Show HN: Time Portal – Get dropped into history, guess where you landed

Re:Show HN: Time Portal – Get dropped into history, guess wh... by samplank2 on Wednesday March 12, 2025 @06:43PM (#43348481)

I agree that it's not possible to have them do 13th century architectural style perfectly right now. But I believe it will be soon. The image/video models are improving, but so are the reasoning models, and they can check for and fix anachronisms.

[ Parent | on HN ]

Re:Show HN: Time Portal – Get dropped into history, guess wh... by lukev on Wednesday March 12, 2025 @06:51PM (#43348538)

I hope you're right. Are you aware of any image-gen models that apply chain-of-thought style reasoning (either agentic or via reinforcment learning to shape outputs?)

For example, consider this imagery from today's challenge: https://firebasestorage.googleapis.com/v0/b/fastab-f08e9.app...

These are some incredible monoliths: if they were real, I feel like I would have heard about them? And if they did... that's so cool. But because it's AI generated, I have a very low confidence level that this ever existed at all. Which is sad.

[ Parent | on HN ]

Re:Show HN: Time Portal – Get dropped into history, guess wh... by samplank2 on Wednesday March 12, 2025 @06:58PM (#43348612)

No, not aware of image models that do chain-of-thought reasoning. But there are vision models that do it, so you can have them review the generated images and iterate on the prompts.

[ Parent | on HN ]

Re:Show HN: Time Portal – Get dropped into history, guess wh... by tralarpa on Thursday March 13, 2025 @06:51AM (#43352026)

[Spoiler] I guess it's this: https://madainproject.com/northern_stelae_park

Which is funny, because the monoliths in the AI video look more eroded than the real ones today.

This looked like a nice idea at first glance. At second glance, it's really bad because you have to assume that everything you see in these videos can be wrong or misleading.

[ Parent | on HN ]

Re:Show HN: Time Portal – Get dropped into history, guess wh... by nl on Wednesday March 12, 2025 @06:51PM (#43348539)

Reasoning models aren't needed for this. The loss function for the image models needs to take year into account.

This is entirely possible, as the incredible accuracy[1] of non-generative picture location models (a very similar problem) shows.

[1] https://paperswithcode.com/sota/image-based-localization-on-...

[ Parent | on HN ]

Re:Show HN: Time Portal – Get dropped into history, guess wh... by littlestymaar on Wednesday March 12, 2025 @06:52PM (#43348558)

Why not using img2vid starting from an historically accurate picture or painting?

[ Parent | on HN ]

Re:Show HN: Time Portal – Get dropped into history, guess wh... by samplank2 on Wednesday March 12, 2025 @07:33PM (#43348841)

This does use img2vid but with AI generated images. Using real pictures or paintings could definitely be fun too.

[ Parent | on HN ]

Re:Show HN: Time Portal – Get dropped into history, guess wh... by peishang on Wednesday March 12, 2025 @09:55PM (#43349657)

You might look into era specific LoRas if they exist, and if not consider training a few to help better capture architectural detail from that specific time frame.

[ Parent | on HN ]

Re:Show HN: Time Portal – Get dropped into history, guess wh... by samplank2 on Wednesday March 12, 2025 @10:07PM (#43349726)

good idea! It would be fun to have a ton of LoRas for different places x eras

[ Parent | on HN ]