Hugging Face Image AI
Pricing
from $0.01 / 1,000 results
Hugging Face Image AI
Image processing w/Hugging Face models Text-to-Image: Stable Diffusion, SDXL, DALL-E generation Image-to-Image: Transform images Inpainting: Edit parts of images Classification: Identify objects Object Detection: Locate label objects Segmentation: Pixel analysis Captioning: Generate descriptions
Pricing
from $0.01 / 1,000 results
Rating
0.0
(0)
Developer
The Howlers
Actor stats
0
Bookmarked
16
Total users
4
Monthly active users
6 days ago
Last modified
Categories
Share
Hugging Face Image
Image processing with Hugging Face - Stable Diffusion generation, classification, object detection, captioning, and segmentation. Built by John Rippy (https://www.linkedin.com/in/johnrippy/).
BYOK (Bring Your Own Key) -- you provide your own API credentials.
Before You Start
This actor requires your own API credentials to fetch real data.
Where to get your key: Your Hugging Face API token
You can test with Demo Mode first (free, no key needed) to see the output format before committing.
Quick Start
Test with Demo Mode (free, no API key needed)
{"demoMode": true,"imageUrl": "https://example.com","maskUrl": "https://example.com"}
Run with real data
{"demoMode": false,"task": "text_to_image","apiToken": "YOUR_API_KEY_HERE","imageUrl": "https://example.com","maskUrl": "https://example.com","width": 1024,"height": 1024,"guidanceScale": 7.5,"numInferenceSteps": 50,"strength": 0.8,"scheduler": "default","waitForModel": true}
Input Parameters
| Parameter | Type | Default | Required | Description |
|---|---|---|---|---|
task | string | "text_to_image" | Yes* | The image operation to perform |
apiToken | string | - | Yes* | Your Hugging Face API token |
model | string | - | No | Hugging Face model ID (leave blank for default) |
prompt | string | - | No | Text prompt for image generation |
negativePrompt | string | - | No | What to avoid in generated images |
imageUrl | string | - | No | URL of input image for image-based tasks |
maskUrl | string | - | No | URL of mask image for inpainting |
candidateLabels | string | - | No | Comma-separated labels for zero-shot classification |
width | integer | 1024 | No | Output image width |
height | integer | 1024 | No | Output image height |
guidanceScale | number | 7.5 | No | How closely to follow the prompt (1-20) |
numInferenceSteps | integer | 50 | No | Number of diffusion steps (more = better quality, slower) |
strength | number | 0.8 | No | How much to transform the input image (0-1) |
seed | integer | - | No | Random seed for reproducible results |
scheduler | string | "default" | No | Diffusion scheduler |
waitForModel | boolean | true | No | Wait for model to load if not ready |
webhookUrl | string | - | No | URL to receive results via webhook |
demoMode | boolean | true | No | Run with sample data (no API calls) |
*Required when Demo Mode is off.
Pricing
This actor uses pay-per-event billing:
| Event | Description | Price |
|---|---|---|
| Image Processed | Each image processing request completed | $0.02 |
Demo mode is free -- no charges for sample data.
Troubleshooting
"API key is required"
You have Demo Mode turned off but didn't provide an API key. Either:
- Turn Demo Mode on to test with sample data
- Add your API key in the input
"API error 403" or "Unauthorized"
Your API key is invalid, expired, or doesn't have access to this specific API endpoint. Double-check your key and account permissions.
"API error 429" or "Rate limit"
Too many requests. Wait a minute and try again, or reduce the number of items per run.
No results or empty dataset
Check the run log for error messages. Common causes:
- Invalid input format (check the examples above)
- API key without proper permissions
- The target data doesn't exist or is too small to track
How do I test without an API key?
Enable Demo Mode in the input. This returns realistic sample data so you can verify the output format works for your workflow.
Built by John Rippy | Actor Arsenal

