# Stable diffusion automatic1111 dreambooth

**URL:** </static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fstable-diffusion-automatic1111-dreambooth%2F27944%3E%5C
**Category:** Beginners\
**Created:** [December 16, 2022, 1:22pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fstable-diffusion-automatic1111-dreambooth%2F27944 "2022-12-16T13:22:24Z")\
**Posts on this page:** 2\
**Page:** 1

<div class="post-metadata">

**Author:** ![geeklan](https://avatars.discourse-cdn.com/v4/letter/g/49beb7/32.png) [@geeklan](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fgeeklan)%5C
**Post date:** [December 16, 2022, 1:22pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fstable-diffusion-automatic1111-dreambooth%2F27944%2F1 "2022-12-16T13:22:24Z")

</div>

Hey, guys! I’m new to stable diffusion and I’m trying to learn. I do not know if I can take this question here, but I installed stable diffusion locally through AUTOMATIC1111. My problem is with Dreambooth. When I start training, it give me a video card memory allocation error even activating the 8bit adam and fp16 option. Could someone help me?

RuntimeError: CUDA out of memory. Tried to allocate 256.00 MiB (GPU 0; 8.00 GiB total capacity; 7.09 GiB already allocated; 0 bytes free; 7.21 GiB reserved in total by PyTorch) If reserved memory is \>\> allocated memory try setting max\_split\_size\_mb to avoid fragmentation. See documentation for Memory Management and PYTORCH\_CUDA\_ALLOC\_CONF

---

<div class="post-metadata">

**Author:** ![de-marauder](https://avatars.discourse-cdn.com/v4/letter/d/e495f1/32.png) [@de-marauder](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fde-marauder)%5C
**Post date:** [December 22, 2022, 10:16am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fstable-diffusion-automatic1111-dreambooth%2F27944%2F2 "2022-12-22T10:16:06Z")

</div>

Hello geeklan  
By any chance have you been able to solve this error? I have run into the exact same error while trying to training a dreambooth model with this repo [GitHub - gammagec/Dreambooth-SD-optimized: Implementation of Dreambooth (https://arxiv.org/abs/2208.12242) with Stable Diffusion](https://github.com/gammagec/Dreambooth-SD-optimized).

Any help will be appreciated. Thank you.