Skip to content
View kabachuha's full-sized avatar

Organizations

@wesnoth

Block or report kabachuha

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
Showing results
Python 89 12 Updated Nov 5, 2026

Speech-to-video inference: an avatar video generated from a reference frame and a speech track

Python 62 10 Updated Nov 11, 2026

llama.cpp fork that abliterates at inference

C++ 219 17 Updated Oct 24, 2026

Clip chaining for Kandinsky 6.0 in ComfyUI, also with an option to set custom audio

Python 2 Updated Oct 24, 2026

Run GLM-5.3 (744B), GLM-5.3-Flash (321B), DeepSeek-V4.1-Flash (748B) and MiniMax-M3.1-Flash (428B) on your own GPUs - one engine, one dashboard, OpenAI- and Anthropic-compatible API.

C++ 2,993 418 Updated Nov 17, 2026

Kandinsky 6.0 Video SR: Models for Video Super-Resolution

Python 25 3 Updated Nov 17, 2026

Kandinsky 6.0 Video: Foundation Models for Synchronized Video and Audio Generation

Python 362 36 Updated Nov 8, 2026

FLUX 3 Action: open weights 7B world action model from Black Forest Labs. Train, fine-tune and run action prediction for robots (DROID, SO-101), simulators and games.

Python 223 24 Updated Nov 10, 2026

The open source coding agent.

TypeScript 227,559 30,851 Updated Nov 17, 2026

Call LLMs and VLMs from ComfyUI with any OpenAI compatible chat completions API: local servers (llama.cpp, vLLM, SGLang, Ollama, LM Studio, tabbyAPI, Unsloth Studio…) or cloud providers. Text and i…

Python 55 18 Updated Nov 17, 2026

Train and chat with a frozen language model coupled to the full retained MaleCNS fly connectome.

Python 92 15 Updated Sep 11, 2026

Story Creation AI Agent for novel, scripts, translation, interactive games, and IP content

TypeScript 11,278 2,032 Updated Oct 24, 2026

Optuna-optimized "abliteration" (directional ablation) directly on quantized GGUF models via llama.cpp. The base GGUF is never modified — trials run as hot-swapped LoRA adapters, and the result exp…

Python 16 3 Updated Aug 9, 2026

Kandinsky WM 1.0 — a family of models for Physical AI. Image-to-video generation for autonomous driving, robotics & general physics.

Python 12 1 Updated Aug 5, 2026

A SillyTavern extension that adds a "Delete All But This Swipe" option to the message deletion prompt, allowing you to discard every unused swipe on a message in one action while keeping the one cu…

JavaScript 14 3 Updated Mar 24, 2026

KVAE-Audio: a continuous full-band audio waveform autoencoder.

Python 128 5 Updated Nov 11, 2026
Python 13 3 Updated Jun 5, 2026

NVIDIA Cosmos is an open platform of world models, datasets, and tools that enables developers to build Physical AI for robots, autonomous vehicles, smart infrastructure, and more.

12,387 963 Updated Nov 11, 2026

The most powerful local music generation model that outperforms almost all commercial alternatives, supporting Mac, AMD, Intel, and CUDA devices.

Python 14,894 1,980 Updated Nov 8, 2026

Globally Set Explorer Folder Views

HTML 2,054 73 Updated Nov 13, 2026

The agent that grows with you

Python 264,180 59,602 Updated Nov 17, 2026

[CVPR 2024] RoMa: Robust Dense Feature Matching; RoMa is the robust dense feature matcher capable of estimating pixel-dense warps and reliable certainties for almost any image pair.

Python 1,338 142 Updated Jan 23, 2026

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

Python 26 Updated Apr 15, 2026

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

Python 290 45 Updated Nov 10, 2026

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

Python 808 27 Updated Oct 30, 2026

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…

Jupyter Notebook 940 78 Updated Aug 20, 2026

"Single-image Layer Decomposition for Anime Characters" (SIGGRAPH 2026 Conference Paper)

Python 5,736 494 Updated Nov 14, 2026

KVAE tokenizers

Python 105 2 Updated Aug 14, 2026

Tools for merging pretrained large language models.

Python 7,474 807 Updated Oct 31, 2026
Next