Stable Diffusion 3.5 Medium
Generate images from text prompts using Stable Diffusion 3.5 Medium. Supports text-to-image and image-to-image modes with configurable aspect ratio, guidance, and quality settings.
Quick Start
Requires an each::labs API key. Get one at eachlabs.ai.
curl -X POST https://api.eachlabs.ai/v1/prediction \
-H "Content-Type: application/json" \
-H "X-API-Key: $EACHLABS_API_KEY" \
-d '{
"model": "stable-diffusion-3-5-medium",
"version": "0.0.1",
"input": {
"prompt": "a majestic eagle soaring over snow-capped mountains, photorealistic, golden hour lighting",
"aspect_ratio": "16:9",
"cfg": 5,
"steps": 40,
"output_format": "webp"
}
}'
Parameters
| Parameter |
Type |
Default |
Description |
| aspect_ratio |
string |
1:1 |
Output aspect ratio. enum: 1:1, 16:9, 21:9, 3:2, 2:3, 4:5, 5:4, 3:4, 4:3, 9:16, 9:21 |
| cfg |
number |
5 |
Guidance scale - how similar the output should be to the prompt |
| image |
string |
- |
Input image for image-to-image mode |
| output_format |
string |
webp |
Output format. enum: webp, jpg, png |
| output_quality |
integer |
90 |
Quality of output images, from 0 to 100 |
| prompt |
string |
- |
Text prompt for image generation |
| prompt_strength |
number |
0.85 |
Prompt strength when using image-to-image. 1.0 is full destruction of input |
| seed |
integer |
- |
Set a seed for reproducibility. Random by default |
| steps |
integer |
40 |
Number of steps to run the sampler for |
Examples
Detailed character art:
curl -X POST https://api.eachlabs.ai/v1/prediction \
-H "Content-Type: application/json" \
-H "X-API-Key: $EACHLABS_API_KEY" \
-d '{
"model": "stable-diffusion-3-5-medium",
"version": "0.0.1",
"input": {
"prompt": "a steampunk inventor in their workshop, intricate gears and brass instruments, warm candlelight, detailed illustration",
"aspect_ratio": "4:5",
"cfg": 6,
"steps": 45,
"output_format": "png",
"output_quality": 100
}
}'
Image-to-image transformation:
curl -X POST https://api.eachlabs.ai/v1/prediction \
-H "Content-Type: application/json" \
-H "X-API-Key: $EACHLABS_API_KEY" \
-d '{
"model": "stable-diffusion-3-5-medium",
"version": "0.0.1",
"input": {
"prompt": "a watercolor painting of a peaceful countryside village",
"image": "https://example.com/village-photo.jpg",
"prompt_strength": 0.7,
"cfg": 5,
"steps": 35,
"seed": 42
}
}'
Related Models
Documentation
1---2name: stable-diffusion-3-5-medium3description: Stable Diffusion 3.5 Medium | AI Image Generation. Generate images from text with optional img2img mode. Triggers: stable diffusion 3.5, sd 3.5 medium, text to image, image generation, sd34---56# Stable Diffusion 3.5 Medium78Generate images from text prompts using Stable Diffusion 3.5 Medium. Supports text-to-image and image-to-image modes with configurable aspect ratio, guidance, and quality settings.910## Quick Start1112> Requires an each::labs API key. Get one at [eachlabs.ai](https://eachlabs.ai).1314```bash15curl -X POST https://api.eachlabs.ai/v1/prediction \16 -H "Content-Type: application/json" \17 -H "X-API-Key: $EACHLABS_API_KEY" \18 -d '{19 "model": "stable-diffusion-3-5-medium",20 "version": "0.0.1",21 "input": {22 "prompt": "a majestic eagle soaring over snow-capped mountains, photorealistic, golden hour lighting",23 "aspect_ratio": "16:9",24 "cfg": 5,25 "steps": 40,26 "output_format": "webp"27 }28 }'29```3031## Parameters3233| Parameter | Type | Default | Description |34|-----------|------|---------|-------------|35| aspect_ratio | string | 1:1 | Output aspect ratio. enum: 1:1, 16:9, 21:9, 3:2, 2:3, 4:5, 5:4, 3:4, 4:3, 9:16, 9:21 |36| cfg | number | 5 | Guidance scale - how similar the output should be to the prompt |37| image | string | - | Input image for image-to-image mode |38| output_format | string | webp | Output format. enum: webp, jpg, png |39| output_quality | integer | 90 | Quality of output images, from 0 to 100 |40| prompt | string | - | Text prompt for image generation |41| prompt_strength | number | 0.85 | Prompt strength when using image-to-image. 1.0 is full destruction of input |42| seed | integer | - | Set a seed for reproducibility. Random by default |43| steps | integer | 40 | Number of steps to run the sampler for |4445## Examples4647**Detailed character art:**48```bash49curl -X POST https://api.eachlabs.ai/v1/prediction \50 -H "Content-Type: application/json" \51 -H "X-API-Key: $EACHLABS_API_KEY" \52 -d '{53 "model": "stable-diffusion-3-5-medium",54 "version": "0.0.1",55 "input": {56 "prompt": "a steampunk inventor in their workshop, intricate gears and brass instruments, warm candlelight, detailed illustration",57 "aspect_ratio": "4:5",58 "cfg": 6,59 "steps": 45,60 "output_format": "png",61 "output_quality": 10062 }63 }'64```6566**Image-to-image transformation:**67```bash68curl -X POST https://api.eachlabs.ai/v1/prediction \69 -H "Content-Type: application/json" \70 -H "X-API-Key: $EACHLABS_API_KEY" \71 -d '{72 "model": "stable-diffusion-3-5-medium",73 "version": "0.0.1",74 "input": {75 "prompt": "a watercolor painting of a peaceful countryside village",76 "image": "https://example.com/village-photo.jpg",77 "prompt_strength": 0.7,78 "cfg": 5,79 "steps": 35,80 "seed": 4281 }82 }'83```8485## Related Models8687- [stable-diffusion-3-5-large](../stable-diffusion-3-5-large/) - Larger SD 3.5 model for higher quality88- [flux-dev](../flux-dev/) - Flux Dev image generation89- [sana](../sana/) - Nvidia Sana image generation9091## Documentation9293- [each::labs Docs](https://docs.eachlabs.ai)94- [API Reference](https://docs.eachlabs.ai/api/overview)
awesome-genmedia