Auto Fix for sizes
Turn it on to round unusable image sizes automatically.
Create a picture from a description
Stable Diffusion 3.5 Medium
Stable Diffusion 3.5 Medium is a Multimodal Diffusion Transformer (MMDiT) text-to-image model that features improved performance in image quality, typography, complex prompt understanding, and resource-efficiency.
Made by Stability AI100 creditsper run Pro
Opens the image studio with Stable Diffusion 3.5 Medium ready to use. You can look around as a guest. Running it takes the Pro plan or higher.
What Stable Diffusion 3.5 Medium makes, what it needs and what you get
What it makes
Create a picture from a description
Turns a written description into a picture.
What you need
- A description of the picture
What you get
A new picture
- JPEG and PNG files
About Stable Diffusion 3.5 Medium
Stable Diffusion 3.5 Medium creates an image from a text description. Its Auto Fix setting rounds an image size the model cannot use directly to the nearest size it can. The model focuses on image quality, typography (lettering inside the picture) and understanding complex prompts.
Besides your prompt, you can change four settings. Image Size begins at landscape 4:3. Steps runs from 1 to 50 and starts at 40. Guidance scale runs from 0 to 20 and starts at 4.5. Auto Fix is on at first. With it off, an image size the model cannot use directly is rejected with an error.
Stable Diffusion 3.5 Large also costs 100 credits. It has no Auto Fix setting, and it starts Steps and Guidance scale at lower values.
Other models for this job
Same job: create a picture from a description. Compare before you choose.
Image Free Open
SDXL LightningCreate a picture from a description
A speed-tuned variant of Stable Diffusion XL that generates high-quality images in a handful of steps, trading a little fine detail for near-instant results - ideal for rapid concept exploration and draft iteration.
ByteDance10 creditsper run
Image Free Open
Qwen Image LightningCreate a picture from a description
Alibaba's fast-inference Qwen Image variant, tuned for near-instant text-to-image generation without sacrificing prompt accuracy - built for rapid drafts and high-volume workflows.
Alibaba10 creditsper run
Image Free Open
Qwen ImageCreate a picture from a description
Alibaba's Qwen Image model generates accurate, detailed visuals from text prompts with strong prompt comprehension, including legible in-image text and complex compositions.
Alibaba10 creditsper run
Image Free Open
Flux KreaCreate a picture from a description
A FLUX variant tuned by Krea for stylized, painterly image generation - strong for concept art and creative visuals that want more artistic flair than strict photorealism.
Black Forest Labs85 creditsper run
What it does well
Image quality and typography
It focuses on image quality and on typography, the lettering inside a picture.
Guidance scale control
Sets how close the model stays to your prompt, from 0 to 20.
How to use Stable Diffusion 3.5 Medium
How It Works
How It Works
01
Type your prompt
Write a text description of the picture you want.
02
Choose size and settings
Pick an Image Size, then change Steps, Guidance scale or Auto Fix if you like.
03
Generate
Generate to receive an image for 100 credits.
Tip Guidance scale runs from 0 to 20 and starts at 4.5.
Good for
Signs and invitations with words
Create pictures where lettering is part of the design.
Illustrations of complex ideas
Describe an idea with many parts and see it as a picture.
Questions
Quick answers to help you get the most out of Stable Diffusion 3.5 Medium in FunAI Studio.
1. What do I need to provide?
2. What does Auto Fix do?
3. How is it priced?