BACKGROUND REMOVAL API
Use vision-language and image generation models to remove backgrounds from product photos, portraits, and marketing materials. Describe what you need in natural language, or use image-to-image generation to isolate subjects. Clean cutouts without Photoshop or specialized segmentation libraries.
QUICK START
from openai import OpenAI
client = OpenAI(
base_url="https://api.runcrate.ai/v1",
api_key="rc_live_YOUR_API_KEY",
)
# Use a vision model to identify and describe the subject
response = client.chat.completions.create(
model="Qwen/Qwen3-VL-235B-A22B-Instruct",
messages=[
{
"role": "user",
"content": [
{"type": "image_url", "image_url": {"url": "https://example.com/product.jpg"}},
{"type": "text", "text": "Describe the main subject for background removal. Return a detailed prompt for regenerating just the subject on a white background."},
],
}
],
)
# Use the description to generate a clean version
image = client.images.generate(
model="black-forest-labs/FLUX.1-dev",
prompt=response.choices[0].message.content,
size="1024x1024",
)
print(image.data[0].url)AVAILABLE MODELS
| Model | Provider | Price | Detail |
|---|---|---|---|
| Qwen/Qwen3-VL-235B-A22B-Instruct | Alibaba | Per-token | Vision analysis for subject isolation |
| black-forest-labs/FLUX.1-dev | Black Forest Labs | Per-image | High-quality image regeneration |
| ideogram-ai/ideogram-v2 | Ideogram | Per-image | Clean product image generation |
WHY RUNCRATE
Vision-language models understand scene semantics, not just edges. They can isolate complex subjects like hair, transparent objects, and reflections.
Generate clean product photos on white backgrounds for marketplaces. Process entire catalogs through the API for consistent presentation.
Skip Photoshop, remove.bg, and specialized segmentation models. Use the same API you already use for chat and image generation.
Describe exactly what you want: subject on white, subject on transparent, subject on a new background. Natural language control over the output.
FAQ