Все модели

openai/whisper with exposed settings for word_timestamps

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

powerful open-source visual language model

Open-weight inpainting model for editing and extending images. Guidance-distilled from FLUX.1 Fill [pro].

Third party Fooocus replicate model

A multimodal image generation model that creates high-quality images. You need to bring your own verified OpenAI key to use this model. Your OpenAI account will be charged for usage.

Speech to speech with any RVC v2 trained AI voice

Nonlinear Activation Free Network for Image Restoration

Uses pixray to generate an image from text prompt

Create music for your content

Create images of a given character in different poses

Use this ultra version of Imagen 4 when quality matters more than speed and cost

Generate a new image from an input image with Babes 2.0

Capture a website screenshot

Only a Matter of Style: Age Transformation Using a Style-Based Regression Model

Blip 3 / XGen-MM, Answers questions about images ({blip3,xgen-mm}-phi3-mini-base-r-v1)

Professional-grade image upscaling, from Topaz Labs

Accelerated transcription, word-level timestamps and diarization with whisperX large-v3 for large audio files

Best-in-class clothing virtual try on in the wild (non-commercial use only)

Dream Shaper stable diffusion

allenai/Molmo-7B-D-0924, Answers questions and caption about images

Turn any image into a video

Transfer the style of one image to another

Text-Driven Manipulation of StyleGAN Imagery

Deployment of Realistic vision v5.0 with xformers for fast inference

OpenAI's new model excelling at coding, writing, and reasoning.

Bringing Old Photos Back to Life

Fastest, most cost-effective GPT-4.1 model from OpenAI

Quality image generation and editing with support for reference images

Synthesizing High-Resolution Images with Few-Step Inference

General Text Embeddings (GTE) model.

Stable Diffusion on Danbooru images

Demucs is an audio source separator created by Facebook Research.

Mask prompting based on Grounding DINO & Segment Anything | Integral cog of doiwear.it

Embed text with Qwen2-7b-Instruct

Faster version of OpenAI's flagship GPT-5 model

Modify images with canny edge detection and Deliberate model twitter: @philz1337x

Open-weight depth-aware image generation. Edit images while preserving spatial relationships.

Stable diffusion for real-time music generation

This model generates beautiful cinematic 2 megapixel images in 3-4 seconds and is derived from the Wan 2.2 model through optimisation techniques from the pruna package

Segments an audio recording based on who is speaking

SANA-Sprint: One-Step Diffusion with Continuous-Time Consistency Distillation

The Qwen3 Embedding model series is specifically designed for text embedding and ranking tasks

Segmind Stable Diffusion Model (SSD-1B) is a distilled 50% smaller version of SDXL, offering a 60% speedup while maintaining high-quality text-to-image generation capabilities

Generate a new image from an input image with Stable Diffusion

FLUX.1-dev with XLabs-AI’s realism lora

Anything V4.5 Model (Text2Img, Img2Img and Inpainting)

batch inference for dreambooth trainings