From 1ef88b664edf2af33d5715513c7e07fe90ac27db Mon Sep 17 00:00:00 2001
From: comrender <139063732+comrender@users.noreply.github.com>
Date: Wed, 17 Sep 2025 14:03:29 +0200
Subject: [PATCH] Update README.md

---
 README.md | 83 ++++++++++++++++++++++++++++++++++++++++++++++++++++++-
 1 file changed, 82 insertions(+), 1 deletion(-)

diff --git a/README.md b/README.md
index 7f6174d..0f63cae 100644
--- a/README.md
+++ b/README.md
@@ -1,2 +1,83 @@
 # ComfyUI-NanoSeed
-A custom ComfyUI node for seamless image editing using fal.ai's NanoBanana and Seedream (v4) models.
+
+A custom ComfyUI node for seamless image editing using fal.ai's NanoBanana and Seedream (v4) models. Edit images with AI-powered prompts, supporting multi-image batches, custom resolutions, and easy fal.ai API key integration directly in the node interface.
+
+## Features
+
+- **Dual Model Support**: Switch between NanoBanana for fast, lightweight edits and Seedream for high-fidelity variations.
+- **Batch Processing**: Handle multiple input images in one go.
+- **Flexible Inputs**: Custom width/height, number of outputs (up to 4), and seed control.
+- **User-Friendly**: No hardcoding—enter your fal.ai key right in ComfyUI.
+
+## Installation
+
+1. Clone this repo into `ComfyUI/custom_nodes/`.
+
+   ```bash
+   git clone https://github.com/yourusername/ComfyUI-NanoSeed.git
+   ```
+
+2. Install dependencies: `pip install -r requirements.txt`.
+
+3. Restart ComfyUI and find the node under **image/edit** as "Edit image NanoBanana + Seededit by ComRender".
+
+Get your fal.ai API key at [fal.ai](https://fal.ai) and drop it into the node for instant edits!
+
+## Usage
+
+### Node Inputs
+
+- **image** (IMAGE): Input image tensor (supports batches).
+- **prompt** (STRING): Descriptive prompt for editing the image.
+- **model** (COMBO): Select "nano_banana" or "seedream".
+- **fal_key** (STRING): Your fal.ai API key.
+- **width/height** (INT, optional): Custom output resolution (0 to use input size).
+- **num_images** (INT, optional): Number of variations to generate (1-4).
+- **seed** (INT, optional): Random seed for reproducibility.
+
+### Outputs
+
+- **edited_image** (IMAGE): Batch of edited image tensors.
+
+### Example Workflow
+
+1. Load an image using `Load Image`.
+2. Connect to `NanoSeedEdit`.
+3. Set prompt: "Add a cyberpunk neon glow to the cityscape".
+4. Select model and enter your API key.
+5. Queue prompt—outputs will be ready for preview or further nodes.
+
+## API Details
+
+This node uses the fal.ai endpoints:
+
+- [NanoBanana Edit](https://fal.ai/models/fal-ai/nano-banana/edit/api)
+- [Seedream v4 Edit](https://fal.ai/models/fal-ai/bytedance/seedream/v4/edit/api)
+
+Images are encoded as base64 PNGs for upload. Sync mode ensures immediate results.
+
+## Troubleshooting
+
+- **API Errors**: Check your fal.ai key and quota. Ensure internet access.
+- **Resolution Issues**: For NanoBanana, custom sizes resize the input; for Seedream, they set output dims.
+- **Batch Limits**: ComfyUI handles batches, but API calls are per-image to avoid rate limits.
+- **Dependencies**: Only `requests` is required; no Torch extras needed.
+
+If issues persist, open a GitHub issue with logs.
+
+## License
+
+MIT License. See [LICENSE](LICENSE) for details.
+
+## Author
+
+ComRender
+
+## Built With
+
+- [ComfyUI](https://github.com/comfyanonymous/ComfyUI)
+- [fal.ai APIs](https://fal.ai)
+
+---
+
+*Star this repo if it helps your workflow! 🚀*