-
SDXL makes use of micro-conditioning, and it does have quite a bit of an effect on the end results. For more details, refer to the paper [here](https://arxiv.org/abs/2307.01952).
Currently, not al…
-
In the paper, T2V or I2V LCM model is distilled from T2I LCM model.
But I thinks there is no training code or model...
Can you check once ?
-
### Is there an existing issue for this?
- [X] I have searched the existing issues and checked the recent builds/commits
### What would your feature do?
My modifications were carried out as follo…
-
(venv) C:\AI\ArtSpew>py artspew.py --xl -p "Space cat cowboy" -c 10 -n 11
A matching Triton is not available, some optimizations will not be enabled
Traceback (most recent call last):
File "C:\AI…
-
Trying to install LCM LoRA from the "Download Models" option, it starts downloading and installing something then the screen refreshes and it starts again, quitting with the error
`[Download Skippe…
-
Incredible results over LCM guys, well done! I'm curious to know if you plan to also add a PCM-LORA, so we can easily integrate your approach with existing models, instead of having to perform trainin…
-
Great Job!
My purpose is to add some lighting to the image without altering it. In the video "ic_light_lcm_example_converted.mp4", such an effect was observed, but the node for this effect was not f…
-
i'm trying to apply LCMScheduler(latent-consistency/lcm-lora-sdxl) to pipe, but get black output image?
-
If I use `load_lora_weights` it breaks the ip adapter model loading.
_Code_:
```pipe.load_lora_weights("latent-consistency/lcm-lora-sdxl")```
...
```ip_model = IPAdapterXL(pipe, image_encoder_pa…
-
Hi there. The LCM sambler is the "new" goodness in A1111. Image generation can be done much faster and they come out better looking than using the standard Euler sampler.
And new custom loras and mod…
CHJ85 updated
3 months ago