contrebande-labs / charred
CHARacter-awaRE Diffusion: Multilingual Character-Aware Encoders for Font-Aware Diffusers That Can Actually Spell
☆14Updated last year
Alternatives and similar repositories for charred:
Users that are interested in charred are comparing it to the libraries listed below
- Unified API to facilitate usage of pre-trained "perceptor" models, a la CLIP☆39Updated 2 years ago
- Finetune the 1.4B latent diffusion text2img-large checkpoint from CompVis using deepspeed. (work-in-progress)☆36Updated 3 years ago
- Load any clip model with a standardized interface☆21Updated last year
- CLOOB training (JAX) and inference (JAX and PyTorch)☆71Updated 2 years ago
- Contains my experiments with the `big_vision` repo to train ViTs on ImageNet-1k.☆22Updated 2 years ago
- Training simple models to predict CLIP image embeddings from text embeddings, and vice versa.☆60Updated 3 years ago
- Describe the format of image/text datasets☆11Updated 3 years ago
- Script and models for clustering LAION-400m CLIP embeddings.☆26Updated 3 years ago
- A CLIP conditioned Decision Transformer.☆22Updated 3 years ago
- Pixel Parsing. A reproduction of OCR-free end-to-end document understanding models with open data☆21Updated 9 months ago
- Updated last year
- ☆30Updated 3 years ago
- ☆28Updated 3 years ago
- ☆24Updated last year
- DALLE-tools provided useful dataset utilities to improve you workflow with WebDatasets.☆15Updated 3 years ago
- Contrastive Language-Image Pretraining☆38Updated 9 months ago
- ☆29Updated 2 years ago
- ☆33Updated 7 months ago
- QAmeleon introduces synthetic multilingual QA data using PaLM, a 540B large language model. This dataset was generated by prompt tuning P…☆34Updated last year
- LoRA fine-tuned Stable Diffusion Deployment☆31Updated 2 years ago
- ☆37Updated last year
- A dashboard for exploring timm learning rate schedulers☆19Updated 5 months ago
- Experimental scripts for researching data adaptive learning rate scheduling.☆23Updated last year
- ☆28Updated 9 months ago
- A minimal TPU compatible Jax implementation of NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis.☆13Updated 3 years ago
- Implementation of Token Shift GPT - An autoregressive model that solely relies on shifting the sequence space for mixing☆48Updated 3 years ago
- Generate images from texts. In Russian☆19Updated 3 years ago
- ☆33Updated 6 months ago
- Train vision models using JAX and 🤗 transformers☆97Updated 3 weeks ago
- Another attempt at a long-context / efficient transformer by me☆37Updated 3 years ago