Photoroom

Most-linked posts?

1. /
   2 people · 2 mentions · first linked 2023-06-28
2. Make Stable Diffusion up to 100% faster with Memory Efficient Attention
   2 people · 2 mentions · first linked 2022-09-26
3. 4x faster image segmentation with TRTorch
   2 people · 2 mentions · first linked 2021-09-07

What Hacker News says?

1. MintsJohn · 2022-09-28

   I'm curious whether this really is "the fastest model yet" there are pytorch optimizations as well. Something like global optimization has been done in pytorch, here's a blog about it: https://www.photoroom.com/tech/stable-diffusion-25-percent-f... Mixed precision seems pretty much default looking at a few Stable Diffusion notebooks. More intriguing, there's also a more local optimization that makes pytorch faster:…

   Comment linking /tech/stable-diffusion-100-percent-faster-with-memory-efficient-attention/

   on “High-performance image generation using Stable Diffusion in KerasCV”
2. ea016 · 2024-07-09

   Submitted So you want to rent an NVIDIA H100 cluster? 2024 Consumer Guide as a story · 297 points

   HN discussion
3. Etheryte · 2025-02-10

   Photoroom [0] is from Y Combinator and their product is essentially SAM plus a lot of polish along with a good user experience. I'm not sure if they're using it, but if they're not, I think they should be. [0] https://www.photoroom.com/

   Comment linking /

   on “AI Demos”
4. vvoyer · 2021-07-27

   Submitted Show HN: AI Background Remover as a story · 102 points

   HN discussion
5. mtthtlt · 2021-10-22

   I think using TRTorch[1] can be quick way to generate both easy to use and fast inference models from PyTorch. It compiles your model, using TensorRT, Ahead of Time and enables you to use the compiled model through torch.jit.load("your_trtorch_model.ts") in your application. Once compiled, you no longer need to keep your model's code in the application (as for usual jit models). The inference time is on par with Ten…

   Comment linking /tech/faster-image-segmentation-trtorch-tensorrt/

   on “PyTorch 1.10”
6. matthieurouif · 2022-09-16

   Submitted CoreML Benchmark for the iPhone 14 Pro as a story · 64 points

   HN discussion
7. Brajeshwar · 2024-02-18

   I think https://www.photoroom.com should be closer to what you are looking.

   Comment linking /

   on “PhotoPea: Advanced Image Editor”
8. ea016 · 2025-01-22

   Submitted Picking a state library for a React app used by millions and why we picked MobX as a story · 6 points

   HN discussion
9. jtriangle · 2023-06-28

   https://www.photoroom.com is also very good for some things.

   Comment linking /

   on “Show HN: Open-source background removal in the browser”
10. ea016 · 2022-09-26

    Submitted Make Stable Diffusion up to 100% faster with Memory Efficient Attention as a story · 6 points

    HN discussion
11. matthieurouif · 2023-05-25

    Background removal is becoming a commodity but at the same time being top quality is an essential block of building quality software. We built photoroom and removing background is free, no subscription needed https://www.photoroom.com/background-remover You can see that we are 2x remove.bg in accuracy https://www.velebit.ai/blog/background-removal/

    Comment linking /background-remover

    on “Show HN: Image background removal without annoying subscriptions”
12. gifflar · 2025-09-23

    Submitted How a “No DM” Slack policy drives impact at Photoroom as a story · 3 points

    HN discussion
13. hunkins · 2022-09-23

    If you're looking for an API, can personally recommend PhotoRoom: https://www.photoroom.com/api/ . Used it in one of my projects, and had zero complaints. They have a free tier as well I believe.

    Comment linking /api/

    on “Ask HN: What are the ways/softwares to remove background from image?”
14. ea016 · 2025-09-12

    Submitted We're training a text-to-image model from scratch and open-sourcing it as a story · 3 points

    HN discussion
15. matthieurouif · 2022-09-14

    Submitted Make Stable Diffusion 25% faster using TensorRT as a story · 3 points

    HN discussion
16. donpho · 2022-05-12

    Submitted AI to remove any object from a picture as a story · 3 points

    HN discussion
17. vvoyer · 2021-09-07

    Submitted 4x faster image segmentation with TRTorch as a story · 3 points

    HN discussion
18. ea016 · 2026-04-08

    Submitted Optimizing our inference back end with custom load balancing as a story · 2 points

    HN discussion
19. ea016 · 2026-01-21

    Submitted Building Google-Docs-like collaboration for an app used by millions (in Rust) as a story · 2 points

    HN discussion
20. ea016 · 2023-08-31

    Submitted We automated our changelog thanks to ChatGPT as a story · 2 points

    HN discussion
21. dsr12 · 2021-09-21

    Submitted Redesigning an Android UI used by millions as a story · 2 points

    HN discussion
22. ea016 · 2021-08-02

    Submitted Packaging your PyTorch project in Docker as a story · 2 points

    HN discussion
23. ea016 · 2020-12-23

    Submitted Show HN: A simple web app to create holiday cards from any photo as a story · 2 points

    HN discussion
24. david_lc · 2026-07-24

    Submitted Photoroom cut inference cold start to seconds with Nvidia Dynamo as a story · 1 points

    HN discussion
25. ea016 · 2026-01-19

    Submitted Building live collaboration in Rust for users, part 1 as a story · 1 points

    HN discussion
26. ea016 · 2026-01-11

    Submitted You should change your mobile app version format to year.week.iteration as a story · 1 points

    HN discussion
27. ea016 · 2026-01-04

    Submitted Our Setup for A/B Testing LLMs with Millions of Users as a story · 1 points

    HN discussion
28. ea016 · 2025-02-05

    Submitted What 9k community votes taught us about our background remover as a story · 1 points

    HN discussion
29. ea016 · 2025-01-20

    Submitted How we run daily standups for 40 engineers at Photoroom as a story · 1 points

    HN discussion
30. vvoyer · 2021-11-05

    Submitted Building a fast cross-platform image renderer as a story · 1 points

    HN discussion

Search all of HN for photoroom.com