For what do you guys use vision in those models? surveillance is the obvious use case... but are there some "nicer" ways to use it?
[dead]
DeepSeek-v4-flash-vision-exp
41–50 of 169 posts
Re: DeepSeek-v4-flash-vision-exp
#42For what do you guys use vision in those models? surveillance is the obvious use case... but are there some "nicer" ways to use it?
The obvious use case, especially on HN, is frontend dev of any kind at all. The second most obvious one is OCR of paper documents.
Frontend Dev? I do not really understand.
do you let the models analyze the webpages you are working on? or for testing?
Re: DeepSeek-v4-flash-vision-exp
#43For what do you guys use vision in those models? surveillance is the obvious use case... but are there some "nicer" ways to use it?
The obvious use case, especially on HN, is frontend dev of any kind at all. The second most obvious one is OCR of paper documents.
but for OCR there are much better suited models, I use mlx-community/PaddleOCR-VL-8bit
Re: DeepSeek-v4-flash-vision-exp
#44For what do you guys use vision in those models? surveillance is the obvious use case... but are there some "nicer" ways to use it?
My product is connecting employers and workers with conversational agents. They love to communicate with images — CVs, documents, photos of worksites. Even CV-as-photo or offer-as-photo format is very popular. My daily driver Deepseek Flash can't see those photos. So I use image models to let agents understand the context.
Re: DeepSeek-v4-flash-vision-exp
#45Earlier quoted context omitted.
The obvious use case, especially on HN, is frontend dev of any kind at all. The second most obvious one is OCR of paper documents.
Frontend Dev? I do not really understand. do you let the models analyze the webpages you are working on? or for testing?
QA of course. You hook up your agent with CDP access to live product + let it screenshot and look into result. Also you could hook agent with CDP access to Figma to read/write, there a vision model is very useful as well.
Re: DeepSeek-v4-flash-vision-exp
#46Earlier quoted context omitted.
For most use cases you can fix that in the harness. Just give the model a tool to request a crop of specific coordinates of any image it has in its context. Call the tool "zoom" and it should be intuitive for the model Maybe there are some use cases where you need high detail everywhere at once, but for OCR of small text and the like a zoom ability should be sufficient
For really dumb models I've also had success automatically cropping it into a grid of N images with the max size, then processing each cell individually, then once all been processed, do one final call with resized image + all other context previously generated per cell. Basically a workaround to the image dimension restrictions without loosing fidelity. Works well with even dumb 7B models. Can't remember if I stole…
Does this not loose context? Especially e.g. in fonts where the character pairs 0O 1I 1l Il may be difficult to differentiate?
Re: DeepSeek-v4-flash-vision-exp
#47For what do you guys use vision in those models? surveillance is the obvious use case... but are there some "nicer" ways to use it?
I've been working on an agentic graphic design tool, so vision is quite useful for having the model check its own work. I'm already seeing improvements with this model vs the text-only one.
Re: DeepSeek-v4-flash-vision-exp
#48Earlier quoted context omitted.
The obvious use case, especially on HN, is frontend dev of any kind at all. The second most obvious one is OCR of paper documents.
Frontend Dev? I do not really understand. do you let the models analyze the webpages you are working on? or for testing?
Standard flow with a vision model in OMP is to write the front end code, fire up the server, fire up a headless browser and then take screenshots and examine and iterate. Works great. When I'm using DeepSeek V4 Flash, it always reminds me instead that I have to validate manually by loading up the page.
Re: DeepSeek-v4-flash-vision-exp
#49Re: DeepSeek-v4-flash-vision-exp
#50Earlier quoted context omitted.
The obvious use case, especially on HN, is frontend dev of any kind at all. The second most obvious one is OCR of paper documents.
but for OCR there are much better suited models, I use mlx-community/PaddleOCR-VL-8bit
Sometimes you intentionally want to verbatim keep "mistakes", sometimes you don't and want them to be "fixed". OCR-only models tend to only do one of those two, in VLM cases often the latter. With multi-modal LLMs you can just tell them (adherence of course needing evals/differs per model).