> ## Documentation Index
> Fetch the complete documentation index at: https://docs.gpuhub.com/llms.txt
> Use this file to discover all available pages before exploring further.

# SD Image Generation Memory Leak

> If you experience continuous memory growth while generating images or switching models in the AUTOMATIC1111 SD WebUI, you can try the following solution:

## Steps to Resolve Memory Growth Issues

1. Install Dependencies

```bash theme={null}
apt install libgoogle-perftools-dev
```

2. Set Environment Variable Before Launching WebUI
   Verify the existence of `libtcmalloc.so.4` using:

```bash theme={null}
ldconfig -p | grep libtcmalloc.so.4
```

If found, set the environment variable:

```bash theme={null}
export LD_PRELOAD=libtcmalloc.so.4
```

3. Launch WebUI

After setting the environment variable, start the WebUI:

```bash theme={null}
python launch.py --port 6006
```

Source

This solution is derived from Discussion ["Linux - Use tcmalloc for memory management for slight speed boost and much, MUCH lower CPU memory leakage" #6722](https://github.com/AUTOMATIC1111/stable-diffusion-webui/discussions/6722) on the AUTOMATIC1111 SD WebUI GitHub repository.