Issues
- 3
i need LORA support
#42 opened by sev7eny - 5
- 3
The first latent space if full of nan, resulting in a black image for the first of each batch
#5 opened by Extraltodeus - 4
IP Adapter Support
#48 opened by Sundragon1993 - 4
Exporting the operator 'aten::scaled_dot_product_attention' to ONNX opset version 17 is not supported. Please feel free to request support or submit a pull request on PyTorch GitHub: https://github.com/pytorch/pytorch/issues.
#21 opened by koyamakkkkk - 0
- 0
Is FreeU_V2 support?
#52 opened by Hamidawaan - 0
- 1
- 0
recommend to cancel "connect to gitlab"
#47 opened by gaoxuxu110 - 4
add ControlNet support
#10 opened by geroldmeisinger - 2
How to run SD3 with Tensor RT?
#45 opened by Jay19751103 - 0
Hangs during TensorRT compilation
#46 opened by nikolatesla20 - 12
[Request] Example workflows for SD3 models.
#28 opened by syddharth - 7
- 0
- 5
Built engines are placed in the "output" folder
#13 opened by aikitoria - 2
- 1
[executionContext.cpp::nvinfer1::rt::ShapeMachineContext::resolveSlots::2842] Error Code 3: API Usage Error (Parameter check failed at: runtime/api/executionContext.cpp::nvinfer1::rt::ShapeMachineContext::resolveSlots::2842, condition: allInputDimensionsSpecified(routine) )
#31 opened by DarkAlchy - 0
output (.engine) files go to --output-directory but are expected in default output directory
#38 opened by pollockjj - 0
"Exception during processing!!! ONNX export failed. Could not open file or directory."
#37 opened by Reno0vacio - 0
Feature request: P100/p4 support
#36 opened by dirkson - 27
- 14
- 1
[Bug] RuntimeError: The size of tensor a (96) must match the size of tensor b (168) at non-singleton dimension 3
#29 opened by yusing - 2
What do I do to delete the list of built models?
#27 opened by alex13by - 1
Error occured when executing KSampler
#17 opened by fusillustrator - 2
Instructions for downloading, installing and using the pre-converted TensorRT versions of SD3 Medium with ComfyUI and ComfyUI_TensorRT
#23 opened by MarcusJT - 1
mat1 and mat2 must have the same dtype
#22 opened by koyamakkkkk - 0
FP8 support for TensorRT?
#24 opened by wingmrc - 2
Can the width and height be dynamically adjusted? For example, support 576×768 or 768×576 at the same time?
#19 opened by petercham - 4
- 9
an illegal memory access was encountered
#9 opened by GavChap - 8
IMPORT FAILED
#12 opened by yotraxxx - 3
How to load only CLIP from checkpoint
#15 opened by aikitoria - 3
- 1
With the current security level configuration, only custom nodes from the "default channel" can be installed.
#6 opened by AlexD81 - 2
Can't convert SDXL models 'aten::scaled_dot_product_attention' to ONNX opset version 17 is not supported
#8 opened by NeoLoger