Official

stability-ai / stable-diffusion-3.5-medium

2.5 billion parameter image model with improved MMDiT-X architecture

Cold

Public
37K runs
$0.035 per image
Commercial use
Weights
Paper
License

Run with an API

Playground API Examples README

Prediction

stability-ai/stable-diffusion-3.5-medium

Official model

stability-ai/stable-diffusion-3.5-medium

zy5ck93mcxrm20cjv1xbcg41x4

Status

Succeeded

Source

Web

Total duration

4.5s

Created

6 months ago

Input

cfg: 5
steps: 40
prompt: A photo of beautiful flowery meadow, at sunset
aspect_ratio: 1:1
output_format: webp
output_quality: 90
prompt_strength: 0.85

{
  "cfg": 5,
  "steps": 40,
  "prompt": "A photo of beautiful flowery meadow, at sunset",
  "aspect_ratio": "1:1",
  "output_format": "webp",
  "output_quality": 90,
  "prompt_strength": 0.85
}

Install Replicate’s Node.js client library:

npm install replicate

Import and set up the client:

import Replicate from "replicate";

const replicate = new Replicate({
  auth: process.env.REPLICATE_API_TOKEN,
});

Run stability-ai/stable-diffusion-3.5-medium using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const input = {
  cfg: 5,
  steps: 40,
  prompt: "A photo of beautiful flowery meadow, at sunset",
  aspect_ratio: "1:1",
  output_format: "webp",
  output_quality: 90,
  prompt_strength: 0.85
};

const output = await replicate.run("stability-ai/stable-diffusion-3.5-medium", { input });

// To access the file URL:
console.log(output[0].url()); //=> "http://example.com"

// To write the file to disk:
fs.writeFile("my-image.png", output[0]);

To learn more, take a look at the guide on getting started with Node.js.

Install Replicate’s Python client library:

pip install replicate

Import the client:

import replicate

Run stability-ai/stable-diffusion-3.5-medium using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "stability-ai/stable-diffusion-3.5-medium",
    input={
        "cfg": 5,
        "steps": 40,
        "prompt": "A photo of beautiful flowery meadow, at sunset",
        "aspect_ratio": "1:1",
        "output_format": "webp",
        "output_quality": 90,
        "prompt_strength": 0.85
    }
)
print(output)

To learn more, take a look at the guide on getting started with Python.

Run stability-ai/stable-diffusion-3.5-medium using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

curl -s -X POST \
  -H "Authorization: Bearer $REPLICATE_API_TOKEN" \
  -H "Content-Type: application/json" \
  -H "Prefer: wait" \
  -d $'{
    "input": {
      "cfg": 5,
      "steps": 40,
      "prompt": "A photo of beautiful flowery meadow, at sunset",
      "aspect_ratio": "1:1",
      "output_format": "webp",
      "output_quality": 90,
      "prompt_strength": 0.85
    }
  }' \
  https://api.replicate.com/v1/models/stability-ai/stable-diffusion-3.5-medium/predictions

To learn more, take a look at Replicate’s HTTP API reference docs.

