-
### Describe the bug
When couch jumping with mv_duckjump enabled, the playermodel will clip into the floor. This only happens when crouchjumping with crouch then jump, and not jump then crouch. Can…
-
Hello, when I run the training code python3 train.py --config ./config/detectiondiffusion.py, it shows:
(affpose) henry@yh:~/project/Language-Conditioned-Affordance-Pose-Detection-in-3D-Point-Cloud…
-
Hello,
I noticed a potential issue in the fit_epoch method in https://github.com/d2l-ai/d2l-en/blob/master/d2l/torch.py, where loss.backward() is called within a torch.no_grad() block:
```
sel…
-
加载Load Eva Clip会自动下载EVA02_CLIP_L_336_psz14_s6B.pt这个模型，但是如果网络不通，会一直报错，可以去下面链接手动下载这个模型，https://huggingface.co/QuanSun/EVA-CLIP/tree/main
然后注释掉Comfy/custom_nodes/PuLID_ComfyUI/eva_clip/factory.py中的279行
…
-
The model is running on cuda
Traceback (most recent call last):
File "demo.py", line 206, in
sam_pipeline = load_sam(cfg, device)
File "demo.py", line 166, in load_sam
pipelines = …
-
I would like to know if pretrained Concept-QA and V-IP are available for use without the need to train them from scratch. If they are, could you provide information on where to download them?
Thank…
-
我的comfyui已经变更了extra_model_paths.yaml，内容如下：
base_path: E:/ComfyUI-aki-v1.3/
checkpoints: E:/comfyui_models/checkpoints/
clip: E:/comfyui_models/clip/
clip_vision: E:/comfyui_models/c…
-
### Model description
Hi!
I recently trained a CLIP model with an NLLB text encoder to extend CLIP capabilities to 201 languages of the Flores-200 dataset. As far as the implementation goes, it is…
-
Why do not use clip image and text encoder? In Stable diffusion, text encoder used clip text encoder, and freeze condtion model while training diffusion. But in SDFusion, text encoder do not use clip-…
-
Using [win vulkan, master-f4c937c](https://github.com/leejet/stable-diffusion.cpp/releases/download/master-f4c937c/sd-master-f4c937c-bin-win-vulkan-x64.zip)
Download the weights following [flux.md]…