Mask Background

$0.0025 per job

Image
0.10s
inference.mask-background.v1
Integrate Prodia's `inference.mask-background.v1` using https://docs.prodia.com/llms.txt

API request

Image inputs are sent as multipart form-data alongside the JSON job. See docs.prodia.com.

curl -X POST https://inference.prodia.com/v2/job \
  -H "Authorization: Bearer $PRODIA_TOKEN" \
  -H "Content-Type: application/json" \
  -H "Accept: image/jpeg" \
  -d '{
  "type": "inference.mask-background.v1",
  "config": {}
}'

Input

Image to use to generate mask.
Limits : Max 10 MB, 2048x2048. Min 256x256.

Enable contour detection for a crisp outline mask style.

Increase contour tolerance to smooth and expand the mask.

Output

Elapsed0.00s

Other endpoints

  • Birefnet inference.birefnet.segment.v1$0.0025 per job
  • Remove Background $0.0025 per job
  • Facerestore inference.facerestore.v1$0.0008 per job
  • Facerestore inference.facerestore.upscale.v1$0.0008 per job
  • Faceswap inference.faceswap.v1$0.0025 per job
  • Flux 2 Dev · Text to Imagefrom $0.0100 per image
  • Flux 2 Dev · Image Editingfrom $0.0100 per image
  • FLUX.2 [klein] 4B · Text to Imagefrom $0.0100 per image
  • Flux 2 Klein 4b · Image Editingfrom $0.0100 per image
  • FLUX.2 [klein] 9B · Text to Imagefrom $0.0100 per image
  • Flux 2 Klein 9b · Image Editingfrom $0.0100 per image
  • Flux 2 Klein · Text to Imageinference.flux-2.klein.txt2img.v1from $0.0100 per image
  • Flux 2 Klein · Image Editinginference.flux-2.klein.img2img.v1from $0.0100 per image
  • Flux Dev · Text to Imageinference.flux.dev.txt2img.v1from $0.0200 per image
  • Flux Dev · Image Editinginference.flux.dev.img2img.v1from $0.0200 per image
  • Flux Dev inference.flux.dev.inpainting.v1from $0.0200 per job
  • Flux Fast Schnell · Text to Imageinference.flux-fast.schnell.txt2img.v1from $0.0020 per image
  • FLUX.1 [dev] · Text to Imagefrom $0.0020 per image
  • FLUX.1 Kontext [dev] · Image Editing$0.0250 per image
  • FLUX.1 Fill [dev] from $0.0200 per job
  • HyPIR $0.0500 per job
  • Minimax H3 Base · Text to Videoinference.minimax.h3.base.txt2vid.v1$0.4000 per 5s clip (about $0.08/s)
  • Minimax H3 Fast · Text to Video$0.4000 per 5s clip (about $0.08/s)
  • Minimax H3 Base · Image to Videoinference.minimax.h3.base.img2vid.v1
  • Minimax H3 Fast · Image to Video
  • Minimax H3 Base · Reference to Videoinference.minimax.h3.base.ref2vid.v1
  • Minimax H3 Fast · Reference to Video
  • Kling · Text to Video
  • Partner Kling · Text to Videoinference.partner.kling.txt2vid.v1
  • Kling · Image to Video
  • Partner Kling · Image to Videoinference.partner.kling.img2vid.v1
  • Seedance Lite · Text to Videoinference.seedance.lite.txt2vid.v1
  • Partner Seedance Lite · Text to Videoinference.partner.seedance.lite.txt2vid.v1
  • Seedance Lite · Image to Videoinference.seedance.lite.img2vid.v1
  • Partner Seedance Lite · Image to Videoinference.partner.seedance.lite.img2vid.v1
  • Seedance Pro · Text to Video
  • Partner Seedance Pro · Text to Videoinference.partner.seedance.pro.txt2vid.v1
  • Seedance Pro · Image to Video
  • Partner Seedance Pro · Image to Videoinference.partner.seedance.pro.img2vid.v1
  • Seedance Proturbo · Text to Videoinference.seedance.proturbo.txt2vid.v1
  • Partner Seedance Proturbo · Text to Videoinference.partner.seedance.proturbo.txt2vid.v1
  • Seedance Proturbo · Image to Videoinference.seedance.proturbo.img2vid.v1
