DeepSeek-v4-flash-vision-exp
api-docs.deepseek.com
DeepSeek-v4-flash-vision-exp
1–10 of 169 posts
Re: DeepSeek-v4-flash-vision-exp
#2I've heard that DeepSeek v4 Flash 0731 has frequently assumed that it has vision capabilities and then resorts to inventing text-based image analysis tools when it finds that it actually can't see. In that case, this is a great upgrade for the model.
Anecdotally, I had to tell 0731 to refrain from viewing screenshots since it kept breaking its sessions by trying to read images.
Re: DeepSeek-v4-flash-vision-exp
#3> Larger images are scaled down while preserving their aspect ratio, so that the total pixel count after resizing is roughly that of an 800×800 image.
It's useful but for OCR and a lot of other applications it needs to be a bit higher (eg: putting in a full A4 / Letter sized page)
Re: DeepSeek-v4-flash-vision-exp
#4DS being unable to precisely view Playwright screenshots is the only thing I really miss from Sonnet. This is promising.
> Images are converted into tokens based on their dimensions, and these tokens are billed together with your text tokens.
> Before inference, every image is automatically resized:
> - Images with a total pixel count below roughly 384×384 are scaled up while preserving their aspect ratio.
> - Larger images are scaled down while preserving their aspect ratio so that the total pixel count after resizing is roughly that of an 800×800 image.
> As a result, there is an upper bound of 384 tokens per image: for example, a 2000×2000 image and a 5000×5000 image consume the same number of tokens after resizing. When a request contains multiple images, each image is counted independently under the same rule—there is no separate calculation for multi-image requests.
400 tokens per image results in 2,500 images per dollar, if I’m not mistaken.
edit: format.
Re: DeepSeek-v4-flash-vision-exp
#5DS being unable to precisely view Playwright screenshots is the only thing I really miss from Sonnet. This is promising. > Images are converted into tokens based on their dimensions, and these tokens are billed together with your text tokens. > Before inference, every image is automatically resized: > - Images with a total pixel count below roughly 384×384 are scaled up while preserving their aspect ratio. > - Larger…
Oof 800 by 800 kills a lot of use cases
Re: DeepSeek-v4-flash-vision-exp
#6> Larger images are scaled down while preserving their aspect ratio, so that the total pixel count after resizing is roughly that of an 800×800 image. It's useful but for OCR and a lot of other applications it needs to be a bit higher (eg: putting in a full A4 / Letter sized page)
Can split and feed?
Re: DeepSeek-v4-flash-vision-exp
#7[dead]
Re: DeepSeek-v4-flash-vision-exp
#8> Larger images are scaled down while preserving their aspect ratio, so that the total pixel count after resizing is roughly that of an 800×800 image. It's useful but for OCR and a lot of other applications it needs to be a bit higher (eg: putting in a full A4 / Letter sized page)
Can split and feed?
that's difficult as well, how do you k ow where to split?
Re: DeepSeek-v4-flash-vision-exp
#9will this be open weights?
Re: DeepSeek-v4-flash-vision-exp
#10DS being unable to precisely view Playwright screenshots is the only thing I really miss from Sonnet. This is promising. > Images are converted into tokens based on their dimensions, and these tokens are billed together with your text tokens. > Before inference, every image is automatically resized: > - Images with a total pixel count below roughly 384×384 are scaled up while preserving their aspect ratio. > - Larger…
Oof 800 by 800 kills a lot of use cases
flash vs fine details. Pick one.