Output

{
  "completed_at": "2024-10-29T13:32:41.279204Z",
  "created_at": "2024-10-29T13:32:36.839000Z",
  "data_removed": false,
  "error": null,
  "id": "zy5ck93mcxrm20cjv1xbcg41x4",
  "input": {
    "cfg": 5,
    "steps": 40,
    "prompt": "A photo of beautiful flowery meadow, at sunset",
    "aspect_ratio": "1:1",
    "output_format": "webp",
    "output_quality": 90,
    "prompt_strength": 0.85
  },
  "logs": "Seed set to: 4100208928\nRunning workflow\ngot prompt\nExecuting node 6, title: CLIP Text Encode (Prompt), class type: CLIPTextEncode\nExecuting node 67, title: ConditioningZeroOut, class type: ConditioningZeroOut\nExecuting node 68, title: ConditioningSetTimestepRange, class type: ConditioningSetTimestepRange\nExecuting node 69, title: Conditioning (Combine), class type: ConditioningCombine\nExecuting node 294, title: KSampler, class type: KSampler\n0%|          | 0/40 [00:00<?, ?it/s]\n5%|▌         | 2/40 [00:00<00:03, 10.79it/s]\n10%|█         | 4/40 [00:00<00:03, 10.78it/s]\n15%|█▌        | 6/40 [00:00<00:03, 10.78it/s]\n20%|██        | 8/40 [00:00<00:02, 10.79it/s]\n25%|██▌       | 10/40 [00:00<00:02, 10.79it/s]\n30%|███       | 12/40 [00:01<00:02, 10.79it/s]\n35%|███▌      | 14/40 [00:01<00:02, 10.79it/s]\n40%|████      | 16/40 [00:01<00:02, 10.77it/s]\n45%|████▌     | 18/40 [00:01<00:02, 10.78it/s]\n50%|█████     | 20/40 [00:01<00:01, 10.79it/s]\n55%|█████▌    | 22/40 [00:02<00:01, 10.79it/s]\n60%|██████    | 24/40 [00:02<00:01, 10.76it/s]\n65%|██████▌   | 26/40 [00:02<00:01, 10.76it/s]\n70%|███████   | 28/40 [00:02<00:01, 10.76it/s]\n75%|███████▌  | 30/40 [00:02<00:00, 10.76it/s]\n80%|████████  | 32/40 [00:02<00:00, 10.77it/s]\n85%|████████▌ | 34/40 [00:03<00:00, 10.78it/s]\n90%|█████████ | 36/40 [00:03<00:00, 10.77it/s]\n95%|█████████▌| 38/40 [00:03<00:00, 10.78it/s]\n100%|██████████| 40/40 [00:03<00:00, 10.79it/s]\n100%|██████████| 40/40 [00:03<00:00, 10.78it/s]\nExecuting node 8, title: VAE Decode, class type: VAEDecode\nExecuting node 309, title: Save Image, class type: SaveImage\nPrompt executed in 4.09 seconds\noutputs:  {'309': {'images': [{'filename': 'R8_sd3.5L_00001_.png', 'subfolder': '', 'type': 'output'}]}}\n====================================\nR8_sd3.5L_00001_.png",
  "metrics": {
    "image_count": 1,
    "predict_time": 4.435928549,
    "total_time": 4.440204
  },
  "output": [
    "https://replicate.delivery/yhqm/K6hD2bwf4SyQWaDJ1vP8854v2xG4ihlQBLu2zfQZTj95XprTA/R8_sd3.5L_00001_.webp"
  ],
  "started_at": "2024-10-29T13:32:36.843276Z",
  "status": "succeeded",
  "urls": {
    "stream": "https://stream.replicate.com/v1/files/wcdb-esjfhl6nkbxvvjexfdm7h36zcyazskn5w2mambxzbqynt5xvvo6q",
    "get": "https://api.replicate.com/v1/predictions/zy5ck93mcxrm20cjv1xbcg41x4",
    "cancel": "https://api.replicate.com/v1/predictions/zy5ck93mcxrm20cjv1xbcg41x4/cancel"
  },
  "version": "hidden"
}

