Unofficial community fork and Diffusers formatted weights of tencent/HunyuanVideo

Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understanding

A simple model to detect and crop face found in image, made for https://outfit.fm

Fork / Remix of Apollo 7B by Luis C. (https://replicate.com/lucataco/apollo-7b) to support multi-turn conversations.

QVQ-72B-Preview by Qwen is an experimental research model focusing on enhancing visual reasoning capabilities

Remodels interior

Autoregressive Video Generation without Vector Quantization

Flawless Text is a high-precision text-to-image model that generates typo-free, visually accurate images from text descriptions, ideal for seamless, error-free creative workflows.

Autoregressive Image Generation without Vector Quantization

ModernBERT-large is a modernized bidirectional encoder-only Transformer model (BERT-style) pre-trained on 2 trillion tokens of English and code data

ModernBERT-base is a modernized bidirectional encoder-only Transformer model (BERT-style) pre-trained on 2 trillion tokens of English and code data

Scalable Streaming Speech Synthesis with Large Language Models

Scaling Bitwise AutoRegressive Modeling for High-Resolution Image Synthesis

A Llama-3.2-11B pretrained model, fine-tuned for content safety classification

sound separation with demucs

FlowEdit: Inversion-Free Text-Based Editing Using Pre-Trained Flow Models

A Llama-3.1-8B pretrained model, fine-tuned for content safety classification

A 7B parameter Llama 2-based input-output safeguard model

Image inpainting with flux

Latest model in the Qwen family for chatting with video and image models

Remove backgrounds from images.

Granite-3.1-8B-Instruct is a lightweight and open-source 8B parameter model is designed to excel in instruction following tasks such as summarization, problem-solving, text translation, reasoning, code tasks, function-calling, and more.

Granite-3.1-2B-Instruct is a lightweight and open-source 2B parameter model designed to excel in instruction following tasks such as summarization, problem-solving, text translation, reasoning, code tasks, function-calling, and more.

Fast Hunyuan Video by Hao AI Lab

Demucs is an audio source separator created by Facebook Research.

Açıklama Testi

Fast Mochi by Hao AI Lab

Quickly generate up to 1 minute of music with lyrics and vocals in the style of a reference track

Ollama Llama 3.2 Vision 90B

comfy with flux model,

Ollama Llama 3.2 Vision 11B

Ollama QwQ 32B

Clothing segmentation tool that generates masks from outfit images, separating them into top and bottom pieces with automatic background removal and edge refinement.

Ollama Llama 3.3 70B

Hyper-SD: Trajectory Segmented Consistency Model for Efficient Image Synthesis

Apollo 7B - An Exploration of Video Understanding in Large Multimodal Models

An image-to-video (I2V) model specifically trained for Live2D and general animation use cases

Apollo 3B - An Exploration of Video Understanding in Large Multimodal Models

Video Background Removal

Prepare arXiv papers for processing by Large Language Models (LLMs) by converting them into a single, expanded LaTeX file.

Arbitrary-steps Image Super-resolution via Diffusion Inversion

Video Preprocessing tool for captioning multiple videos using GPT, Claude or Gemini

Simple tool to split apart a video into snippets

Create ads for marketing, social media with your own company logo on any object you want.

a-r-r-o-w/cogvideox-factory for Mochi-1 LoRA Training

Make realistic images of real people instantly