Create variations of an image while preserving shape and depth

LLaVA v1.6: Large Language and Vision Assistant (Mistral-7B)

A SDXL Model trained from another SDXL-hiroshinagai model images

7B base version of Google’s Gemma model

Stable Diffusion XL specifically trained on Inpainting by huggingface

Locality-enhanced Projector for Multimodal LLM

SigLIP proposes to replace the loss function used in CLIP by a simple pairwise sigmoid loss

Fully distilled and accelerated MobileSAM

Generate videos from text prompts with Kandinsky-2.2

flan-t5-xl trained on the Memory Alpha Star Trek Wiki

A 6B parameter open bilingual chat LLM (optimized for 8k+ context) | 开源双语对话语言模型

whisper-large-v3, incredibly fast, with video transcription

Lucid Sonic Dreams syncs StyleGAN XL -generated visuals to music

Segments an audio recording based on who is speaking (on A100)

A SDXL LoRA inspired by Tomb Raider (1996)

datasets: Flickr8k

Generate image prompts for Midjourney. Prefix inputs with "Image: "

Source: Unbabel/TowerInstruct-7B-v0.1 ✦ Quant: TheBloke/TowerInstruct-7B-v0.1-AWQ ✦ This model is trained to handle several translation-related tasks, such as general machine translation, gramatical error correction, and paraphrase generation

An SDXL finetune of photos I took while riding a train in Finland (Helsinki-Vaasa)

Accelerated transcription, word-level timestamps and diarization with whisperX large-v3