-
```
from transformers import Qwen2VLForConditionalGeneration, AutoTokenizer, AutoProcessor
from qwen_vl_utils import process_vision_info
from transformers import Qwen2VLProcessor
from awq.models.q…
-
How to do the inference on multi-images? I try to input 2 images, but enconter a error ValueError: Number of image tokens in input_ids (1) different from num_images (2). Here is my code:
---------…
-
Great work!
How to perform the task of generating video captions？
-
**What API design would you like to have changed or added to the library? Why?**
we are using class UNetMotionModel(ModelMixin, ConfigMixin, UNet2DConditionLoadersMixin, PeftAdapterMixin)
and its `f…
-
I have macbook pro m3 max 48 GB. Can i run Mochi?
-
I have been trying to fix this error for a while now, and the ongoing threads are of NO help.
I have checked these (and ALL issue on the HF community page for this model):
* https://github.com/Qwe…
-
Q: Does HallowMeme support video-2-video mode? Or does it only support the input image?
-
https://github.com/user-attachments/assets/c2445e46-ea45-459a-83d2-ff7c1265ec16
-
**Describe the bug**
When using the PVP Style feature (for single target, aoe or for winder combo), the reawaken feature only displays the first generation/legacy combo, and gets stuck at that. It ne…
-
你好，我的推理代码如下
```python
from PIL import Image
import torch
from transformers import Qwen2VLForConditionalGeneration, AutoTokenizer, AutoProcessor
from qwen_vl_utils import process_vision_info
…