Skip to content

Commit 689d397

Browse files
fpagnybene2k1
authored andcommitted
Update pixtral-12b-2409.mdx (#4424)
Updated limitations for Pixtral model regarding image size.
1 parent 4d3c71e commit 689d397

File tree

1 file changed

+3
-1
lines changed

1 file changed

+3
-1
lines changed

pages/managed-inference/reference-content/pixtral-12b-2409.mdx

Lines changed: 3 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -160,7 +160,9 @@ Process the output data according to your application's needs. The response will
160160
Only bitmaps can be analyzed by Pixtral, PDFs and videos are not supported.
161161

162162
#### Is there a limit to the size of each image?
163-
The only limitation is in context window (1 token for each 16x16 pixel).
163+
Images size are limited:
164+
- Directly by the maximum context window. As an example, since tokens are squares of 16x16 pixels, the maximum context window taken by a single image is `4096` tokens (ie. `(1024*1024)/(16*16)`)
165+
- Indirectly by the model accuracy: resolution above 1024x1024 will not increase model output accuracy. Indeed, images above 1024 pixels width or height will be automatically downscaled to fit within 1024x1024 dimension. Note that image ratio and overall aspect is preserved (images are not cropped, only additionaly compressed).
164166

165167
#### What is the maximum amount of images per conversation?
166168
One conversation can handle up to 12 images (per request). The 13rd will return a 413 error.

0 commit comments

Comments
 (0)