-
### Describe the bug
I am running IP adapter for 768x1344 which is one of the sdxl listed resolutions. I find that the output quality is much less than say regular 768x768 generations. I've attached …
-
### Model/Pipeline/Scheduler description
https://huggingface.co/huchenlei/ControlNet_plus_plus_collection_fp16/tree/main
https://huggingface.co/huchenlei/ControlNet_plus_plus_collection_fp16/discu…
-
如题，ckpt怎么转化为ppdiffusers格式，相反ppdiffusers格式怎么转化为ckpt格式。
另外训练出的Lora模型怎么和基础模型合并？
还有训练controlnet时，--pretrained_model_name_or_path runwayml/stable-diffusion-v1-5 \这里是填写基础模型，还是要训练的controlnet模型。如果是基础模型的话，假如…
-
**Is your feature request related to a problem? Please describe.**
The current AnimateDiffSDXLPipeline doesn't support neither 1 controlnet nor multi controlnets.
I've been working on this task for …
-
I change controlnet args as follow:
class ControlNetModel(nn.Module):
_supports_gradient_checkpointing = True
def __init__(
self,
in_channels: int = 4,
flip_s…
-
I went through the instructions for installation. During the Canny run got these errors
```
python controlnet_union_test_canny.py
Traceback (most recent call last):
File "controlnet_union_tes…
-
There are such introductory data: take the basic module (https://civitai.com/models/4384 ?modelVersionId=128713), this is the control network (https://huggingface.co/lllyasviel/sd-controlnet-depth ), …
-
any chance you can add an example of using control net with img2img to the Collab doc (without inpainting)?
I followed the instructions and tried adding the StableDiffusionControlNetInpaintImg2ImgP…
-
### Describe the bug
argument of type 'NoneType' is not iterable
checkpoint = os.path.join(hub_dir, "checkpoints/StableDiffusionXL/model/ud_sdxl-动漫二次元.safetensors")
pipe = StableDiffusionCon…
-
When I use Dynamically Switch LoRA, I cannot achieve the switching of LoRa. Switching to LoRa 2 results in the same image as LoRa 1.
PyTorch version 2.1.2
```python
def update_state_dict(dst, s…