-
I 've noticed that 'decode_to_img' function in taming-transformer and vq-vae using decode_code or get_codebook_entry, but in ldm, decode_first_stage is quantize -> decode if not set predict_cid = True…
-
### Is there an existing issue for this?
- [X] I have searched the existing issues and checked the recent builds/commits
### What happened?
I ran into very weird oddity with VRAM usage of hir…
-
Error completing request
Arguments: ('task(27pjrvvz6k7p7oz)', ' (masterpiece), best quality, black background, solo, black theme, black capelet, glowing, simple background, 1girl, capelet, dark, lo…
-
Im trying to use control net on colab which seems to work fine on 'standard' GPU instances, when i try to use faster premium instance on colab i get the following errors
`Error completing request
…
-
Currently, the tool supports inpainting through cli and ui but having a python api is extremely helpful since it gives a better control on the process.
Any possibility of working on a python api?
-
Hi, I'm running stablediffusion through a conda environment and the diffusers library.
Say my code looks like this:
```py
# make sure you're logged in with `huggingface-cli login`
from torch i…
-
AttributeError: partially initialized module 'cv2' has no attribute 'gapi_wip_gst_GStreamerPipeline' (most likely due to
a circular import)
I ensure that no erro in pip install and pip list ,but w…
-
Nvidia has released their new paper regarding video generating model, ```Nvidia Video LDM```, which is based on stable diffusion.
https://arxiv.org/pdf/2304.08818.pdf
Do you have any plans to re…
-
### Actual Behavior
I have an error using the new controlnet
### Steps to Reproduce
I used an workflow with the UNET loader
### Debug Logs
```powershell
got prompt
Using pytorch att…
-
I used your great work to train a model, and the generated safetensors files works in WebUI;
however it could not be used in pure code with pipeline, such as
```
# in main
pipeline = StableDi…
sinri updated
9 months ago