stability-ai/stable-diffusion-3.5-large-turbo 🔢🖼️📝❓ → 🖼️
About
A text-to-image model that generates high-resolution images with fine details. It supports various artistic styles and produces diverse outputs from the same prompt, with a focus on fewer inference steps
Example Output
Prompt:
"An impasto unicorn"
Output
Performance Metrics
0.93s
Prediction Time
0.93s
Total Time
1
Images
All Input Parameters
{
"cfg": 1,
"steps": 4,
"prompt": "An impasto unicorn",
"aspect_ratio": "3:2",
"output_format": "webp",
"output_quality": 90,
"prompt_strength": 0.85
}
Input Parameters
- cfg
- The guidance scale tells the model how similar the output should be to the prompt.
- seed
- Set a seed for reproducibility. Random by default.
- image
- Input image for image to image mode. The aspect ratio of your output will match this image.
- prompt (required)
- Text prompt for image generation
- aspect_ratio
- The aspect ratio of your output image. This value is ignored if you are using an input image.
- output_format
- Format of the output images
- negative_prompt
- What you do not want to see in the image
- prompt_strength
- Prompt strength (or denoising strength) when using image to image. 1.0 corresponds to full destruction of information in image.
Output Schema
Output
Example Execution Logs
Seed set to: 3293944150
Running workflow
got prompt
Executing node 294, title: KSampler, class type: KSampler
0%| | 0/4 [00:00<?, ?it/s]
50%|█████ | 2/4 [00:00<00:00, 8.91it/s]
75%|███████▌ | 3/4 [00:00<00:00, 8.90it/s]
100%|██████████| 4/4 [00:00<00:00, 8.89it/s]
100%|██████████| 4/4 [00:00<00:00, 8.90it/s]
Executing node 8, title: VAE Decode, class type: VAEDecode
Executing node 309, title: Save Image, class type: SaveImage
Prompt executed in 0.75 seconds
outputs: {'309': {'images': [{'filename': 'R8_sd3.5L_00001_.png', 'subfolder': '', 'type': 'output'}]}}
====================================
R8_sd3.5L_00001_.png
Version Details
- Version ID
6ce89263555dde3393564e799f1310ee247c5339c3c665250b5dd5d26b7bcc3d- Version Created
- November 7, 2025