Все модели

Make realistic images of real people instantly

'''Last update: Now supports img2img.''' SDXL Canny controlnet with LoRA support.

Third party Fooocus replicate model with preset 'realistic'

Spleeter is Deezer source separation library with pretrained models written in Python and uses Tensorflow.

A better alternative to SDXL refiners, providing a lot of quality and detail. Can also be used for inpainting or upscaling.

Fine-tune FLUX.1-dev using ai-toolkit

Edit images with human instructions

Use FLUX Kontext to restore, fix scratches and damage, and colorize old photos

A text-to-image model that generates high-resolution images with fine details. It supports various artistic styles and produces diverse outputs from the same prompt, with a focus on fewer inference steps

Demucs Music Source Separation

Fast sdxl with higher quality

😊 Hotshot-XL is an AI text-to-GIF model trained to work alongside Stable Diffusion XL

Extract the first or last frame from any video file as a high-quality image

Models fine-tuned from Pony-XL series.

Take a video and replace the face in it with a face of your choice. You only need one image of the desired face. No dataset, no training.

Base version of Llama 3, a 70 billion parameter language model from Meta.

CLIP Interrogator for SDXL optimizes text prompts to match a given image

Google's most advanced reasoning Gemini model

Modify images using canny edge detection

Jina-CLIP v2: 0.9B multimodal embedding model with 89-language multilingual support, 512x512 image resolution, and Matryoshka representations

Video Upscaling from Topaz Labs

A multimodal LLM-based AI assistant, which is trained with alignment techniques. Qwen-VL-Chat supports more flexible interaction, such as multi-round question answering, and creative capabilities.

Generate 5s and 10s videos in 1080p resolution

Amazing photorealism with RealVisXL_V3.0, based on SDXL, trainable

ControlNet QR Code Generator: Simplify QR code creation for various needs using ControlNet's user-friendly neural interface, making integration a breeze. Just key in the url !

Florence-2: Advancing a Unified Representation for a Variety of Vision Tasks

Adapt any picture of a face into another image

Make Emoji with AI.

Robust Monocular Depth Estimation

Granite-3.1-8B-Instruct is a lightweight and open-source 8B parameter model is designed to excel in instruction following tasks such as summarization, problem-solving, text translation, reasoning, code tasks, function-calling, and more.

Create 5s-8s videos with enhanced character movement, visual effects, and exclusive 1080p-8s support. Optimized for anime characters and complex actions

Google's latest image generation model in Gemini 2.5

Turn your image into a cartoon

Realistic Inpainting with ControlNET (M-LSD + SEG)

A llama-3 based moderation and safeguarding language model

A faster and cheaper version of Seedance 1 Pro

This is a 3x faster FLUX.1 [dev] model from Black Forest Labs, optimised with pruna with minimal quality loss.

Runway's Gen-4 Image model with references. Use up to 3 reference images to create the exact image you need. Capture every angle.

Segment foreground objects with high resolution and matting, using InSPyReNet

Juggernaut XL v7 Model (Text2Img, Img2Img and Inpainting)

Modify images using depth maps

Inpainting || multi-controlnet || single-controlnet || ip-adapter || ip adapter face || ip adapter plus || No ip adapter

Generate a new image given any input text with Deliberate v2

CogVLM2: Visual Language Models for Image and Video Understanding

The current model is used for graphics replacement processing

Modify images using depth maps

Generate 6s videos with prompts or images. (Also known as Hailuo). Use a subject reference to make a video with a character and the S2V-01 model.

Base version of Llama 2 7B, a 7 billion parameter language model

Create Pixar poster easily with SDXL Pixar.

UPDATE: new upscaling algorithm for a much improved image quality. Fermat.app open-source implementation of an efficient ControlNet 1.1 tile for high-quality upscales. Increase the creativity to encourage hallucination.