Generated in

4.4 seconds

Tweak it Share

Seed set to: 4100208928
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]
5%|▌         | 2/40 [00:00<00:03, 10.79it/s]
10%|█         | 4/40 [00:00<00:03, 10.78it/s]
15%|█▌        | 6/40 [00:00<00:03, 10.78it/s]
20%|██        | 8/40 [00:00<00:02, 10.79it/s]
25%|██▌       | 10/40 [00:00<00:02, 10.79it/s]
30%|███       | 12/40 [00:01<00:02, 10.79it/s]
35%|███▌      | 14/40 [00:01<00:02, 10.79it/s]
40%|████      | 16/40 [00:01<00:02, 10.77it/s]
45%|████▌     | 18/40 [00:01<00:02, 10.78it/s]
50%|█████     | 20/40 [00:01<00:01, 10.79it/s]
55%|█████▌    | 22/40 [00:02<00:01, 10.79it/s]
60%|██████    | 24/40 [00:02<00:01, 10.76it/s]
65%|██████▌   | 26/40 [00:02<00:01, 10.76it/s]
70%|███████   | 28/40 [00:02<00:01, 10.76it/s]
75%|███████▌  | 30/40 [00:02<00:00, 10.76it/s]
80%|████████  | 32/40 [00:02<00:00, 10.77it/s]
85%|████████▌ | 34/40 [00:03<00:00, 10.78it/s]
90%|█████████ | 36/40 [00:03<00:00, 10.77it/s]
95%|█████████▌| 38/40 [00:03<00:00, 10.78it/s]
100%|██████████| 40/40 [00:03<00:00, 10.79it/s]
100%|██████████| 40/40 [00:03<00:00, 10.78it/s]
Executing node 8, title: VAE Decode, class type: VAEDecode
Executing node 309, title: Save Image, class type: SaveImage
Prompt executed in 4.09 seconds
outputs:  {'309': {'images': [{'filename': 'R8_sd3.5L_00001_.png', 'subfolder': '', 'type': 'output'}]}}
====================================
R8_sd3.5L_00001_.png

Prediction

stability-ai/stable-diffusion-3.5-medium

Official model

stability-ai/stable-diffusion-3.5-medium

0wx084def9rm20cjv1yb27bb6g

Status

Succeeded

Source

Web

Total duration

4.4s

Created

6 months ago

Input

cfg: 5
steps: 40
prompt: a captivating anime-style illustration of a woman in a white astronaut suit. She has long, dark wavy hair. Surrounding the astronaut are vibrant orange flowers with yellow centers. The background itself is a mesmerizing night sky filled with countless stars
aspect_ratio: 1:1
output_format: webp
output_quality: 90
prompt_strength: 0.85

{
  "cfg": 5,
  "steps": 40,
  "prompt": "a captivating anime-style illustration of a woman in a white astronaut suit. She has long, dark wavy hair. Surrounding the astronaut are vibrant orange flowers with yellow centers. The background itself is a mesmerizing night sky filled with countless stars",
  "aspect_ratio": "1:1",
  "output_format": "webp",
  "output_quality": 90,
  "prompt_strength": 0.85
}

Install Replicate’s Node.js client library:

npm install replicate

Import and set up the client:

import Replicate from "replicate";

const replicate = new Replicate({
  auth: process.env.REPLICATE_API_TOKEN,
});

Run stability-ai/stable-diffusion-3.5-medium using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const input = {
  cfg: 5,
  steps: 40,
  prompt: "a captivating anime-style illustration of a woman in a white astronaut suit. She has long, dark wavy hair. Surrounding the astronaut are vibrant orange flowers with yellow centers. The background itself is a mesmerizing night sky filled with countless stars",
  aspect_ratio: "1:1",
  output_format: "webp",
  output_quality: 90,
  prompt_strength: 0.85
};

const output = await replicate.run("stability-ai/stable-diffusion-3.5-medium", { input });

// To access the file URL:
console.log(output[0].url()); //=> "http://example.com"

// To write the file to disk:
fs.writeFile("my-image.png", output[0]);

To learn more, take a look at the guide on getting started with Node.js.

Install Replicate’s Python client library:

pip install replicate

Import the client:

import replicate

Run stability-ai/stable-diffusion-3.5-medium using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "stability-ai/stable-diffusion-3.5-medium",
    input={
        "cfg": 5,
        "steps": 40,
        "prompt": "a captivating anime-style illustration of a woman in a white astronaut suit. She has long, dark wavy hair. Surrounding the astronaut are vibrant orange flowers with yellow centers. The background itself is a mesmerizing night sky filled with countless stars",
        "aspect_ratio": "1:1",
        "output_format": "webp",
        "output_quality": 90,
        "prompt_strength": 0.85
    }
)
print(output)

To learn more, take a look at the guide on getting started with Python.

