Comments (4)
I will try decrease the sampling steps, undoubtedly, this will accelerate inference,
but to ensure the final SR effect, this may not be the preferred solution,
as for distributed inference, currently I only have one A100 server.
This is the SR method that I have seen that can support any input size、any upscale、suitable for images such as wild and AIGC, and has almost the best effect.
Thanks again for your amazing work. I will continue to pay attention to this issue.
from stablesr.
Hi, thanks for your interest.
Large-resolution results require huge GPU memory since for sr_val_ddpm_text_T_vqganfin_oldcanvas.py
, it decodes the whole latent codes together for the final outputs. This can avoid border artifacts but 32G memory only can host 2k resolution at most.
For your case, you just need to turn to use sr_val_ddpm_text_T_vqganfin_oldcanvas_tile.py
which use the chop operation to generate image part by part for memory saving, but may lead to border artifacts. Actually, we also use this file for generating the SR result of this image.
from stablesr.
Yes
when I switch to use sr_val_ddpm_text_T_vqganfin_oldcanvas_tile.py,I got the expected output, it was perfect,and almost no boundary artifacts can be seen!!
Although I don't have many test cases, I believe that using this script can yield reasonable super-resolution results in the vast majority of cases, with almost no boundary artifacts
The only problem now is that the inference time is too long. The 4K example above took more than an hour in total,is there any optimization space in the inference time, or if I mistake used your script?
look forward to your reply
from stablesr.
The inference time can be very long for large resolutions and sometimes we observe boundary artifacts, it depends on the content.
Currently, we have not involved any inference acceleration.
I used to try DDIM but it leads to weird results so I gave up. But other accelerated technologies may work.
Under the current case, I think you can decrease the sampling steps. It is 200 by default but reduce it to 50 or even 20 sometimes can also lead to relatively good results, though some details tend to be a little blurry compared with the default settings. This is expected for diffusion models.
BTW, another thing you can try if you are interested is to add multi-GPU support. Although the batch size is 1, since we divide the image into multiple tiles, it is still possible to deal with them separately. Just make sure they are under the same seed.
from stablesr.
Related Issues (20)
- Increasing Batch Size using Multiple GPUs HOT 1
- Socket problem HOT 2
- Ask about feature maps modulation HOT 1
- Question about testing data HOT 1
- Question on no FID Results for RealSR and DRealSR in Paper. HOT 2
- The Practicability of ComfyUI Integration HOT 1
- DPED-iphone dataset HOT 1
- DDIM inference eta HOT 1
- missing code HOT 3
- 4x upscale is fine but 2x upsacle poor with my own finetuned model HOT 1
- How long does it take to generate training data? HOT 1
- During the model training process, the degraded images in the training set were restored to the ink style. HOT 1
- what is the command to run the upscaler on colab HOT 2
- ---
- Question about Test FaceSR HOT 4
- is "python main.py --train --base configs/stableSRNew/v2-finetune_text_T_512.yaml --gpus GPU_ID, --name NAME --scale_lr False" still runable? HOT 6
- AttributeError: module 'ldm.models.diffusion.ddpm' has no attribute 'LatentDiffusionSRTextWT' HOT 3
- How to inference with batch size >1? HOT 2
- StableSR v.s. Stable Diffusion x4 Upscaler HOT 1
- I can't find output picture 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 stablesr.