Real-ESRGAN
PyTorch implementation of Real-ESRGAN model (by ai-forever)
onnx-web
web UI for GPU-accelerated ONNX pipelines like Stable Diffusion, even on Windows and AMD (by ssube)
Real-ESRGAN | onnx-web | |
---|---|---|
3 | 8 | |
402 | 179 | |
3.2% | - | |
0.0 | 9.7 | |
27 days ago | 5 days ago | |
Python | Python | |
BSD 3-clause "New" or "Revised" License | MIT License |
The number of mentions indicates the total number of mentions that we've tracked plus the number of user suggested alternatives.
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
Real-ESRGAN
Posts with mentions or reviews of Real-ESRGAN.
We have used some of these posts to build our list of alternatives
and similar projects. The last one was on 2021-11-07.
-
Retrained Real-ESRGAN version used by ruDALL-E (a text-to-image AI) may be of interest
I noticed that the 256x256 -> 1024x1024 upscalings used by the ruDALL-E (text-to-image AI) demo site looked more detailed than other upscalers I've used. It apparently uses a retrained Real-ESRGAN. Here is a comparison I did of 2 synthetic images upscaled with this and 2 other upscalers. The GitHub repos are here and here. A web app version is here.
-
"a dog in a sweater. no watermark." (4 images) generated by CogView 2. ~256x256 cropped screenshot upscaled 4x with Real-ESRGAN from ruDALL-E demo.
I used this Colab for the upscaling. GitHub repo for the upscaler.
-
Real-ESRGAN (an upscaler) implementation used by ruDALL-E demo seems to create a lot more fine details than the other implementation of Real-ESRGAN that I used. Gallery contains upscaler comparisons for 2 input images. An implementation of SwinIR upscaler is also included.
Colab for Real-ESRGAN used by ruDALL-E demo. GitHub repo.
onnx-web
Posts with mentions or reviews of onnx-web.
We have used some of these posts to build our list of alternatives
and similar projects. The last one was on 2023-04-23.
- I hope that by A1111 is everything fine. Best wishes for great man! In mean time lets, develope Vlad fork
-
AMD ROCm Comes To Windows On Consumer GPUs
ONNX uses DirectML on Windows, at least for now, yeah. It can be very difficult to convince it to release VRAM, and even unloading the models on the Python side does not always work. https://github.com/ssube/onnx-web/issues/242 has an example. There was also a more severe memory leak, which has since been fixed, that only affected models > 2GB.
-
another UI for Stable Diffusion for Windows and AMD, now with LoRA and Textual Inversions
Thanks for reporting #1, I wrote up a bug and will fix that for the next bundle: https://github.com/ssube/onnx-web/issues/315
What are some alternatives?
When comparing Real-ESRGAN and onnx-web you can also consider the following projects:
Real-ESRGAN-colab - A Real-ESRGAN model trained on a custom dataset
ComfyUI-to-Python-Extension - A powerful tool that translates ComfyUI workflows into executable Python code.