---
title: "SD 3.5 Large — Spacelike AI"
description: "Multimodal Diffusion Transformer · 8.1 B parameters · Stability AI"
canonical: https://spacelike.ai/models/sd-3-5-large/
---

# SD 3.5 Large — on dedicated hardware, by Spacelike AI

_Multimodal Diffusion Transformer · 8.1 B parameters · Stability AI_

SD 3.5 Large is the flagship of the SD 3.5 family. At 8.1 B parameters it is the largest MM-DiT-based Stable Diffusion model Stability AI has released, targeting **professional image generation at 1-megapixel native resolution** with substantially improved typography, anatomy and compositional coherence over SD 3.

A sibling distilled variant, *SD 3.5 Large Turbo*, produces equivalent quality in 4 steps at the cost of some prompt adherence. Both share the same MM-DiT backbone.

## Specification

- **Architecture:** MM-DiT · 38 blocks · improved-QK-norm
- **Parameters:** 8.1 B *(backbone)*
- **Training objective:** Rectified flow matching
- **Native resolution:** 1024 × 1024 (1 MP)
- **Text encoders:** CLIP-L + CLIP-G + T5-XXL (frozen)
- **Sampler shown:** Euler · 28 steps · cfg 3.5
- **License:** Stability AI Community License
- **Release:** October 22, 2024
- **Checkpoint:** sd3.5_large.safetensors

## Client

[Tenstorrent Inc.](https://tenstorrent.com/) — performance improvement

## Links

- [implementation](https://github.com/tenstorrent/tt-metal/blob/main/models/tt_dit/models/StableDiffusion35.md)
- [Hugging Face](https://huggingface.co/stabilityai/stable-diffusion-3.5-large)
- [Vendor announcement](https://stability.ai/news/introducing-stable-diffusion-3-5)

## Sample output

![SD 3.5 Large — sample output generated by Spacelike AI](https://spacelike.ai/images/sd-3-5-large/05.avif)

---

SD 3.5 Large implementation by **Spacelike AI GmbH**, Vienna. Interactive viewer: https://spacelike.ai/models/sd-3-5-large/

Sample images licensed [CC BY 4.0](https://creativecommons.org/licenses/by/4.0/) — attribute "Spacelike AI" and link back to https://spacelike.ai/.