Kosmos-G: Generating Images in Context with Multimodal Large Language Models

SVD + in-painting

A ~7B parameter language model from Deepseek for SOTA repository level code completion

Source: Pclanglais/MonadGPT ✦ Quant: TheBloke/MonadGPT-AWQ ✦ What would have happened if ChatGPT was invented in the 17th century?

Playground v2 is a diffusion-based text-to-image generative model trained from scratch by the research team at Playground

Source: fblgit/una-cybertron-7b-v2-bf16 ✦ Quant: TheBloke/una-cybertron-7B-v2-AWQ ✦ A 7B MistralAI based model, best on it's series. Trained on SFT, DPO and UNA (Unified Neural Alignment) on multiple datasets

Generate plasma shader equations

Translate audio while keeping the original style, pronunciation and tone of your original audio.

Convert your videos to DensePose and use it with MagicAnimate

API for enhanced word-level timestamp accuracy using OpenAI's Whisper model

Add a watermark to your videos using the power of Replicate brought to you from your friends at FullJourney.AI

Extracts motion from video

Train your own custom RVC model

A fine-tuned SDXL LoRA trained on Georgia O'keeffe art

Deliberate V5 Model (Text2Img, Img2Img and Inpainting)

Counterfeit XL v2 Model (Text2Img, Img2Img and Inpainting)

Edit real or generated images

Edit real or generated images

Simple model to make addition and answer is send to supabase

highist resolutioin image

Juggernaut XL v7 Model (Text2Img, Img2Img and Inpainting)

MagicAnimate: Temporally Consistent Human Image Animation using Diffusion Model

Generate color codes for prominent colors in the image

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