Open syddharth opened 1 week ago
same here !
I just made a pull request for it.
sd3-TensorRT-empty_prompt.json Here you go
Or
https://github.com/yusing/ComfyUI_TensorRT/tree/master/workflows
I am still getting black images using the same workflow.
I am still getting black images using the same workflow.
Multiple possible reasons
I am still getting black images using the same workflow.
try it again (I don't know why but it works sometime).
@yusing Thank you so much!
I am still getting black images using the same workflow.
Multiple possible reasons
- You didn't enter anything in the prompts
- Loading the wrong CLIP? Use those from SD3, not SDXL.
- Loading the wrong model, should be plain SD3 Medium, not the one with CLIP.
- Loading the wrong vae. Do not use vae from SDXL. Dump vae first, then select it in the "load vae" node.
Yeah everything is correct, I re trained the engine. With 1024 and Batch 1. Now when I use Dual Clip like in your workflow, I get no command errors, however in queing a batch of 20, 2-3 are noise or black. At that point it gives an error in cmd for that que.
Now when I use the triple clip, I get this in the command prompt:
[TRT] [E] 3: [executionContext.cpp::nvinfer1::rt::ExecutionContext::setInputShape::2068] Error Code 3: API Usage Error (Parameter check failed at: runtime/api/executionContext.cpp::nvinfer1::rt::ExecutionContext::setInputShape::2068, condition: satisfyProfile Runtime dimension does not satisfy any optimization profile.)
However its working and behavior is same like the dual clip. I get 2-3 black images out of 20.
I am still getting black images using the same workflow.
Multiple possible reasons
- You didn't enter anything in the prompts
- Loading the wrong CLIP? Use those from SD3, not SDXL.
- Loading the wrong model, should be plain SD3 Medium, not the one with CLIP.
- Loading the wrong vae. Do not use vae from SDXL. Dump vae first, then select it in the "load vae" node.
Yeah everything is correct, I re trained the engine. With 1024 and Batch 1. Now when I use Dual Clip like in your workflow, I get no command errors, however in queing a batch of 20, 2-3 are noise or black. At that point it gives an error in cmd for that que.
Now when I use the triple clip, I get this in the command prompt:
[TRT] [E] 3: [executionContext.cpp::nvinfer1::rt::ExecutionContext::setInputShape::2068] Error Code 3: API Usage Error (Parameter check failed at: runtime/api/executionContext.cpp::nvinfer1::rt::ExecutionContext::setInputShape::2068, condition: satisfyProfile Runtime dimension does not satisfy any optimization profile.)
However its working and behavior is same like the dual clip. I get 2-3 black images out of 20.
That may be a bug with the TensorRT extension itself, I see many spaghetti codes inside this repo.
@yusing Thank you so much!
- how to create the TensorRT engines (missing workflow)? I just used the SDXL one.
- is the TensorRT version supposed to be reproducable, meaning should it create the same image (with same settings) as the non-rt version?
- how to load the official TensorRT models? https://github.com/comfyanonymous/ComfyUI_TensorRT/issues/23#issuecomment-2164667520
- btw you have a lora linked in your workflow
The black issue has been fixed. Works great with SD3, and the workflow given here. Update Comfy and tensor RT nodes.
https://github.com/comfyanonymous/ComfyUI_TensorRT/issues/7#issuecomment-2174013968
Are there some specific settings to get the SD3 medium models to work? I tried both dynamic and static methods but the compiled engines produce only noise or black images.