zer0int

PrivacyBackdoor

Privacy backdoors

open_clip

An open source implementation of CLIP.

huggingface_guess

A simple tool to guess an HuggingFace repo URL from a state dict.

clip-guided-diffusion

CLIP Guided Diffusion

ImplicitBiasAdversarial

Code for the paper "Relating Implicit Bias and Adversarial Attacks through Intrinsic Dimension" [https://arxiv.org/abs/2305.15203]

second_order_lens

Official pytorch implementation of "Interpreting the Second-Order Effects of Neurons in CLIP"

ComfyUI-Custom-Scripts

Enhancements & experiments for ComfyUI, mostly focusing on UI features

CLIP-fine-tune-Adjustment

Fine-tuning code for CLIP models

OutEffHop

[ICML 2024] Outlier-Efficient Hopfield Layers for Large Transformer-Based Models

CLIP_benchmark

CLIP-like model evaluation

SimpleTuner

A general fine-tuning kit geared toward diffusion models.

Omost

Your image is almost there!

clip_text_span

official implementation of "Interpreting CLIP's Image Representation via Text-Based Decomposition"

disentangling_spelling_in_clip

geometric-parameterization

Official TensorFlow 2 Implementation of Geometric Parameterization from ReLU Characteristic Activation Analysis

magikarp

github2file

ComfyUI-Long-CLIP

ComfyUI implementation of Long-CLIP

Long-CLIP

[ECCV 2024] official code for "Long-CLIP: Unlocking the Long-Text Capability of CLIP"

SPRIGHT

[ECCV 2024] Official PyTorch implementation of "Getting it Right: Improving Spatial Consistency in Text-to-Image Models"

ExeIntegrityBypassAgainstRGL

A Version Check Bypass ASI for Grand Theft Auto V for older versions that use Rockstar Games Launcher

GenDataAttribution

Evaluating Data Attribution for Text-to-Image Models: a visual data attribution benchmark for evaluating and learning training image influences.

multimodal-maestro

Effective prompting for Large Multimodal Models like GPT-4 Vision, LLaVA or CogVLM. 🔥

text2image_safety

3DGPT