-
Hello,
I am using python 2.7 with Bokeh 0.12.9. My plot is similar to the mixed factor example where I would like to label a glyph on the plot. I can draw on the plot using a tuple of strings of th…
-
Currently, image hashes are in the form `{hash}-{id}-image.png` (with some minor variations)
my proposal, inspired by @preimpression, is to change this convention to `{id}-{hash}-image.png`
### …
-
I try training with with this parameter:
{
"adaptive_noise_scale": 0,
"additional_parameters": "",
"async_upload": false,
"bucket_no_upscale": true,
"bucket_reso_steps": 64,
"cache_…
-
Hi! It's a user from issue #255.
I seem to have three possibly related issues:
1) The trainer reports the loss value of nan.
2) None of the `Save only last`, `Save ratio`, `Save freq` options sav…
-
Both exllamav2 and llama.cpp support [quantized KV cache](https://github.com/ggerganov/llama.cpp/discussions/5932) to allow pretty large context lengths on consumer hardware. It would be a great addit…
-
![20161123202302_1](https://cloud.githubusercontent.com/assets/18079316/20562040/9e2aa504-b1bc-11e6-9d7a-9fbb8b51908d.jpg)
Hard to spot on atlas's screen but it's in between the 2 models.
-
Can I modify the `examples/cogvideo/train_cogvideox_image_to_video_lora.py` in [diffusers](https://github.com/huggingface/diffusers/blob/main/examples/cogvideo/train_cogvideox_image_to_video_lora.py)…
-
PLEASE add option to make the 3D model handles smaller. The "normal" option is way too large for small models. In this screenshot with three nodes, it took my nearly an hour of zooming, trying to grab…
-
### Describe the bug
When I use IP_adapter and hd_painter at the same time.
it pop out the RuntimeError: mat1 and mat2 shapes cannot be multiplied (514x1280 and 1024x3072).
It should be successfu…
-
### Bug description
The default OCR model works very well, but the `render()` algorithm which converts coordinates to text positions is very buggy.
This causes lines originally placed at the top t…