Run stability-ai/stable-diffusion-3.5-medium using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

curl -s -X POST \
  -H "Authorization: Bearer $REPLICATE_API_TOKEN" \
  -H "Content-Type: application/json" \
  -H "Prefer: wait" \
  -d $'{
    "input": {
      "cfg": 5,
      "steps": 40,
      "prompt": "a captivating anime-style illustration of a woman in a white astronaut suit. She has long, dark wavy hair. Surrounding the astronaut are vibrant orange flowers with yellow centers. The background itself is a mesmerizing night sky filled with countless stars",
      "aspect_ratio": "1:1",
      "output_format": "webp",
      "output_quality": 90,
      "prompt_strength": 0.85
    }
  }' \
  https://api.replicate.com/v1/models/stability-ai/stable-diffusion-3.5-medium/predictions

To learn more, take a look at Replicate’s HTTP API reference docs.

Output

{
  "completed_at": "2024-10-29T13:35:07.173715Z",
  "created_at": "2024-10-29T13:35:02.778000Z",
  "data_removed": false,
  "error": null,
  "id": "0wx084def9rm20cjv1yb27bb6g",
  "input": {
    "cfg": 5,
    "steps": 40,
    "prompt": "a captivating anime-style illustration of a woman in a white astronaut suit. She has long, dark wavy hair. Surrounding the astronaut are vibrant orange flowers with yellow centers. The background itself is a mesmerizing night sky filled with countless stars",
    "aspect_ratio": "1:1",
    "output_format": "webp",
    "output_quality": 90,
    "prompt_strength": 0.85
  },
  "logs": "Seed set to: 3551813581\nRunning workflow\ngot prompt\nExecuting node 294, title: KSampler, class type: KSampler\n0%|          | 0/40 [00:00<?, ?it/s]\n5%|▌         | 2/40 [00:00<00:03, 10.76it/s]\n10%|█         | 4/40 [00:00<00:03, 10.78it/s]\n15%|█▌        | 6/40 [00:00<00:03, 10.76it/s]\n20%|██        | 8/40 [00:00<00:02, 10.77it/s]\n25%|██▌       | 10/40 [00:00<00:02, 10.78it/s]\n30%|███       | 12/40 [00:01<00:02, 10.78it/s]\n35%|███▌      | 14/40 [00:01<00:02, 10.78it/s]\n40%|████      | 16/40 [00:01<00:02, 10.78it/s]\n45%|████▌     | 18/40 [00:01<00:02, 10.78it/s]\n50%|█████     | 20/40 [00:01<00:01, 10.79it/s]\n55%|█████▌    | 22/40 [00:02<00:01, 10.77it/s]\n60%|██████    | 24/40 [00:02<00:01, 10.76it/s]\n65%|██████▌   | 26/40 [00:02<00:01, 10.77it/s]\n70%|███████   | 28/40 [00:02<00:01, 10.76it/s]\n75%|███████▌  | 30/40 [00:02<00:00, 10.77it/s]\n80%|████████  | 32/40 [00:02<00:00, 10.76it/s]\n85%|████████▌ | 34/40 [00:03<00:00, 10.76it/s]\n90%|█████████ | 36/40 [00:03<00:00, 10.77it/s]\n95%|█████████▌| 38/40 [00:03<00:00, 10.78it/s]\n100%|██████████| 40/40 [00:03<00:00, 10.79it/s]\n100%|██████████| 40/40 [00:03<00:00, 10.77it/s]\nExecuting node 8, title: VAE Decode, class type: VAEDecode\nExecuting node 309, title: Save Image, class type: SaveImage\nPrompt executed in 4.03 seconds\noutputs:  {'309': {'images': [{'filename': 'R8_sd3.5L_00001_.png', 'subfolder': '', 'type': 'output'}]}}\n====================================\nR8_sd3.5L_00001_.png",
  "metrics": {
    "image_count": 1,
    "predict_time": 4.389376381,
    "total_time": 4.395715
  },
  "output": [
    "https://replicate.delivery/yhqm/b8ZWW3KneUSuca1q7wzUrSpRsElbIdLtFqXEMaZetgrLaprTA/R8_sd3.5L_00001_.webp"
  ],
  "started_at": "2024-10-29T13:35:02.784339Z",
  "status": "succeeded",
  "urls": {
    "stream": "https://stream.replicate.com/v1/files/wcdb-meh23tz2vbo4lup5tdivjpnvcfwtwvyoupyqu4bhcwmgan7kzytq",
    "get": "https://api.replicate.com/v1/predictions/0wx084def9rm20cjv1yb27bb6g",
    "cancel": "https://api.replicate.com/v1/predictions/0wx084def9rm20cjv1yb27bb6g/cancel"
  },
  "version": "hidden"
}

