ViTs-vs-CNNs
DALLE2-pytorch
| ViTs-vs-CNNs | DALLE2-pytorch | |
|---|---|---|
| 1 | 65 | |
| 173 | 10,916 | |
| - | - | |
| 0.0 | 4.3 | |
| over 2 years ago | 28 days ago | |
| Python | Python | |
| - | MIT License |
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.
ViTs-vs-CNNs
DALLE2-pytorch
-
One year ago I got access to closed beta DALL-E 2.
I was showing people Dalle2 last year and telling them how much of an impact an open source solution was going to have on, well, everything to do with art and design. (At the time Stable Diffusion had not released, not even the leak, and all hopes was on https://github.com/lucidrains/DALLE2-pytorch)
- [Machinelearning] [D] Quelqu'un travaille-t-il sur l'open-sourcing de Dall-E 2 ?
-
AMA (Emad here hello)
Stable diffusion is the model, MJ will use a variant and DALL-E is the old version (we have our own implementation from our distinguished fellow Lucidrains here: https://github.com/lucidrains/DALLE2-pytorch)
-
An impressionist painting of an floating raccoon god, 4k, digital painting, trending on artstation
Sadly I don't think so. From what I understand the architecture is fixed to 1024x1024 pictures.
- I asked AI to turn P&R characters into muppets..
-
Comparison of AI text-to-image generators
The code is open source, the model is not I believe. https://github.com/lucidrains/DALLE2-pytorch
- Protests erupt outside of DALL-E offices after pricing implementation, press photograph
-
$15 for 115 “generation increments” Very expensive Beta pricing announcement. Dissapointed
Phil Wang has been fairly prolific at creating open source implementations of these text to image models. For example, here is the dalle-2 repo https://github.com/lucidrains/DALLE2-pytorch
-
DALL·E Now Available in Beta
There's already an open-source implementation of DALL-E 2 (https://github.com/lucidrains/DALLE2-pytorch) and a pretrained model for it should be released within this year.
Also true for Google's Imagen, which should be even better than DALLE-2 (and faster) https://github.com/lucidrains/imagen-pytorch.
This is possible because the original research papers behind both DALLE-2 and Imagen were publicly released.
-
would love to know what portion of this prompt is not allowed
The paper describing the model is public and has been implemented here, but that's not the hard part. The model likely requires months of compute and dozens of gigabytes of VRAM to train and run, likely costing several hundred thousand dollars.
What are some alternatives?
safe-control-gym - PyBullet CartPole and Quadrotor environments—with CasADi symbolic a priori dynamics—for learning-based control and RL
dalle-mini - DALL·E Mini - Generate images from a text prompt
disco-diffusion
DALLE-pytorch - Implementation / replication of DALL-E, OpenAI's Text to Image Transformer, in Pytorch
DALL-E - PyTorch package for the discrete VAE used for DALL·E.
dalle-2-preview
latent-diffusion - High-Resolution Image Synthesis with Latent Diffusion Models
imagen-pytorch - Implementation of Imagen, Google's Text-to-Image Neural Network, in Pytorch
CLIP - CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image
dalle2-laion - Pretrained Dalle2 from laion
v-diffusion-jax - v objective diffusion inference code for JAX.
VQGAN-CLIP - Just playing with getting VQGAN+CLIP running locally, rather than having to use colab.