From cfbbcbf922ca5b71249c8a89c72f6492eb4da732 Mon Sep 17 00:00:00 2001 From: Artur Penner Date: Thu, 15 Jan 2026 18:12:57 +0100 Subject: [PATCH] Add documentation and requirements --- README.md | 71 ++++++++++++++++++++++++++++++++++++++++++++++++ requirements.txt | 8 ++++++ 2 files changed, 79 insertions(+) create mode 100644 README.md create mode 100644 requirements.txt diff --git a/README.md b/README.md new file mode 100644 index 0000000..a14edd8 --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +# ComfyUI-VIBE 🎨 + +Implementation of **VIBE** (Visual Instruction Based Editor) as a custom node for [ComfyUI](https://github.com/comfyanonymous/ComfyUI). Edit images using natural language instructions (e.g., "make it winter", "change the dog to a cat"). + +VIBE leverages the efficient **Sana1.5-1.6B** diffusion model and **Qwen3-VL-2B-Instruct** for fast, high-quality image manipulation. + +--- + +## ✨ Features +- **Instruction-based Editing**: No complex prompting required. +- **Latent Support**: Connect an `Empty Latent Image` to define output resolution. +- **Fast Inference**: Powered by Sana1.5's linear attention. +- **Local Model Support**: Runs entirely on your hardware. + +--- + +## 🚀 Installation + +1. **Clone the repository**: + Navigate to your `ComfyUI/custom_nodes` folder and run: + ```bash + git clone https://github.com/ato-zen/ComfyUI-VIBE + ``` + +2. **Install dependencies**: + Open terminal in the `ComfyUI-VIBE` folder and run: + ```bash + pip install -r requirements.txt + ``` + +--- + +## 📂 Model Setup + +This node looks for models in: `ComfyUI/models/vibe/` + +1. **Create the target folder**: + ```bash + mkdir -p models/vibe + cd models/vibe + ``` + +2. **Download the weights**: + Clone from Hugging Face (requires [git-lfs](https://git-lfs.github.com/)): + ```bash + git clone https://huggingface.co/iitolstykh/VIBE-Image-Edit + ``` + +Structure should look like: +```text +ComfyUI/models/vibe/ +└── VIBE-Image-Edit/ + ├── model_index.json + ├── unet/ + ├── vae/ + ├── text_encoder/ + └── tokenizer/ +``` + +--- + +## 📜 Credits & Acknowledgements + +- **Original Project**: [VIBE: Visual Instruction Based Editor](https://github.com/ai-forever/VIBE) +- **Model Authors**: Grigorii Alekseenko, Aleksandr Gordeev, Irina Tolstykh, et al. +- **Based on**: [Sana](https://github.com/NVlabs/Sana) and [Qwen3-VL](https://github.com/QwenLM/Qwen3-VL). + +**ComfyUI Node implementation by [ato-zen](https://github.com/ato-zen).** + +--- +*License: Apache 2.0* diff --git a/requirements.txt b/requirements.txt new file mode 100644 index 0000000..f1a4968 --- /dev/null +++ b/requirements.txt @@ -0,0 +1,8 @@ +diffusers>=0.33.1 +transformers +accelerate +loguru +pydantic>=2.0.0 +pydantic-settings +python-dotenv +sentencepiece