  • Partner Seedance Proturbo · Image to Videoinference.partner.seedance.proturbo.img2vid.v1
  • Seedance 2 · Text to Videoinference.seedance-2.txt2vid.v1
  • Partner Seedance 2 · Text to Videoinference.partner.seedance-2.txt2vid.v1
  • Seedance 2 · Image to Videoinference.seedance-2.img2vid.v1
  • Partner Seedance 2 · Image to Videoinference.partner.seedance-2.img2vid.v1
  • Seedance 2 Fast · Text to Videoinference.seedance-2.fast.txt2vid.v1
  • Partner Seedance 2 Fast · Text to Videoinference.partner.seedance-2.fast.txt2vid.v1
  • Seedance 2 Fast · Image to Videoinference.seedance-2.fast.img2vid.v1
  • Partner Seedance 2 Fast · Image to Videoinference.partner.seedance-2.fast.img2vid.v1
  • Seedream · Text to Imageinference.seedream.txt2img.v1
  • Partner Seedream · Text to Imageinference.partner.seedream.txt2img.v1
  • Seedream 4 · Text to Imageinference.seedream-4.txt2img.v1
  • Partner Seedream 4 · Text to Image
  • Seedream 4 · Image Editinginference.seedream-4.img2img.v1
  • Partner Seedream 4 · Image Editing
  • Seedream 4 5 · Text to Imageinference.seedream-4-5.txt2img.v1
  • Partner Seedream 4 5 · Text to Image
  • Seedream 4 5 · Image Editinginference.seedream-4-5.img2img.v1
  • Partner Seedream 4 5 · Image Editing
  • Seedream 5 0 Lite · Text to Imageinference.seedream-5-0.lite.txt2img.v1
  • Partner Seedream 5 0 Lite · Text to Image
  • Seedream 5 0 Lite · Image Editinginference.seedream-5-0.lite.img2img.v1
  • Partner Seedream 5 0 Lite · Image Editing
  • Recraft V3 · Text to Image
  • Partner Recraft · Text to Imageinference.partner.recraft.txt2img.v1
  • Recraft V3 · Image Editing
  • Partner Recraft · Image Editinginference.partner.recraft.img2img.v1
  • Recraft V3
  • Partner Recraft inference.partner.recraft.img2vec.v1
  • Recraft V4 · Text to Image
  • Partner Recraft V 4 · Text to Imageinference.partner.recraft.v4.txt2img.v1
  • Recraft V4 Pro · Text to Image
  • Partner Recraft V 4 Pro · Text to Imageinference.partner.recraft.v4.pro.txt2img.v1
  • Recraft V4 Vector
  • Partner Recraft V 4 inference.partner.recraft.v4.txt2vec.v1
  • Recraft V4 Pro Vector
  • Partner Recraft V 4 Pro inference.partner.recraft.v4.pro.txt2vec.v1
  • Topaz Gigapixel from $0.0100 per job
  • Partner Topaz Gigapixel Standard 2 inference.partner.topaz.gigapixel-standard-2.upscale.v1from $0.0100 per job
  • Topaz Proteus from $0.0500 per job
  • Partner Topaz Proteus inference.partner.topaz.proteus.upscale.v1from $0.0500 per job
  • Minimax H3 · Text to Video
  • Partner Minimax H3 · Text to Videoinference.partner.minimax.h3.txt2vid.v1
  • Minimax H3 · Image to Video
  • Partner Minimax H3 · Image to Videoinference.partner.minimax.h3.img2vid.v1
  • Minimax H3 · Reference to Video
  • Partner Minimax H3 · Reference to Videoinference.partner.minimax.h3.ref2vid.v1
  • Pruna P-Video · Text to Video
  • Partner Pruna P Video · Text to Videoinference.partner.pruna.p-video.txt2vid.v1
  • Pruna P-Video · Image to Video
  • Partner Pruna P Video · Image to Videoinference.partner.pruna.p-video.img2vid.v1
  • Pruna P-Video
  • Partner Pruna P Video inference.partner.pruna.p-video.aud2vid.v1
  • Pruna P-Image Ideogram · Text to Image
  • Partner Pruna P Image Ideogram · Text to Imageinference.partner.pruna.p-image-ideogram.txt2img.v1
  • Runway Gen-4 · Video to Video
  • Partner Runway Gen 4 · Video to Videoinference.partner.runway.gen4.vid2vid.v1
  • Sora 2 · Text to Video
  • Partner Sora 2 · Text to Videoinference.partner.sora-2.txt2vid.v1
