DisCa: Accelerating Video Diffusion Transformers with Distillation-Compatible Learnable Feature Caching

Automated alignment adjustment for LLMs — direct steering, LoRA, and MoE expert-granular abliteration, optimized via multi-objective Optuna TPE.

Official Implementation of OmniWeaving: Towards Unified Video Generation with Free-form Composition and Reasoning

A ComfyUI plugin that wraps [See-through](https://github.com/shitagaki-lab/see-through) — an AI system that decomposes a single anime illustration into manipulatable 2.5D layer-decomposed models wi…

"Single-image Layer Decomposition for Anime Characters" (SIGGRAPH 2026, Conditionally Accepted)

KVAE tokenizers

Tools for merging pretrained large language models.

What's your LLM's personality? Measure warmth, patience, confidence and 5 more axes from hidden states.

Demo for AudioSAE paper

Web UI for training and running open models like Gemma 4, Qwen3.5, DeepSeek, gpt-oss locally.

All available LTX-2 models, encoders, workflows, LoRAs for ComfyUI

CVPR 2026 (Highlight)-Guiding a Diffusion Transformer with the Internal Dynamics of Itself (IG)

Abliterate large quantized models at home using llama.cpp!

A SillyTavern extension that generates AI-powered "audience" reactions in various chat styles (Discord/Twitch, Twitter, News, MST3K, etc.) that appear below the chat input.

Official Python inference and LoRA trainer package for the LTX-2 audio–video generative model.

A library to automatically evaluate LLM refusal behavior on different datasets

Statistical toolkit for LLM refusal steering. Uses judge scores to weight training data, correlation analysis to identify effective layers, and automated alpha optimization. Implements WRMD method …

SillyInnkeeper is an open-source local character card manager for SillyTavern. It scans PNG cards, extracts metadata, generates previews, and provides a UI for organizing and managing large charact…

UniAVGen: Unified Audio and Video Generation with Asymmetric Cross-Modal Interactions

LLM Frontend for Power Users.

Make abliterated models with transformers, easy and fast

RAM is all you need

A research project exploring WanVideo LoRA training.

[CVPR 2026] An official implementation of Adv-GRPO. The Image as Its Own Reward: Reinforcement Learning with Adversarial Reward for Image Generation.

Official inference repo for FLUX.2 models

Lightweight video space-time cropper GUI

HunyuanVideo-1.5: A leading lightweight video generation model