Categories: Tutorials

Local Installation of Stable Diffusion 3.5

So, it’s finally here. Stable Diffusion 3.5 has been released by StabilityAI on October 22nd, 2024. After huge back clashes in the community on Stable Diffusion 3, they are back with the improved version.

Basically three model variants are on the open market:

Model Variant	Parameters	Resolution Range	Key Features	Ideal Use Cases
Stable Diffusion 3.5 Large (Base Model)	8 billion	1 megapixel	Most powerful model in the SD family Superior image quality and prompt adherence Supports professional-grade outputs	Professional-grade, high-quality image generation at 1 megapixel resolution
Stable Diffusion 3.5 Large Turbo (Distilled model)	8 billion	1 megapixel	Distilled version of 3.5 Large Faster generation in just 4 steps Maintains high-quality images with exceptional prompt adherence	Faster image generation with high quality for time-sensitive professional projects
Stable Diffusion 3.5 Medium ( release on Oct 29th)	2.5 billion	0.25 – 2 megapixels	Designed for consumer hardware Features improved MMDiT-X architecture Balanced quality with ease of customization	Consumer-grade projects with flexibility and support for resolutions up to 2 megapixels

All the models weights are customizable in nature and can be used for free non-commercial and commercial usage up to $1M in annual revenue. The released models are under StabilityAI Community License. Interested AI Startups and Enterprises can checkout their license page for in-depth understanding.

Now we just dive into the installation in ComfyUI. For Automatic1111 and Forge its all in development stage. We will be updating it soon in the coming days.

Install SD3.5 locally now ! 😍

3 variants available:
– Large
-Medium
-Large Turbo

Support for:-
-Comfy
-A1111/Forge not yet

Follow our installation page from here:https://t.co/fJVfhsYjDf

Enjoy some cool SD3.5 ImaGens 😋 pic.twitter.com/kbTS4zis96

— Stable Diffusion Tutorials (@SD_Tutorial) October 23, 2024

Table of Contents

Installation

1. First you have to install ComfyUI into your machine if you are new to it. Old user need to update the ComfyUI by navigating to the Manager and select “Update ComfyUI” and “Update All“.

2. Download the model weight from StabilityAI’s Hugging face for Stable Diffusion 3.5 Large.

Download the model weight from StabilityAI’s Hugging face for Stable Diffusion 3.5 Large turbo.

3. While downloading for the first time, you need to accept their license from their repository.

4. After downloading save them inside “ComfyUI/models/checkpoint” folder.

5. Now, download the clip models (clip_g.safetensors, clip_l.safetensors, and t5xxl_fp16.safetensors) from StabilityAI’s Hugging Face and save them inside “ComfyUI/models/clip” folder.

As Stable Diffusion 3.5 uses the same clip models, you do not need to download if you are a Stable Diffusion 3 or Flux user.

6. Restart ComfyUI to take effect.

Workflow

1. Download both the workflows for Stable Diffusion3.5 Large and Stable Diffusion3.5 Large Turbo from StabilityAI’s Hugging face.

2. Drag and drop to ComfyUI.

Recommended settings by Official StabilityAI:

For Stable Diffusion 3.5 Large

CFG:4.5

Steps: 28

Sampler: Euler, DPM++

For Stable Diffusion 3.5 Large turbo

CFG:0

Steps: 4

Sampler: Euler, DPM++

We have tested Stable Diffusion 3.5 Large with the recommended settings.

Here is the result. Frankly, the result is not cherry picked. This is the first generation we got. Not so bad.

Prompt used:

portrait , high quality creative photoshoot of a model , black dress, bluish hair, red lipstick, wearing funky sunglasses, Vogue style, fashion photoshoot, professional makeup, uhd

Negative prompts are not required.

CFG: 4.5

Resolution: 1024 by 1024

Steps: 28

admage