  • Sora 2 Pro · Text to Video
  • Partner Sora 2 Pro · Text to Videoinference.partner.sora-2.pro.txt2vid.v1
  • Sora 2 · Image to Video
  • Partner Sora 2 · Image to Videoinference.partner.sora-2.img2vid.v1
  • Sora 2 Pro · Image to Video
  • Partner Sora 2 Pro · Image to Videoinference.partner.sora-2.pro.img2vid.v1
  • FLUX1.1 [pro] · Text to Image$0.0400 per image
  • Partner Flux Pro 1.1 · Text to Imageinference.partner.flux.pro11.txt2img.v1$0.0400 per image
  • Flux Pro 1.1ultra · Text to Imageinference.flux.pro11ultra.txt2img.v1$0.0600 per image
  • Partner Flux Pro 1.1ultra · Text to Imageinference.partner.flux.pro11ultra.txt2img.v1$0.0600 per image
  • Flux Pro 1.1ultra · Image Editinginference.flux.pro11ultra.img2img.v1$0.0600 per image
  • Partner Flux Pro 1.1ultra · Image Editinginference.partner.flux.pro11ultra.img2img.v1$0.0600 per image
  • FLUX.2 [pro] · Text to Image$0.0300 per image
  • Partner Flux 2 Pro · Text to Imageinference.partner.flux-2.pro.txt2img.v1$0.0300 per image
  • FLUX.2 [flex] · Text to Image$0.0600 per image
  • Partner Flux 2 Flex · Text to Imageinference.partner.flux-2.flex.txt2img.v1$0.0600 per image
  • Flux 2 Pro · Image Editing$0.0450 per image
  • Partner Flux 2 Pro · Image Editinginference.partner.flux-2.pro.img2img.v1$0.0450 per image
  • Flux 2 Flex · Image Editing$0.1200 per image
  • Partner Flux 2 Flex · Image Editinginference.partner.flux-2.flex.img2img.v1$0.1200 per image
  • FLUX.2 [max] · Text to Image$0.0400 per image
  • Partner Flux 2 Max · Text to Imageinference.partner.flux-2.max.txt2img.v1$0.0400 per image
  • Flux 2 Max · Image Editing$0.0600 per image
  • Partner Flux 2 Max · Image Editinginference.partner.flux-2.max.img2img.v1$0.0600 per image
  • Flux Kontext Pro · Text to Image$0.0400 per image
  • Partner Flux Kontext Pro · Text to Imageinference.partner.flux-kontext.pro.txt2img.v1$0.0400 per image
  • FLUX.1 Kontext [pro] · Image Editing$0.0400 per image
  • Partner Flux Kontext Pro · Image Editinginference.partner.flux-kontext.pro.img2img.v1$0.0400 per image
  • Flux Kontext Max · Text to Image$0.0800 per image
  • Partner Flux Kontext Max · Text to Imageinference.partner.flux-kontext.max.txt2img.v1$0.0800 per image
  • FLUX.1 Kontext [max] · Image Editing$0.0800 per image
  • Partner Flux Kontext Max · Image Editinginference.partner.flux-kontext.max.img2img.v1$0.0800 per image
  • Partner Nano Banana · Image Editinginference.partner.nano-banana.img2img.v1$0.0390 per image
  • Nano Banana Pro · Text to Imagefrom $0.1500 per image
  • Partner Gemini 3 Pro · Text to Imageinference.partner.gemini-3-pro.txt2img.v1from $0.1500 per image
  • Nano Banana Pro · Image Editingfrom $0.1500 per image
  • Partner Gemini 3 Pro · Image Editinginference.partner.gemini-3-pro.img2img.v1from $0.1500 per image
  • Nano Banana 2 · Text to Imagefrom $0.0672 per image
  • Partner Gemini 3 1 Flash · Text to Imageinference.partner.gemini-3-1-flash.txt2img.v1from $0.0672 per image
  • Nano Banana 2 · Image Editingfrom $0.0672 per image
  • Partner Gemini 3 1 Flash · Image Editinginference.partner.gemini-3-1-flash.img2img.v1from $0.0672 per image
  • Wan 2 6 · Text to Imageinference.wan2-6.txt2img.v1
  • Partner Wan 2 6 · Text to Imageinference.partner.wan2-6.txt2img.v1
  • Wan 2 6 · Image Editinginference.wan2-6.img2img.v1
  • Partner Wan 2 6 · Image Editinginference.partner.wan2-6.img2img.v1
  • Wan 2 6 · Text to Videoinference.wan2-6.txt2vid.v1
