Все модели

A Stable Diffusion model fine tuned on a limited set of Studio Ghibli landscape images

MistralLiteA is a fine-tuned Mistral-7B-v0.1 language model, with enhanced capabilities of processing long context (up to 32K tokens)

Generate image with transparent background

An SDXL fine-tune on bad 2048x2048 images

ziggislide is a model of an adventurous character of an influencer always wearing colorful fabulous outfit, goggles and helmet, he loves water sliding boards and taking selfies. To invoke his presence use the token ziggyslide inside the prompt

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

Masked-attention Mask Transformer for Universal Image Segmentation

SOTA open-source model for chatting with videos and the newest model in the Qwen family

Flux finetune of the style: TIMES 100 Most Influential People in AI

Gradient-Based Discrete Optimization for Prompt Tuning and Discovery

isometric, skeumorphic icon design

Generate a model with a garment faster if you have a mask image

One Model to Rig Them All: Diverse Skeleton Rigging with UniRig

RealVisXL v3 fine-tuned on 80s cyberpunk images

Depth Anything on full video files

E5-mistral-7b-instruct language embedding model

This is the chat model finetuned on top of TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T

Monocular relative depth estimation

SDXL Fine-tune on LEGO

A simple, fast API that converts any HTML/CSS string into a high-quality PNG or JPEG image with customizable dimensions.

Creates fully 360 panoramas for VR and backdrop media

majicMIX realistic V7 support civitai lora,text2image,image2image

flux trained on me

Free Lunch towards Style-Preserving in Text-to-Image Generation by InstantX team, with ControlNet

Doodles trained on black line drawings, fashion illustrations, and wire sculptures. Simple images for complex intellectuals, luxury brands, b2b marketing, saas..

STAR Video Upscaler: Spatial-Temporal Augmentation with Text-to-Video Models for Real-World Video Super-Resolution

Salesforce/codegen2-1B

SDXL model for mandalas coloring pages and coloring book designs

Use flux-kontext-pro to change the first or last frame of a video. Useful to use as inputs for restyling an entire video in a certain way

Bokeh Prediction, a hybrid bokeh rendering framework that combines a neural renderer with a classical approach. It generates high-resolution, adjustable bokeh effects from a single image and potentially imperfect disparity maps.

Multilingual Stable Diffusion

Jessie Jess

SDXL fine-tuned on Xmas sweaters

High-quality image generation with a focus on interior design, architectural visualization, and style adaptation. 🏡🎨

The VALL-E models by Amphion.