Все модели

Nemotron-3-Nano-30B-A3B is a large language model (LLM) trained from scratch by NVIDIA

Transform Images & Text into 3D Models with AI

Flux lora trained on photos of Neelesh Kumar

for backsound

Mockup generator (bags, t-shirts, mugs, billboard etc) using Stable Diffusion in-painting

For my AI punk band The Buttredettes I wanted the option to generate images where they show the finger. This gesture is either censored in all major models or not trained. This lora should fix it. It's not working all the time, but more often than not.

2DN XL Model (Text2Img, Img2Img and Inpainting)

A multi-input ControlNet model. Pass in control images and set the weights.

The Fish Speech V1.4 model.

Transforms pet photos into high-quality 90s Disney-style cartoon illustrations with accurate fur details and charming expressions.

A fork of https://replicate.com/idea-research/ram-grounded-sam that outputs usable(grayscale) mask values

Anime Illust model

Generates cursed images

A model I copied to blur an image

The Fish Speech V1.2 SFT model.

Detect and simplify the contours of a binary image

Stable output of daily life photos of the same person

End-to-end video diffusion transformer, which synthesizes infinite-length high-quality audio-driven avatar videos without any post-processing

2.7B param open source chat model trained on Glaive’s synthetic data generation platform

Optimized model

LCM AOM3 Superfast

Simple version of https://huggingface.co/teknium/OpenHermes-2-Mistral-7B

A Single Model for Many Visual Modalities

The Fish Speech V1.2 model.

Nougat: Neural Optical Understanding for Academic Documents

Synthiola is a synthetic being living in SDXL latent space: https://www.fabianmosele.com/synthiola

ShieldGemma 2 is a model trained on Gemma 3's 4B IT checkpoint for image safety classification across key categories that takes in images and outputs safety labels per policy.

This model creates images in the style of pulp novels and magazines from the mid 20th century. Tough