Generated in

4.4 seconds

Tweak it Share

Prediction

stability-ai/stable-diffusion-3.5-medium

Official model

stability-ai/stable-diffusion-3.5-medium

dz66ferp39rm20cjv1zskn3tmw

Status

Succeeded

Source

Web

Total duration

4.2s

Created

6 months ago

Input

cfg: 5
steps: 40
prompt: a portrait of a man standing in front of a white wall. He is looking up towards something beyond the frame, fine art photography with dappled light
aspect_ratio: 1:1
output_format: webp
output_quality: 90
prompt_strength: 0.85

{
  "cfg": 5,
  "steps": 40,
  "prompt": "a portrait of a man standing in front of a white wall. He is looking up towards something beyond the frame, fine art photography with dappled light",
  "aspect_ratio": "1:1",
  "output_format": "webp",
  "output_quality": 90,
  "prompt_strength": 0.85
}

Install Replicate’s Node.js client library:

npm install replicate

Import and set up the client:

import Replicate from "replicate";

const replicate = new Replicate({
  auth: process.env.REPLICATE_API_TOKEN,
});

Run stability-ai/stable-diffusion-3.5-medium using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const input = {
  cfg: 5,
  steps: 40,
  prompt: "a portrait of a man standing in front of a white wall. He is looking up towards something beyond the frame, fine art photography with dappled light",
  aspect_ratio: "1:1",
  output_format: "webp",
  output_quality: 90,
  prompt_strength: 0.85
};

const output = await replicate.run("stability-ai/stable-diffusion-3.5-medium", { input });

// To access the file URL:
console.log(output[0].url()); //=> "http://example.com"

// To write the file to disk:
fs.writeFile("my-image.png", output[0]);

To learn more, take a look at the guide on getting started with Node.js.

Install Replicate’s Python client library:

pip install replicate

Import the client:

import replicate

Run stability-ai/stable-diffusion-3.5-medium using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "stability-ai/stable-diffusion-3.5-medium",
    input={
        "cfg": 5,
        "steps": 40,
        "prompt": "a portrait of a man standing in front of a white wall. He is looking up towards something beyond the frame, fine art photography with dappled light",
        "aspect_ratio": "1:1",
        "output_format": "webp",
        "output_quality": 90,
        "prompt_strength": 0.85
    }
)
print(output)

To learn more, take a look at the guide on getting started with Python.

Run stability-ai/stable-diffusion-3.5-medium using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

curl -s -X POST \
  -H "Authorization: Bearer $REPLICATE_API_TOKEN" \
  -H "Content-Type: application/json" \
  -H "Prefer: wait" \
  -d $'{
    "input": {
      "cfg": 5,
      "steps": 40,
      "prompt": "a portrait of a man standing in front of a white wall. He is looking up towards something beyond the frame, fine art photography with dappled light",
      "aspect_ratio": "1:1",
      "output_format": "webp",
      "output_quality": 90,
      "prompt_strength": 0.85
    }
  }' \
  https://api.replicate.com/v1/models/stability-ai/stable-diffusion-3.5-medium/predictions

To learn more, take a look at Replicate’s HTTP API reference docs.

