-
### System Info
- CPU architecture: x86_64
- CPU/Host memory size: 32GB DDR4
- GPU properties
- GPU name: RTX 3070 Ti
- GPU memory size: 8GB
- Libraries
- TensorRT-LLM version: 0.12.0.d…
-
Hi,
Recently, I need to add attention module to mobilev2 to improve the model performance.
The cc module in your repo means `Criss-Cross Attention`? (curious aha)
Thanks!
-
Can Stable Diffusion 3 Medium be implemented via StableDiffusion3Pipeline? I noticed there were problems with self.pipe.unet.config.cross_attention_dim in SD3
-
### Your question
Hey, i've been trying to run ComfyUI with Flux for the past few weeks and it seems that no matter what I try and which Flux model I try (dev/schnell), I always get very blurred imag…
-
**Short Description**
Any possibility of getting Cross Attention Control support added for Stable Diffusion as seen implemented as per the repo linked below on the PyTorch side?
https://github.com/b…
-
Hi,
Thanks for your interest in our work.
When I compare the code with the paper, I have doubts about Cross-Modal Gated Attention, the paper and the code seem to be inconsistent, can you provide mor…
-
-
Hi authors,
Thanks for your great work! I'd like to ask have you ever tested the performance of this transformer encoder-only model for 3D instance segmentation compared with Oneformer3D.
Best
-
Currently, encoder-decoder models lack support for Grad-CAM (Gradient-weighted Class Activation Mapping) visualization with cross-attention mechanisms. Grad-CAM is a valuable tool for interpreting mo…
-
Hi, I'm interested in your work and try to reproduce it, but there are some details need to be confirmed.
The first one is the implementation of MVAE. The paper said,
> We copy the network archi…