-
### Describe the bug
I currently have a Flask app that uses Gradio API for inferencing. If I run it with normal Flask built-in WSGI server, it'll work.
However, I want to run it with gunicorn and ge…
-
**LocalAI version:**
[9aa2a7c](https://github.com/mudler/LocalAI/commit/9aa2a7ca13c5fa47ea46eb5359eec5d2c9d7f5ad)
**Environment, CPU architecture, OS, and Version:**
Proxmox Ubuntu 20.04, Docker …
-
I am on amd (rx 6600 8gb) on windows , normally with sdxl I get 10sec/it which I am cool with. I have to use CPU for face analysis , and that makes the average step around 60 secs on the same workflow…
-
### Processor
M1 (or later)
### Memory
8GB
### What happened?
I loaded [SDXL Turbo 1.0 fp16 6bit split einsum](https://huggingface.co/coreml-community/coreml-sd_xl_turbo_1.0_fp16_6-bit/…
-
### System Info
I am trying to compile `stabilityai/sdxl-turbo` for Inferentia inf2.
I used the optimum CLI to export to neuron, using `optimum-cli export neuron -m stabilityai/sdxl-turbo --bat…
-
### Describe the bug
I am try to implement a Talk bot using this model: https://huggingface.co/stabilityai/sdxl-turbo
Model size is **6.94G**, it always fail in download after probably 40 second…
-
Am trying to run the SDXL model with Optimum Neuron and inf2 and getting the following error when compiling the UNET portion:
```
2023-12-03 22:21:00.337954: F /opt/workspace/KaenaTorchXlaWheels/b…
-
**Is your feature request related to a problem? Please describe.**
I'm trying to download a lot of different models via a script for HuggingFace deployment. I would like them to have all the metadata…
-
### First, confirm
- [X] I have read the [instruction](https://github.com/Gourieff/comfyui-reactor-node/blob/main/README.md) carefully
- [X] I have searched the existing issues
- [X] I have updated t…
-
### Describe the bug
When I use HF diffusers to download a model/checkpoint from HF using the `.from_pretrained()` method, it downloads the same model/checkpoint over and over, usually on different…