Comments (15)
Yes it's planned. There's a few more things I want to implement before. Unless something better comes out in the meantime I'm going to implement it.
from comfyui.
SDXL models now have a TensorRT variant. https://huggingface.co/stabilityai/stable-diffusion-xl-1.0-tensorrt
from comfyui.
Aaaand new drivers just dropped promising 2X performance boost with TRT
https://www.nvidia.com/en-us/geforce/news/game-ready-driver-dlss-3-naraka-vermintide-rtx-vsr/
from comfyui.
support!
https://github.com/NVIDIA/Stable-Diffusion-WebUI-TensorRT
from comfyui.
advanced users can try my node: https://github.com/phineas-pta/comfy-trt-test
from comfyui.
I just tested Nvidia's A1111 TRT extension and results are 2x faster indeed (at least for 512x768 simple generation).
from comfyui.
There was a pull for automatic that references the limits of TRT.
AUTOMATIC1111/stable-diffusion-webui-tensorrt#36
There is an upper limit of what it can do. As an example, if you have your batch size set to 8, you may not be able to generate dynamic images greater than 512x480 and the like.
I took note of some issues I've found during the year of TRT implementations flooding GitHub.
AUTOMATIC1111/stable-diffusion-webui-tensorrt#46 (comment)
Max dimensions I got from the calculated limit is Batch size 1, 858 x 858.
from comfyui.
Be prepared to pull your hair out if you get to it. Getting it setup on one machine is a chore, but getting it to work on someone else's is worse. Many TensorRT implementations have fallen because of it. Volta-ML and SDA-node are the larger examples.
from comfyui.
I would love to see tensorrt support, because SD XL is quite slow.
Also, tensorrt only seems to support max 768x768px. Do you think it is somehow possible to pass the SDXL 1024 in?
from comfyui.
Yeah I'm going to go with AITemplate instead of TRT unless they add a way to replace the weights at runtime.
from comfyui.
Yeah AiTemplate seems good too.
from comfyui.
yeah its there! any idea how make it work in comfyui
from comfyui.
from comfyui.
Aaaand new drivers just dropped promising 2X performance boost with TRT https://www.nvidia.com/en-us/geforce/news/game-ready-driver-dlss-3-naraka-vermintide-rtx-vsr/
and with that I'd love to see the fruits of this 2x speed boost as that could greatly improve my workflow on my 3090.
from comfyui.
Ok so how do i translate that support instructions for auto1111 to compfy. As I was using auto1111 but I was getting issues creating and using the optimized versions
from comfyui.
Related Issues (20)
- add tag and branch while upgrade ComfyUI HOT 1
- keyerror due to missing nodes are not reported in the websocket api
- inpaint sketch in comfyui HOT 1
- Error: Transport Endpoint not Connected - Can't Run ComfyUI in Colab
- PatchModelAddDownscale(Kohya Deep Shrink) + ControlNet = warning control could not be applied
- how ot use FlashAttention (flash-attn) in comfyui HOT 1
- Sugguest allow to add description at node params
- Sam Detector from Load Image doesn't have a CPU only option HOT 2
- Out of memory condition on 8 gig GPUs in SDXL outputing 16 x 9 picture in high resolution
- AssertionError: Torch not compiled with CUDA enabled HOT 1
- Add stable diffusion 3 / MMDiT based model support HOT 2
- [ERROR] RuntimeError: CUDA error: the launch timed out and was terminated (Driving me nuts) HOT 1
- KeyError: 'VideoTriangleCFGGuidance' HOT 2
- Getting error as of 24 hours ago: Error starting the server: startup_server() missing 1 required positional argument: 'port' HOT 23
- ImageSharpen is broken on macOS due to a commit a week ago HOT 1
- The generation is "running on another tab" but it isn't
- CUDA error: operation not supported
- showing blanck screen
- API web socket hangs? HOT 1
- Ask for help: TLS/SSL question, failed to startup with the arg --tls-keyfile key.pem --tls-certfile cert.pem HOT 2
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from comfyui.