Hacker News Reader

Hacker News

Comment by vinni2 | Hacker News Reader

Parent Full thread

vinni2

I thought Anthropic models didn’t generate images.

View on HN

This is SVG, but recent Anthropic models have got extremely good at other forms of visual data.

Here's a Blender model I had Claude Opus 5.5 create: https://tools.simonwillison.net/blender-viewer?url=https%3A%...

And here's some animated pixel art by Opus 5.5: https://tools.simonwillison.net/kakapo-party

And some Monkey Island style music (Opus can compose music too): https://tools.simonwillison.net/scrimshaw-jukebox

Anthropic's models do all of this by outputting code. GPT-6 Astra has similar capabilities - I got this Blender model using that: https://tools.simonwillison.net/blender-viewer?url=https%3A%...

They are really good at generating artifacts, which are windows within the replies containing all kind of visualization, often interactive.

They are still not great at SVG. I just asked Opus and Fable to add a background to an SVG and the results were, well, not great.

SVG is hard.

Tried it with GPT-6 Astra with Ultra but the outcome was underwhelming with Blender. Maybe it was my prompting ¯\_(ツ)_/¯

This is great! Love the pixel art and tunes.

Pardon, I have a lot of questions about that Scrimshaw music text format. It's clever. Did you invent it, and is it specifically intended to be written to by LLMs? Is the editor/player LLM-coded as well, and was this its recommendation for a format that would be easy for LLMs to write? I'm wondering why this instead of say, asking it to write a .MOD file.

Opus invented it, and wrote the player, and the songs.

My prompts were:

> I want you to write some computer game music for me. First design simple text based format for the music and build an artifact that can play it out loud - include some example tracks in that artifact

> I am looking for music of the quality of the original secret of Monkey Island

And then later:

> Modify scrimshaw jukebox to add a copy-paste prompt that explains the music format, it should be shown at the bottom of the page below the readable instructions, the prompt should be designed to help any LLM tool compose music in the correct format. It should have a copy to clipboard button.

https://claude.ai/share/1f721c20-2499-4d23-b368-3ab57146d956 and then https://claude.ai/code/session_01R3xuRtjVHqHo1GNbget6Tu

What was the prompt for the widow's bay egg?

I pasted in a concept image (created by ChatGPT images here https://chatgpt.com/share/6ac16336-c288-83e8-9f28-084d184363...) and prompted:

> Use your blender local skill to create a blender model of this faverge egg

The blender local skill is this one: https://github.com/simonw/gpt-6-astra-blender-pelican-bicycl... - which I described here: https://til.simonwillison.net/llms/blender-coding-agents-mac...

I’ve had it transcribe speech from images of a waterfall viz

I have been using these models to make 3d models with build123d — they are great at it. I am never touching Fusion again. Astra is current a bit better than Opus 5.5.

I’ve been playing around with Opus 5.5 which has made a big leap over previous generations in its ability to use a simple drawing-instruction prompt to generate images.

This creates Sierra AGI-style adventure game scenes painted live from simple Turtle-esque drawing instructions so you can basically provide it an empty canvas and then position text labels on the canvas where you want certain things (tavern, oak tree, etc) and it will generate a custom script for rendering them in a EGA graphics style.

https://kq-styles.specr.net

They generate svg. You can paste in pngs and they'll convert them to svg with varying degrees of success.

> You can paste in pngs and they'll convert them to svg with varying degrees of success.

I've found Opus to be REALLY good at converting images that are well-suited to being SVGs (decent resolution, sharp edges, clear color boundaries [though gradients do OK]) after a few rounds of back-and-forth. It'll do precise measurements to figure out curvature, the exact colors to use/gradient stepping, simplify complex paths, etc.

I've created multiple videos using Claude Code, including music and speech. It generates python which in turn generates frame PNGs that it runs through ffmpeg.

Please don't judge me too harshly for this particular poop video. But here is an example of something 100% generated with claude prompts only.

https://www.youtube.com/watch?v=2EqMplbt0gU

To clarify the ”100%” part - the Python script generated the video output, and you did nothing? No video edit at all? Then I think it is impressive! Are you able to share the prompts you used?

Source code is linked from the video! Scan the QR code. I will try to /resume tonight and give you some prompts.

I mean Claude code sessions are all jsonl files that it can interrogate on its own. Get a new agent to capture how it was made and what the prompts were. No need for tedious /resume’ing and prompting.

It's the easiest way to convey what I was doing. Anyway, some prompts added. I have other videos too if intersted.

I'm going to truncate a lot of this. But here is the root prompt that will get you a video.

  Make a youtube poop video about having too many tabs that keep appearing faster than you can close them. Style it after the "too many cooks" viral youtube video that seemed to repeat over and over, getting worse and worse every time. You have ffmpeg and a plethora of programming languages at your disposal. Go completely nuts and make it as extensive and creative as you want. Render should be 1920x1080, and later 4k if you did a good job.

[discussions about acts, characters, darkening theme, etc.]

Workshopping the acts:

  The play has a font issue. See screenshot.

  [Image #1]

  Also, can you change the thing that happens at the start of episode one the cursor clicking the one tab and it becomes two. Then it clicks another tab and it becomes four. Is that a breaking change? You can change the speed of the actions to fit it in if needed.

Here is a refinement prompt:

  The last screen just before "The End", the cursor clicks on the browser window instead of the tab close button. Can you make it click on the tab itself? Here is a screenshot of where it clicks [Image #3]

  Also, on the intro screen, the cursor clicks the tab and new tabs open, can you have it click the links in the page instead. See screenshot[Image #4].

  You can keep the exact same timing for both of these.

The Purple Screen of Death at the end :)

... is a link to the source code.

They don’t do raster images.

This isn't entirely true! Here's a cat I had claude write the binary "directly" to a .bmp file! ;)

https://imgur.com/a/i7KAgB6

SVG is code

They're SVGs

Those are SVGs not images.

Bruh. Svg. It is like drawing something with geometric shapes which are represented using equations.

Reply on news.ycombinator.com