  • Partner Wan 2 6 · Text to Videoinference.partner.wan2-6.txt2vid.v1
  • Wan 2 6 · Image to Videoinference.wan2-6.img2vid.v1
  • Partner Wan 2 6 · Image to Videoinference.partner.wan2-6.img2vid.v1
  • Wan 2.7 · Text to Image
  • Partner Wan 2 7 · Text to Imageinference.partner.wan2-7.txt2img.v1
  • Wan 2.7 · Image Editing
  • Partner Wan 2 7 · Image Editinginference.partner.wan2-7.img2img.v1
  • Wan 2.7 · Text to Video
  • Partner Wan 2 7 · Text to Videoinference.partner.wan2-7.txt2vid.v1
  • Wan 2.7 · Image to Video
  • Partner Wan 2 7 · Image to Videoinference.partner.wan2-7.img2vid.v1
  • Wan 2.7 · Video to Video
  • Partner Wan 2 7 · Video to Videoinference.partner.wan2-7.vid2vid.v1
  • Tenstorrent Wan 2.2 Lightning · Image to Video
  • Partner Tenstorrent Wan 2.2 Lightning · Image to Videoinference.partner.tenstorrent.wan2-2-lightning.img2vid.v1
  • Wan 3 0 · Text to Videoinference.wan3-0.txt2vid.v1
  • Partner Wan 3 0 · Text to Videoinference.partner.wan3-0.txt2vid.v1
  • Wan 3 0 · Image to Videoinference.wan3-0.img2vid.v1
  • Partner Wan 3 0 · Image to Videoinference.partner.wan3-0.img2vid.v1
  • Happyhorse 1 1 · Image to Videoinference.happyhorse-1-1.img2vid.v1
  • Partner Happyhorse 1 1 · Image to Videoinference.partner.happyhorse-1-1.img2vid.v1
  • Seedance 2 5 · Text to Videoinference.seedance-2-5.txt2vid.v1
  • Partner Seedance 2 5 · Text to Videoinference.partner.seedance-2-5.txt2vid.v1
  • Seedance 2 5 · Image to Videoinference.seedance-2-5.img2vid.v1
  • Partner Seedance 2 5 · Image to Videoinference.partner.seedance-2-5.img2vid.v1
  • Gemini Omni Flash · Text to Videoinference.gemini-omni-flash.txt2vid.v1
  • Partner Gemini Omni Flash · Text to Videoinference.partner.gemini-omni-flash.txt2vid.v1
  • Grok Imagine · Text to Video
  • Partner Grok Imagine · Text to Videoinference.partner.grok-imagine.txt2vid.v1
  • Grok Imagine · Image to Video
  • Partner Grok Imagine · Image to Videoinference.partner.grok-imagine.img2vid.v1
  • LTX 2 Pro · Text to Video
  • Partner Ltx 2 Pro · Text to Videoinference.partner.ltx-2-pro.txt2vid.v1
  • LTX 2 Pro · Image to Video
  • Partner Ltx 2 Pro · Image to Videoinference.partner.ltx-2-pro.img2vid.v1
  • Vidu Q3 Pro · Text to Video
  • Partner Vidu Q 3 Pro · Text to Videoinference.partner.vidu-q3-pro.txt2vid.v1
  • Vidu Q3 Pro · Image to Video
  • Partner Vidu Q 3 Pro · Image to Videoinference.partner.vidu-q3-pro.img2vid.v1
  • Seedance 2.0 Mini · Text to Video
  • Seedance 2.0 Mini · Image to Video
  • Seedream 5.0 Flash · Text to Image
  • Seedream 5.0 Flash · Image Editing
  • Seedream 5.0 Pro · Text to Image
  • Seedream 5.0 Pro · Image Editing
  • Seedance 2.0 Mini · Reference to Video
  • Stable Diffusion XL · Text to Imagefrom $0.0020 per image
  • Stable Diffusion XL · Image Editingfrom $0.0020 per image
  • Stable Diffusion XL from $0.0020 per job
  • Segment $0.0100 per job
  • Sam 2 inference.sam2.segment.v1$0.0100 per job
  • Sam 3 inference.sam3.segment.v1from $0.0100 per job
  • Sam 3 Segment inference.sam3.segment.video.v1from $0.0500 per job
  • Upscale from $0.0010 per job
  • Vit inference.vit.img2label.v1
  • Wan 2 1 · Text to Imageinference.wan2-1.txt2img.v1
  • Wan 2 1 Lightning · Text to Imageinference.wan2-1.lightning.txt2img.v1
  • Wan 2 1 · Image Editinginference.wan2-1.img2img.v1
  • Wan 2 1 Lightning · Image Editinginference.wan2-1.lightning.img2img.v1
  • Generate Hero inference.generate-hero.v1

Related models