nostalgebraist / improved-diffusionLinks
Text-writing denoising diffusion (and much more)
☆30Updated 2 years ago
Alternatives and similar repositories for improved-diffusion
Users that are interested in improved-diffusion are comparing it to the libraries listed below
Sorting:
- Training simple models to predict CLIP image embeddings from text embeddings, and vice versa.☆60Updated 3 years ago
- CLOOB training (JAX) and inference (JAX and PyTorch)☆74Updated 3 years ago
- Unified API to facilitate usage of pre-trained "perceptor" models, a la CLIP☆39Updated 2 years ago
- A JAX implementation of the continuous time formulation of Consistency Models☆84Updated 2 years ago
- This contains the Flax model of min(DALL·E) and code for converting it to PyTorch☆44Updated 3 years ago
- A client library for LAION's effort to filter CommonCrawl with CLIP, building a large scale image-text dataset.☆31Updated 2 years ago
- ☆30Updated 3 years ago
- Hidden Engrams: Long Term Memory for Transformer Model Inference☆35Updated 4 years ago
- Latent Diffusion Language Models☆68Updated 2 years ago
- CLOOB Conditioned Latent Diffusion training and inference code☆111Updated 3 years ago
- ESGD-M is a stochastic non-convex second order optimizer, suitable for training deep learning models, for PyTorch.☆56Updated 3 years ago
- ☆89Updated 3 years ago
- Finetune the 1.4B latent diffusion text2img-large checkpoint from CompVis using deepspeed. (work-in-progress)☆36Updated 3 years ago
- Aim for the moon. If you miss, you may hit a star.☆163Updated 2 years ago
- Majesty Diffusion by @Dango233 and @apolinario (@multimodalart)☆25Updated 3 years ago
- High-Resolution Image Synthesis with Latent Diffusion Models☆60Updated 3 years ago
- Implementation / replication of DALL-E, OpenAI's Text to Image Transformer, in Pytorch☆88Updated 3 years ago
- ☆28Updated 3 years ago
- ☆63Updated 3 years ago
- Script and models for clustering LAION-400m CLIP embeddings.☆26Updated 3 years ago
- ☆19Updated 4 years ago
- ☆56Updated 3 years ago
- Pedagogical codebase for a simplified score-based generative model design, with training loop☆40Updated 4 years ago
- Train vision models using JAX and 🤗 transformers☆99Updated last month
- checkpoints for glide finetuned on laion and other datasets. wip.☆50Updated 3 years ago
- ☆22Updated 3 years ago
- RWKV-v2-RNN trained on the Pile. See https://github.com/BlinkDL/RWKV-LM for details.☆66Updated 3 years ago
- DiCE: The Infinitely Differentiable Monte-Carlo Estimator☆31Updated 2 years ago
- One stop shop for all things carp☆59Updated 3 years ago
- Discord AI Generation Bot to collect an aesthetic rating dataset☆57Updated 2 years ago