stability-ai/stable-diffusion-3.5-large 🔢🖼️📝❓ → 🖼️

⭐ Official ▶️ 1.9M runs 📅 Oct 2024 ⚙️ Cog 0.16.8 📄 Paper ⚖️ License
image-to-image text-to-image

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, thanks to Query-Key Normalization.

Example Output

Prompt:

"*aesthetic* #boho #fashion, full-body 30-something woman laying on microfloral grass, candid pose, overlay reads Stable Diffusion 3.5, cheerful cursive typography font"

Output

Example output

Performance Metrics

8.85s Prediction Time
8.85s Total Time
1 Images
All Input Parameters
{
  "cfg": 4.5,
  "steps": 40,
  "prompt": "~*~aesthetic~*~ #boho #fashion, full-body 30-something woman laying on microfloral grass, candid pose, overlay reads Stable Diffusion 3.5, cheerful cursive typography font",
  "aspect_ratio": "1:1",
  "output_format": "webp",
  "output_quality": 90,
  "prompt_strength": 0.85
}
Input Parameters
cfg Type: numberDefault: 5Range: 1 - 10
The guidance scale tells the model how similar the output should be to the prompt.
seed Type: integer
Set a seed for reproducibility. Random by default.
image Type: string
Input image for image to image mode. The aspect ratio of your output will match this image.
prompt (required) Type: string
Text prompt for image generation
aspect_ratio Default: 1:1
The aspect ratio of your output image. This value is ignored if you are using an input image.
output_format Default: webp
Format of the output images
negative_prompt Type: string
What you do not want to see in the image
prompt_strength Type: numberDefault: 0.85Range: 0 - 1
Prompt strength (or denoising strength) when using image to image. 1.0 corresponds to full destruction of information in image.
Output Schema

Output

Type: stringFormat: uri

Example Execution Logs
Seed set to: 3168632025
Running workflow
got prompt
Executing node 6, title: CLIP Text Encode (Prompt), class type: CLIPTextEncode
Executing node 67, title: ConditioningZeroOut, class type: ConditioningZeroOut
Executing node 68, title: ConditioningSetTimestepRange, class type: ConditioningSetTimestepRange
Executing node 69, title: Conditioning (Combine), class type: ConditioningCombine
Executing node 294, title: KSampler, class type: KSampler
0%|          | 0/40 [00:00<?, ?it/s]
2%|▎         | 1/40 [00:00<00:05,  7.48it/s]
5%|▌         | 2/40 [00:00<00:08,  4.60it/s]
8%|▊         | 3/40 [00:00<00:07,  4.71it/s]
10%|█         | 4/40 [00:00<00:07,  4.77it/s]
12%|█▎        | 5/40 [00:01<00:07,  4.80it/s]
15%|█▌        | 6/40 [00:01<00:07,  4.82it/s]
18%|█▊        | 7/40 [00:01<00:06,  4.83it/s]
20%|██        | 8/40 [00:01<00:06,  4.84it/s]
22%|██▎       | 9/40 [00:01<00:06,  4.73it/s]
25%|██▌       | 10/40 [00:02<00:06,  4.77it/s]
28%|██▊       | 11/40 [00:02<00:06,  4.79it/s]
30%|███       | 12/40 [00:02<00:05,  4.81it/s]
32%|███▎      | 13/40 [00:02<00:05,  4.83it/s]
35%|███▌      | 14/40 [00:02<00:05,  4.84it/s]
38%|███▊      | 15/40 [00:03<00:05,  4.84it/s]
40%|████      | 16/40 [00:03<00:04,  4.84it/s]
42%|████▎     | 17/40 [00:03<00:04,  4.85it/s]
45%|████▌     | 18/40 [00:03<00:04,  4.86it/s]
48%|████▊     | 19/40 [00:03<00:04,  4.86it/s]
50%|█████     | 20/40 [00:04<00:04,  4.86it/s]
52%|█████▎    | 21/40 [00:04<00:03,  4.86it/s]
55%|█████▌    | 22/40 [00:04<00:03,  4.85it/s]
57%|█████▊    | 23/40 [00:04<00:03,  4.85it/s]
60%|██████    | 24/40 [00:04<00:03,  4.86it/s]
62%|██████▎   | 25/40 [00:05<00:03,  4.86it/s]
65%|██████▌   | 26/40 [00:05<00:02,  4.86it/s]
68%|██████▊   | 27/40 [00:05<00:02,  4.86it/s]
70%|███████   | 28/40 [00:05<00:02,  4.86it/s]
72%|███████▎  | 29/40 [00:05<00:02,  4.85it/s]
75%|███████▌  | 30/40 [00:06<00:02,  4.85it/s]
78%|███████▊  | 31/40 [00:06<00:01,  4.86it/s]
80%|████████  | 32/40 [00:06<00:01,  4.85it/s]
82%|████████▎ | 33/40 [00:06<00:01,  4.85it/s]
85%|████████▌ | 34/40 [00:07<00:01,  4.85it/s]
88%|████████▊ | 35/40 [00:07<00:01,  4.86it/s]
90%|█████████ | 36/40 [00:07<00:00,  4.85it/s]
92%|█████████▎| 37/40 [00:07<00:00,  4.86it/s]
95%|█████████▌| 38/40 [00:07<00:00,  4.85it/s]
98%|█████████▊| 39/40 [00:08<00:00,  4.85it/s]
100%|██████████| 40/40 [00:08<00:00,  4.85it/s]
100%|██████████| 40/40 [00:08<00:00,  4.85it/s]
Executing node 8, title: VAE Decode, class type: VAEDecode
Executing node 309, title: Save Image, class type: SaveImage
Prompt executed in 8.65 seconds
outputs:  {'309': {'images': [{'filename': 'R8_sd3.5L_00001_.png', 'subfolder': '', 'type': 'output'}]}}
====================================
R8_sd3.5L_00001_.png
Version Details
Version ID
2fdf9488b53c1e0fd3aef7b477def1c00d1856a38466733711f9c769942598f5
Version Created
November 7, 2025
Run on Replicate →