TE
TechEcho
Home24h TopNewestBestAskShowJobs
GitHubTwitter
Home

TechEcho

A tech news platform built with Next.js, providing global tech news and discussions.

GitHubTwitter

Home

HomeNewestBestAskShowJobs

Resources

HackerNews APIOriginal HackerNewsNext.js

© 2025 TechEcho. All rights reserved.

Show HN: Visualise novels using Midjourney and GPT-4

13 pointsby parsabgover 1 year ago

3 comments

druskacikover 1 year ago
Great job. I recently had a similar idea while reading the sci-fi series <i>The Expanse</i> - I read in English and since it&#x27;s not my first language, I am often confused by descriptions of spaceships, planets, constructions, etc. I have problems visualising it.<p>I had an idea to use RAG to extract all relevant descriptions of given object and compile them to a detailed description. The description would be fed to a text-to-image model.<p>Have you considered something similar? It would be harder to implement, but the results could be more precise and it would be possible to cover books GPT-4 is not familiar with.
a2codeover 1 year ago
Well done. What are your thoughts on a tool for generalizing the idea of linking a multiplicity of models? In this case, you linked: GPT-4 -&gt; Midjourney. A generalized example would be: Model-A -&gt; Model-B -&gt; Model-C etc.
jackofspadesover 1 year ago
Very interesting. Could someone feed their own novel to it?