-
### Feature request
Is it possible to upload an example of how to finetune PaLIGemma on multi-image inputs?
Something similar to [multi-image-inference](https://huggingface.co/docs/transformers/ma…
-
We have a "squared()" method to compensate with the Apple's default cropper's errors. I think we can include it in the upload function but in a way that is easily replaceable, like the image processor…
-
I'm getting this error when running sage inside a docker container on my mac (ARM processor), using the image in the GHCR.
> root@bf99e12ee497:/app# sage --version
> rosetta error: failed to open …
-
### Component(s)
processor/k8sattributes
### What happened?
## Description
For better integrity guarantees we've started using `name:tag@digest` image reference format (e.g. `alpine:3.19@sha256:…
-
import requests
from PIL import Image
from io import BytesIO
from controlnet_aux.processor import Processor
url = "https://huggingface.co/lllyasviel/sd-controlnet-openpose/resolve/main/images/…
-
### Describe the bug
The `apply_overlay` method of `image_processor` works unexpectedly if `init_image` and `image` have different shapes. For example it can appear using `StableDiffusionXLInpaintPip…
-
**Is your feature request related to a problem? Please describe.**
Previously, OMRChecker used to read all images in grayscale. But since we're supporting colored inputs and outputs in the v2 release…
-
Hello,
I am trying the following code to test sending multiple images:
```
import requests
import torch
from PIL import Image
from transformers import MllamaForConditionalGeneration, AutoProces…
-
I want to use surya-ocr offline. I have downloaded models `DETECTOR_MODEL_CHECKPOINT ` and `RECOGNITION_MODEL_CHECKPOINT` and updated OCR (text recognition) script as shown bellow. However, the scrip…
-
### System Info
- `transformers` version: 4.46.2
- Platform: Linux-5.4.0-1134-aws-x86_64-with-glibc2.31
- Python version: 3.10.2
- Huggingface_hub version: 0.26.2
- Safetensors version: 0.4.5
- …