StyleGAN-nada | prompt-to-prompt | |
---|---|---|
14 | 18 | |
1,141 | 2,860 | |
- | 2.1% | |
0.0 | 3.7 | |
over 1 year ago | 3 months ago | |
Python | Jupyter Notebook | |
MIT License | Apache License 2.0 |
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.
StyleGAN-nada
-
Artists Tomorrow
Here's a paper about adding the ability to guide outputs with text a full year before Stable Diffusion was published.
-
StyleGAN-NADA: CLIP-Guided Domain Adaptation of Image Generators
StyleGAN-NADA: CLIP-Guided Domain Adaptation of Image Generators
-
[R][P] Gradio Web demo for StyleGAN-NADA: CLIP-Guided Domain Adaptation of Image Generators (SIGGRAPH 2022)
project page: https://stylegan-nada.github.io/
-
The Danny AI of your dreams
Sooo I retrained the FFHQ model to be Danny using StyleGAN-NADA via this Colab notebook.
-
I made a VFX face filter thing that might be of interest to you guys (it runs in the browser without sending anything to a server and is quite fast)
Haha thanks for trying it out :) It was actually really challenging to get it working (especially all in the browser without processing on a server). A lot of help came from stylegan-nada https://github.com/rinongal/StyleGAN-nada (and a custom lightweight model basically distilling pairs from it and ffhq).
-
[D] StyleGAN3: Overview, Tutorial, and Pre-Trained Model
As for usage on non-face images most of NVidia's pre-trained models were face based (animal, humans, and paintings). Which was the aim of releasing our WikiArt model so the community would have something that could generate a greater variety of images. However these models are still constrained to the dataset that they were trained on. So without some tricks you can't generate "novel" images (like mashups of different objects)
-
[D] What are some cool projects for generating art?
I think the directional loss concepts in https://github.com/rinongal/StyleGAN-nada have real potential for artistic work, as they can go beyond the filter and paint effects that traditional style transfer applies well, while maintaining recognisable equivalency between the resulting images.
-
[R] NVIDIA and Tel Aviv Researchers Propose ‘StyleGAN-NADA’, A Text-Driven Method That Converts a Pre-Trained AI Generator to New Domains Using Only a Textual Prompt and No Training Data
5 Min Read | Paper | Project | Code
- Arquitectura colonial Argentina (Generado por IA)
- StyleGAN-NADA: Clip-Guided Domain Adaptation of Image Generators
prompt-to-prompt
- Has google prompt-to-prompt / Cross Attention Control ever been implemented as a plugin for ComfyUI or Automatic1111?
-
[D] CFG role in diffusion vs autoregressive transformers
Found relevant code at https://github.com/google/prompt-to-prompt + all code implementations here
-
Auto1111 Fork with pix2pix
Null text inversion produces almost a perfect textual inversion, and then allows you to edit it with a prompt, like instruct2pix. https://github.com/google/prompt-to-prompt
- Are there ways to use img2img without manually inpainting the clothes of a person I order to change the type of clothing or color of it, etc. I saw a few people here who were able to detect clothing automatically, any advice is welcome 🙏🏼
-
Artists Tomorrow
First we had Google's prompt to prompt https://github.com/google/prompt-to-prompt
-
Backgrounds HATE me?
Narratives can also work, like "walking down forest path". However, it'll be difficult to keep the character positioned the way you want with that. If you're a techie somewhat, you can try to use https://github.com/google/prompt-to-prompt to generate someone you like and then see if you can get a better background without changing the character.
- Anybody here looked into and wanna share the major deviations (if any) between Google's implementation of prompt2prompt vs Doggettx's implementation (which was included in Automatic1111's repo as "Prompt Editing" feature)?
- I did not expect it, but that's the reality now
- Prompt-to-Prompt: Latent Diffusion and Stable Diffusion Implementation
-
[R] can diffusion model be used for domain adaptation?
Google has a nice paper on text-guided image2image translation by inferring the (random) init image and changing the prompt: https://github.com/google/prompt-to-prompt
What are some alternatives?
awesome-pretrained-stylegan3 - A collection of pretrained models for StyleGAN3
jukebox - Code for the paper "Jukebox: A Generative Model for Music"
artistic-videos - Torch implementation for the paper "Artistic style transfer for videos"
cycle-diffusion - [ICCV 2023] A latent space for stochastic diffusion models
neural-style-pt - PyTorch implementation of neural style transfer algorithm
stable-diffusion-webui - Stable Diffusion web UI
stylegan3 - Official PyTorch implementation of StyleGAN3
stylegan2-pytorch - Simplest working implementation of Stylegan2, state of the art generative adversarial network, in Pytorch. Enabling everyone to experience disentanglement
stylegan3-fun - Modifications of the official PyTorch implementation of StyleGAN3. Let's easily generate images and videos with StyleGAN2/2-ADA/3!
stable-diffusion-webui-pix2pix - Stable Diffusion web UI
deep-photo-styletransfer - Code and data for paper "Deep Photo Style Transfer": https://arxiv.org/abs/1703.07511
latentblending - Create butter-smooth transitions between prompts, powered by stable diffusion