Replies: 6 comments 4 replies
-
I successfully installed it but still encountered the same issue as before. I can guarantee that this model works in the normal dev mode and performs better than the original model. I used a special reverse distillation dev model for training, but it seems that the quantization is not compatible with it. lora_unet_img_in.alpha, lora_unet_img_in.lora_down.weight, lora_unet_img_in.lora_up.weight, lora_unet_txt_in.alpha, lora_unet_txt_in.lora_down.weight, lora_unet_txt_in.lora_up.weight lora_unet_img_in.alpha, lora_unet_img_in.lora_down.weight, lora_unet_img_in.lora_up.weight, lora_unet_txt_in.alpha, lora_unet_txt_in.lora_down.weight, lora_unet_txt_in.lora_up.weight |
Beta Was this translation helpful? Give feedback.
-
That was working for me flawlessly almost for 1 day. Then, I wanted to do some post processing on image so I added some custom nodes: But after the install of those, nunchaku wasn't loading properly. The error I get: The above exception was the direct cause of the following exception: Traceback (most recent call last): Cannot import H:\AIgenerated\StableDiffusion\ComfyUI_TEST2\custom_nodes\ComfyUI-nunchaku module for custom nodes: Failed to import diffusers.models.transformers.transformer_flux because of the following error (look up to see its traceback): Most likely something to do with, Triton, Diffusers, cuda_utils, cuda DLL, but i reinstalled all of those so many time i lost the count. |
Beta Was this translation helpful? Give feedback.
-
When will union PRO2 be supported? |
Beta Was this translation helpful? Give feedback.
-
Any ipadpter supported? |
Beta Was this translation helpful? Give feedback.
-
ComfyUI Error ReportError Details
Stack Trace
System Information
Devices
Logs
Attached WorkflowPlease make sure that workflow does not contain any sensitive information such as API keys or passwords.
Additional Context(Please add any additional context or steps to reproduce the error here) |
Beta Was this translation helpful? Give feedback.
-
Beta Was this translation helpful? Give feedback.
Uh oh!
There was an error while loading. Please reload this page.
Uh oh!
There was an error while loading. Please reload this page.
-
This discussion is no longer actively monitored. For the most up-to-date FAQ, please refer to docs/faq.md.
❗ Import Error:
ImportError: cannot import name 'to_diffusers' from 'nunchaku.lora.flux' (...)
(e.g., #250)This error usually indicates that the nunchaku library was not installed correctly. We’ve prepared step-by-step installation guides for Windows users:
📺 English tutorial | 📺 Chinese tutorial | 📖 Corresponding Text guide
Please also check the following common causes:
You only installed the ComfyUI plugin (
ComfyUI-nunchaku
) but not the corenunchaku
library. Please follow the installation instructions in our README to install the correct version of thenunchaku
library.You installed
nunchaku
usingpip install nunchaku
, but this is the wrong package.The
nunchaku
name on PyPI is already taken by an unrelated project. Please uninstall the incorrect package and follow our installation guide to install the correct version.(MOST LIKELY) You installed
nunchaku
correctly, but into the wrong Python environment.If you're using the ComfyUI portable package, its Python interpreter is very likely not the system default. To identify the correct Python path, launch ComfyUI and check the several initial lines in the log. For example, you will find
To install
nunchaku
into this environment, use the following format:Example (for Python 3.11 and torch 2.6):
"G:\ComfyUI\python\python.exe" -m pip install https://github.com/mit-han-lab/nunchaku/releases/download/v0.2.0/nunchaku-0.2.0+torch2.6-cp311-cp311-linux_x86_64.whl
You have a folder named
nunchaku
in your working directory.Python may mistakenly load from that local folder instead of the installed library. Also, make sure your plugin folder under
custom_nodes
is namedComfyUI-nunchaku
, notnunchaku
.❗ Runtime Error:
Assertion failed: this->shape.dataExtent == other.shape.dataExtent, file ...Tensor.h
(e.g., #212)This error is typically due to using the wrong model for your GPU.
❗ System crash or blue screen (e.g., #57)
We have observed some cases where memory is not properly released after image generation, especially when using ComfyUI. This may lead to system instability or crashes.
We’re actively investigating this issue. If you have experience or insights into memory management in ComfyUI, we would appreciate your help!
❗Out of Memory or Slow Model Loading (e.g.,#249 #311 #276)
Try upgrading your CUDA driver and try setting the environment variable
NUNCHAKU_LOAD_METHOD
to eitherREAD
orREADNOPIN
.❗Same Seeds Produce Slightly Different Images (e.g., #229 #294)
This behavior is due to minor precision noise introduced by the GPU’s accumulation order. Because modern GPUs execute operations out of order for better performance, small variations in output can occur, even with the same seed.
Enforcing strict accumulation order would reduce this variability but significantly hurt performance, so we do not plan to change this behavior.
❓ PuLID Support (e.g., #258)
PuLID support is currently in development and will be included in the next major release.
❗ Assertion Error:Assertion failed: a.dtype() == b.dtype(), file ...misc_kernels.cu
(e.g., #57)At the moment, we only support the 16-bit version of ControlNet-Union-Pro. Support for FP8 and other ControlNets is planned for a future release.✅ This issue has now been resolved.❗ Assertion Error:assert image_rotary_emb.shape[2] == batch_size * (txt_tokens + img_tokens)
(e.g., #24)Currently, batch sizes greater than 1 are not supported during inference. We will support this in a future major release.✅ Multi-batch inference is now supported as of v0.3.0dev0.Beta Was this translation helpful? Give feedback.
All reactions