Source: chargoddard/loyal-piano-m7 ✦ Quant: TheBloke/loyal-piano-m7-AWQ ✦ Intended to be a roleplay-focused model with some smarts and good long-context recall

A fine-tuned SDXL LoRA trained on images of stealth planes

Notus-7b-v1 model

A pipeline for superfast video editing! Make cuts to a video by editing its transcript.

Juggernaut Aftermath Model with original TRCVAE (Text2Img, Img2Img and Inpainting)

Starling-LM-7B-alpha

PixArt-Alpha 1024px is a transformer-based text-to-image diffusion system trained on text embeddings from T5

Deliberate V4 Model (Text2Img, Img2Img and Inpainting)

Generates multi-view optical illusions

MusicGen stereo fine-tuned on Xmas music

DemoFusion: Democratising High-Resolution Image Generation With No 💰

A simple SDXL model trained on artistic patterns in the Andalusian style.

MusicGen Stereo model fine-tuned on the tracks of Oneohtrix Point Never with the text token "OPN"

Generates subtitles

Separate instruments and/or vocals from any song.

SDXL fine-tuned using my own sketches and photos in a dark, moody style

SDXL fine-tuned using some artworks by one artist

SDXL fine-tuned on paper collages

Source: fblgit/juanako-7b-UNA ✦ Quant: TheBloke/juanako-7B-UNA-AWQ ✦ juanako uses UNA, Uniform Neural Alignment. A training technique that ease alignment between transformer layers yet to be published

SDXL fine-tuned on Xmas sweaters

human-like cat sdxl-lora model

Simple binary sentiment analysis with BERT

SDXL turbo + SVD

VideoReTalking: Audio-based Lip Synchronization for Talking Head Video Editing in the Wild

Tempo BPM estimation with Essentia

Source: berkeley-nest/Starling-LM-7B-alpha ✦ Quant: TheBloke/Starling-LM-7B-alpha-AWQ ✦ An open large language model (LLM) trained by Reinforcement Learning from AI Feedback (RLAIF)

SEINE: Short-to-Long Video Diffusion Model for Generative Transition and Prediction

powerful open-source visual language model

InterpAny-Clearer: Clearer anytime frame interpolation & Manipulated interpolation

Generate music in stereo, restricted to chord sequences and tempo

Source: monology/openinstruct-mistral-7b ✦ Quant: TheBloke/openinstruct-mistral-7B-AWQ ✦ Commercially-usable 7B model, based on mistralai/Mistral-7B-v0.1 and finetuned on VMware/open-instruct

Coqui XTTS-v2: Multilingual Text To Speech Voice Cloning

Source: TokenBender/evolvedSeeker_1_3 ✦ Quant: TheBloke/evolvedSeeker_1_3-AWQ ✦ A fine-tuned version of deepseek-ai/deepseek-coder-1.3b-base on 50k instructions for 3 epochs

A1111 webui api

A fine-tuned SDXL LoRA trained on images from World War 2

Generate texture for your mesh with text prompts

A fine-tuned SDXL LoRA trained on steet art murals

LCM AOM3 Superfast

URPM V1.3 Model (Text2Img, Img2Img and Inpainting)

Deliberate V3 Model (Text2Img, Img2Img and Inpainting)

Controlnet v1.1 - Tile Version