carefree0910
Joined 4 years ago
Karma
135
Submissions
27
Member since
Oct 7
Recent submissions
Comment · 3 years ago
Comment · 4 years ago
Of course! I will be more than happy to hear real demands!
Comment · 4 years ago
Hi, thank you so much for the valuable advice and information!
If I didn't get you wrong, maybe another project (carefree-learn) meets your needs better: https://github.com/carefree0910/carefree-learn.
This is an old project, with a VERY outdated document, but all the features of carefree-creator can be achieved with one or few lines of code from carefree-learn.
Take the typical text to image feature as an example, here's a piece of minimal-working-codes:
```python
import torch, cflearn
api = cflearn.cv.DiffusionAPI.from_sd("cuda:0", use_half=True)
api.txt2img("a beautiful, fantasy landscape", "out.png") # this will save the generated image to `out.png`
```
And you can install it with `pip install carefree-learn[cv]` XD.
Comment · 4 years ago
Yes indeed, my poor cloud server burnt down just now... But I fixed it so it should be OK now!
Comment · 4 years ago
Coooool! And yes, I'm not sure whether the models can run on the m1 chip, but I think this is more of a PyTorch issue instead of this project XD.
Comment · 4 years ago
Guess what, I'm actually using the runway inpainting model as the backend of the `Erase & Replace` feature XD!
Comment · 4 years ago
Thank you so much for your patience! You experience will definitely help me make this project compatible to the m1 chip systems XD!
And since ONNX is not a forced requirement, maybe the following guides can make things easier:
1. Install `carefree-learn` instead of `carefree-learn[cv]`
2. Install the following packages manually:
ftfy regex lmdb albumentations carefree-cv
> I'll consider removing the `onnx` requirements from the `cv` spec in the near future!
Comment · 4 years ago
That's a ton of great suggestions! I'll try to digest them and use them to guide my future works!
And for your requirement, actually carefree-creator is built to be a stand-alone backend server, so you can indeed customize your own frontend if you like, as I mentioned here (the first point): https://github.com/carefree0910/carefree-creator/issues/11#i...
And if you are interested in customizing carefree-creator itself (like integrating your fancy model into it), I haven't written any documentation yet, but here are some brief guides: https://github.com/carefree0910/carefree-creator/issues/8#is...
Feel free to contact me if you encountered any trouble!
Comment · 4 years ago
I haven't tested on m1 macbook yet, but the Docker solution should be OK...
Here's the onnx-simplifier project: https://pypi.org/project/onnx-simplifier/, looks like it already goes to 0.4.8.
I'll try to reproduce the error, before that maybe you can try the Google Colab solution:
https://colab.research.google.com/github/carefree0910/carefr...
Comment · 4 years ago
It is not designed to generate pixel art, but you can try something like:
a lovely little cat, pixel art.
It will generate something weird, but (maybe) the quality of the generated image will be better with some tweaks!
Comment · 4 years ago
Oh, that looks like a bug... Could you please share the `fidelity` property of your `img2img` process, or share the `AI Parameters` on the right (after you select the generated image) (there should be a little `copy` icon) here? Thanks!
Comment · 4 years ago
I'm so glad that you like it!
Currently the UX is not perfect, and I'll definitely try my best to improve it XD.
Looking forward to your advice and feedbacks!
Comment · 4 years ago
Wow, I'm so glad that you like it so much!
Just as you said, I'm trying to make it a studio-ish product which combines various AI magics, so they can work together and create something that a single AI model can hardly achieve.
Here's my future plan: I'm going to integrate natural language generation, music generation, video generation... Into this project, so you can make something really cool with and only with AI!
And the most important part: it will always be completely open source and free, and (maybe) a Google Colab is enough to serve all these stuffs XD.
Comment · 4 years ago
And BTW, you don't need an account to use this project if I fixed the bug / you visit it on PC!
`carefree-drawboard` made assumptions that:
* It is a painful process to spend time thinking and designing the layout of various UIs.
* Most user interactions can be abstracted into "send something to server" & "receive something to server".
* A completely decoupled system is what we dreamed of, because it can be easily customized, extended and maintained.
* An infinite drawboard is capable of building (almost) all the desired applications.
So, we derived the following design principles:
* Everything is a plugin on an infinite drawboard.
* Plugin Styles should be fully declarative and should contain a smart layout system (which should also be declarative).
* Plugin Logics should only have access to the data from:
> Itself (e.g., some input fields declared by the Styles).
> The selecting Node(s).
Under these principles, no matter what programming languages (even JSON, if your plugins contain no logics) you are using, you can easily extend the functionality of `carefree-drawboard` by writing plugins.
And since:
* We love Python.
So (currently) we provide a python binding, the `cfdraw` package, for you to write plugins (both styles and logics) using Python. However, theoretically speaking, any backend programming languages are able to write plugins that work with `carefree-drawboard`. I've already wrote a brief introduction in the wiki page about this topic, if you are really interested, please check it out and send feedbacks to me!