Comments (4)
Yes, the current logic selects engines on
- How close is the requested resolution to the optimal resolution of an engine
- If multiple engines have the same score, select the one with the least VRAM consumption.
from stable-diffusion-webui-tensorrt.
I've created multiple Profile for a SD 1.5, but when I change the resolution to match another profile, in the console I still see it take the Profile 0.
How can I switch between profile?
I have a 4090 video card with latest drivers (545.84)
The first picture asked, was batch 4, 512x512, 1 word in positive prompt
And in the 2 picture asked, same as 1 but with an upscale to x2 that lead to a 1024x1024 that should have take my profile 3:
Loading TensorRT engine: F:\IMAGES\AIgenerated\SDXL 1.6\stable-diffusion-webui\models\Unet-trt\photon_v1_d902a082_cc89_sample=1x4x64x64+2x4x64x64+8x4x96x96-timesteps=1+2+8-encoder_hidden_states=1x77x768+2x77x768+8x154x768.trt
[I] Loading bytes from F:\IMAGES\AIgenerated\SDXL 1.6\stable-diffusion-webui\models\Unet-trt\photon_v1_d902a082_cc89_sample=1x4x64x64+2x4x64x64+8x4x96x96-timesteps=1+2+8-encoder_hidden_states=1x77x768+2x77x768+8x154x768.trt
Profile 0:
sample = [(1, 4, 64, 64), (2, 4, 64, 64), (8, 4, 96, 96)]
timesteps = [(1,), (2,), (8,)]
encoder_hidden_states = [(1, 77, 768), (2, 77, 768), (8, 154, 768)]
latent = [(-1945914624), (-1945909504), (-1945910272)]
100%|█████████████████████████████████████████████████████████████████████████████████| 20/20 [00:04<00:00, 4.79it/s]
Total progress: 100%|█████████████████████████████████████████████████████████████████| 20/20 [00:01<00:00, 10.12it/s]
100%|█████████████████████████████████████████████████████████████████████████████████| 20/20 [00:01<00:00, 13.27it/s]
Total progress: 100%|█████████████████████████████████████████████████████████████████| 20/20 [00:02<00:00, 9.66it/s]
100%|█████████████████████████████████████████████████████████████████████████████████| 20/20 [00:01<00:00, 12.42it/s]
0%| | 0/20 [00:00<?, ?it/s]Loading TensorRT engine: F:\IMAGES\AIgenerated\SDXL 1.6\stable-diffusion-webui\models\Unet-trt\photon_v1_d902a082_cc89_sample=1x4x64x64+2x4x128x128+8x4x128x128-timesteps=1+2+8-encoder_hidden_states=1x77x768+2x77x768+8x154x768.trt
[I] Loading bytes from F:\IMAGES\AIgenerated\SDXL 1.6\stable-diffusion-webui\models\Unet-trt\photon_v1_d902a082_cc89_sample=1x4x64x64+2x4x128x128+8x4x128x128-timesteps=1+2+8-encoder_hidden_states=1x77x768+2x77x768+8x154x768.trt
Profile 0:
sample = [(1, 4, 64, 64), (2, 4, 128, 128), (8, 4, 128, 128)]
timesteps = [(1,), (2,), (8,)]
encoder_hidden_states = [(1, 77, 768), (2, 77, 768), (8, 154, 768)]
latent = [(-1945966336), (-1945972992), (-1945967872)]
100%|█████████████████████████████████████████████████████████████████████████████████| 20/20 [00:14<00:00, 1.41it/s]
Total progress: 100%|█████████████████████████████████████████████████████████████████| 40/40 [00:23<00:00, 1.69it/s]
Total progress: 100%|█████████████████████████████████████████████████████████████████| 40/40 [00:23<00:00, 1.76it/s]
from stable-diffusion-webui-tensorrt.
Thanks for the clarification, If the extension automatically changes the optimal resolution, is it possible to add the ability to set multiple resolutions and generate them at once when using the 'Export Engine'? I think that would be really useful.
from stable-diffusion-webui-tensorrt.
This has been asked in #60 as well. Currently, there is no support to export multiple checkpoints or profiles at once.
from stable-diffusion-webui-tensorrt.
Related Issues (20)
- TensorRT gives a Runtime Error when Positive prompt value is 150 and Negative prompt value is 75.
- Does tensorRT support direct use of apis, and what are the parameters? HOT 1
- how to generate json config file in the LoRA tab. HOT 1
- [branch: Controlnet_V2] ONNX IR model version conflict, how do i downgrade?
- [E] 3: getPluginCreator could not find plugin: InstanceNormalization_TRT version: 1 when building engine with latest TRT_VERSION="10.0.0b6"
- No config file found for You can generate it in the LoRA tab. HOT 3
- Advise to add promt token check in warning report
- [Feature Request] Add a Command Line Interface for the exporter process.
- AttributeError: 'tensorrt_bindings.tensorrt.ICudaEngine' object has no attribute 'get_profile_shape' HOT 2
- How to process a batch of images with ControlNet TensorRT in img2img ?
- Latest version of automatic1111 wont start with this extension installed. HOT 2
- AttributeError: 'NoneType' object has no attribute 'device_memory' HOT 12
- Error Code 3: API Usage Error (Parameter check failed
- Export LoRA to onnx depending on cyberrealistic_v31 can't fit to v1-5-pruned-emaonly_cnet_1846e6c3c239531e.trt
- TensorRT doesn't install on fresh A1111 install on Ubuntu, stuck at install after copy/paste de git link HOT 10
- TensorRT doesn't find Loras from subdirectories HOT 2
- TensorTR extension is building engine with wrong parameters
- may a name mistake in beta version (utilities.py)
- Engines not loading with text size larger than 75 HOT 1
- SD3 TensoRRT (sd3-clip-t5xxlfp8) works perfectly but cannot get SDXL ... HOT 1
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 stable-diffusion-webui-tensorrt.