Output

{
  "completed_at": "2024-10-29T13:37:44.529970Z",
  "created_at": "2024-10-29T13:37:40.378000Z",
  "data_removed": false,
  "error": null,
  "id": "dz66ferp39rm20cjv1zskn3tmw",
  "input": {
    "cfg": 5,
    "steps": 40,
    "prompt": "a portrait of a man standing in front of a white wall. He is looking up towards something beyond the frame, fine art photography with dappled light",
    "aspect_ratio": "1:1",
    "output_format": "webp",
    "output_quality": 90,
    "prompt_strength": 0.85
  },
  "logs": "Seed set to: 3405743627\nRunning workflow\ngot prompt\nExecuting node 294, title: KSampler, class type: KSampler\n0%|          | 0/40 [00:00<?, ?it/s]\n5%|▌         | 2/40 [00:00<00:03, 10.66it/s]\n10%|█         | 4/40 [00:00<00:03, 10.71it/s]\n15%|█▌        | 6/40 [00:00<00:03, 10.70it/s]\n20%|██        | 8/40 [00:00<00:02, 10.70it/s]\n25%|██▌       | 10/40 [00:00<00:02, 10.70it/s]\n30%|███       | 12/40 [00:01<00:02, 10.68it/s]\n35%|███▌      | 14/40 [00:01<00:02, 10.69it/s]\n40%|████      | 16/40 [00:01<00:02, 10.71it/s]\n45%|████▌     | 18/40 [00:01<00:02, 10.72it/s]\n50%|█████     | 20/40 [00:01<00:01, 10.72it/s]\n55%|█████▌    | 22/40 [00:02<00:01, 10.72it/s]\n60%|██████    | 24/40 [00:02<00:01, 10.73it/s]\n65%|██████▌   | 26/40 [00:02<00:01, 10.73it/s]\n70%|███████   | 28/40 [00:02<00:01, 10.73it/s]\n75%|███████▌  | 30/40 [00:02<00:00, 10.74it/s]\n80%|████████  | 32/40 [00:02<00:00, 10.73it/s]\n85%|████████▌ | 34/40 [00:03<00:00, 10.73it/s]\n90%|█████████ | 36/40 [00:03<00:00, 10.74it/s]\n95%|█████████▌| 38/40 [00:03<00:00, 10.75it/s]\n100%|██████████| 40/40 [00:03<00:00, 10.76it/s]\n100%|██████████| 40/40 [00:03<00:00, 10.73it/s]\nExecuting node 8, title: VAE Decode, class type: VAEDecode\nExecuting node 309, title: Save Image, class type: SaveImage\nPrompt executed in 4.00 seconds\noutputs:  {'309': {'images': [{'filename': 'R8_sd3.5L_00001_.png', 'subfolder': '', 'type': 'output'}]}}\n====================================\nR8_sd3.5L_00001_.png",
  "metrics": {
    "image_count": 1,
    "predict_time": 4.146679204,
    "total_time": 4.15197
  },
  "output": [
    "https://replicate.delivery/yhqm/fa78p5ERflveDIl2hXnB8TRgjbozUcX2BeEWDL7lUSGiyluOB/R8_sd3.5L_00001_.webp"
  ],
  "started_at": "2024-10-29T13:37:40.383290Z",
  "status": "succeeded",
  "urls": {
    "stream": "https://stream.replicate.com/v1/files/wcdb-awlahmf27q6wdumdozolydio6zhoukcj3iw7vpmt3gptonkvkmlq",
    "get": "https://api.replicate.com/v1/predictions/dz66ferp39rm20cjv1zskn3tmw",
    "cancel": "https://api.replicate.com/v1/predictions/dz66ferp39rm20cjv1zskn3tmw/cancel"
  },
  "version": "hidden"
}

Generated in

4.2 seconds

Tweak it Share

Want to make some of these yourself?

Run this model

stability-ai / stable-diffusion-3.5-medium

Prediction

Input

Output

Prediction

Input

Output

Prediction

Input

Output

Logs (zy5ck93mcxrm20cjv1xbcg41x4)

Logs (0wx084def9rm20cjv1yb27bb6g)

Logs (dz66ferp39rm20cjv1zskn3tmw)