo path(s) and proof of ownership/authority. (I intentionally do not publish a direct email address in this README to reduce bot scraping/spam.)
- No license bypass: if an upstream model requires accepting terms (gated access), you must obtain and use it under those terms. This repo is not intended to bypass gating or restrictions.
Getting models
Codex WebUI is the intended client for this repository.
Use Codex WebUI to discover, download, and manage models from this official hub.
How this repo integrates with Codex WebUI
Codex WebUI discovers model files by scanning configured model roots and then exposes them in the UI.
This repository is laid out to match Codex WebUI's default model roots as defined in apps/paths.json (in the WebUI repo). In other words: the folder names here are part of the contract.
If you customize model roots, update apps/paths.json accordingly.
Folder layout (matches Codex WebUI defaults)
These folder names are intentionally aligned with Codex WebUI's default mapping in apps/paths.json. Treat the names as part of the contract (rename only if you also update the paths).
sd15/β SD 1.5 checkpoints (.safetensors)sd15-loras/β SD 1.5 LoRAssd15-vae/β SD 1.5 VAEssd15-tenc/β SD 1.5 text encoderssdxl/β SDXL checkpoints (.safetensors)sdxl-loras/β SDXL LoRAssdxl-vae/β SDXL VAEssdxl-tenc/β SDXL text encodersflux/β Flux model weights (engine-dependent)flux-loras/β Flux LoRAsflux-vae/β Flux VAEsflux-tenc/β Flux text encoderswan22/β WAN 2.2 model weights (engine-dependent)wan22-loras/β WAN 2.2 LoRAswan22-vae/β WAN 2.2 VAEswan22-tenc/β WAN 2.2 text encoderszimage/β ZImage model weights (engine-dependent)zimage-loras/β ZImage LoRAszimage-vae/β ZImage VAEszimage-tenc/β ZImage text encoders
If you change the layout, update apps/paths.json accordingly (otherwise Codex WebUI won't find your files).
Support
For WebUI issues and usage: open an issue on the Codex WebUI GitHub repo.
For missing/corrupt files in this Hugging Face repo: open a discussion/issue here.
- Downloads last month
- 113