Pinned Repositories
CLIP-Direct-Ascent-Synthesis
Like a CLIP + VQGAN. Except without a VQGAN.
CLIP-fine-tune
Fine-tuning code for CLIP models
CLIP-fine-tune-registers-gated
Vision Transformers Needs Registers. And Gated MLPs. And +20M params. Tiny modality gap ensues!
CLIP-Interrogator-LongCLIP-hallucinwords
CLIP Interrogator, fully in HuggingFace Transformers 🤗, with LongCLIP & CLIP's own words and / or *your* own words!
CLIP-ViT-visualization
What do CLIP Vision Transformers learn? Feature Visualization can show you!
CLIP-XAI-GUI
CLIP GUI - XAI app ~ explainable (and guessable) AI with ViT & ResNet models
ComfyUI-HunyuanVideo-Nyan
Text Encoders finally matter 🤖🎥 - scale CLIP & LLM influence! + a Nerdy Transformer Shuffle node
ComfyUI-Long-CLIP
ComfyUI implementation of Long-CLIP, including Flux node: LongCLIPTextEncodeFlux
ComfyUI-Nuke-a-Text-Encoder
For SDXL, SD1.5, Flux. Nuke T5 and let CLIP guide Flux.1 on its own! Or let let random guide Flux.1! Or load a CLIP crazy opinion embedding about your image and let that guide the AI!
Long-CLIP
Scripts for use with LongCLIP, including fine-tuning Long-CLIP
zer0int's Repositories
zer0int/CLIP-fine-tune
Fine-tuning code for CLIP models
zer0int/ComfyUI-HunyuanVideo-Nyan
Text Encoders finally matter 🤖🎥 - scale CLIP & LLM influence! + a Nerdy Transformer Shuffle node
zer0int/Long-CLIP
Scripts for use with LongCLIP, including fine-tuning Long-CLIP
zer0int/ComfyUI-Long-CLIP
ComfyUI implementation of Long-CLIP, including Flux node: LongCLIPTextEncodeFlux
zer0int/CLIP-fine-tune-registers-gated
Vision Transformers Needs Registers. And Gated MLPs. And +20M params. Tiny modality gap ensues!
zer0int/ComfyUI-Nuke-a-Text-Encoder
For SDXL, SD1.5, Flux. Nuke T5 and let CLIP guide Flux.1 on its own! Or let let random guide Flux.1! Or load a CLIP crazy opinion embedding about your image and let that guide the AI!
zer0int/CLIP-XAI-GUI
CLIP GUI - XAI app ~ explainable (and guessable) AI with ViT & ResNet models
zer0int/CLIP-Interrogator-LongCLIP-hallucinwords
CLIP Interrogator, fully in HuggingFace Transformers 🤗, with LongCLIP & CLIP's own words and / or *your* own words!
zer0int/CLIP-SAE-finetune
Sparse Autoencoders (SAE) vs CLIP fine-tuning fun.
zer0int/CLIP-ViT-visualization
What do CLIP Vision Transformers learn? Feature Visualization can show you!
zer0int/CLIP-txt2img-diffusers-scripts
Example scripts for using [my] fine-tuned CLIP models with HuggingFace 🤗
zer0int/ComfyUI-LLama3-Layer-Shuffle-Prompting
Shuffle LLama-3.2 layers and have it prompt an image. Node works with any model - Flux, SD3, SDXL...
zer0int/ComfyUI-CLIP-Flux-Layer-Shuffle
Comfy Nodes (and a CLI script) for shuffling around layers in transformer models, creating a curious confusion.
zer0int/CLIP-Direct-Ascent-Synthesis
Like a CLIP + VQGAN. Except without a VQGAN.
zer0int/CLIP-gradient-ascent-embeddings
Use CLIP to create matching texts + embeddings for given images; useful for XAI, adversarial training
zer0int/ComfyUI-GPT2-Layer-Shuffle-Prompting
Shuffle GPT-2's layers and have it prompt an image. Node works with any model - Flux, SD3, SDXL...
zer0int/CLIP-DeepDream
Deep Dreaming with CLIP Vision Transformers
zer0int/CLIP-Layer-Deck-Shuffle
Experimental removal / shuffling of layers in CLIP ViT + Text Transformer
zer0int/CLIP-tokenizer
A simple CLIP tokenizer encode / decode script. For when you need to know CLIP's tokenization and / or token IDs for some reason.
zer0int/CLIPInversion
What do we learn from inverting CLIP models? And what does a CLIP 'see' in an image?
zer0int/ComfyUI-workflows
Workflows to implement fine-tuned CLIP Text Encoders with ComfyUI / SD, SDXL, SD3
zer0int/CLIP-attention-entropy
A small script for CLIP attn entropy plots
zer0int/Inf-CLIP
Geometric Parametrization GmP-Inf-CLIP modification of: "Breaking the Memory Barrier: Near Infinite Batch Size Scaling for Contrastive Loss". A super memory-efficiency CLIP training scheme.
zer0int/sam_faster
SAM: Sharpness-Aware Minimization (PyTorch)
zer0int/bitsandbytes-windows
Windows bitsandbytes 0.44.1.dev0 for Python 3.10, CUDA 12.6
zer0int/CLIP-ringelpiez
Plotting a CLIP vs. a CLIP in arbitrary ways.
zer0int/Block_Patcher_ComfyUI
Experimental sampler to iterate through blocks weight
zer0int/ComfyUI-HunyuanVideoWrapper
zer0int/comfyui_overly_complicated_sampling
Wildly unsound and experimental sampling for ComfyUI
zer0int/LLMorse
Talk Morse code to multimodal LLM using your voice. Beep-boop!