Replicate in a visual AI workflow

Remove backgrounds from images.

Ghiblify any image, 10x cheaper/faster than GPT 4o

Flux lora, use "CNSTLL" to trigger

multilingual text2image latent diffusion model

GFPGAN aims at developing Practical Algorithms for Real-world Face and Object Restoration

Add colours to old images

FLUX1.1 [pro] in ultra and raw modes.

Inference model for FLUX 1.1 [pro] Ultra using custom `finetune_id`.

Quality image generation and editing with support for reference images

Max-quality image generation and editing with support for ten reference images

Very fast image generation and editing model.

Un-distilled version of FLUX.2 [klein].

A version of FLUX.2 [klein] 4B-base that supports fast fine-tuned lora inference

4 step distilled version of FLUX.2 [klein].

Un-distilled version of FLUX.2 [klein].

A version of FLUX.2 [klein] 9B-base that supports fast fine-tuned lora inference

The highest fidelity image model from Black Forest Labs

High-quality image generation and editing with support for eight reference images

Open-weight edge-guided image generation.

Professional edge-guided image generation.

Open-weight depth-aware image generation.

Professional depth-aware image generation.

A 12 billion parameter rectified flow transformer capable of generating images from text descriptions

A version of flux-dev, a text to image model, that supports fast fine-tuned lora inference

Open-weight inpainting model for editing and extending images.

Professional inpainting and outpainting model with state-of-the-art performance.

Open-weight version of FLUX.1 Kontext

FLUX.1 Kontext[dev] image editing model for running lora finetunes

A premium text-based image editing model that delivers maximum performance and improved typography generation for transforming images through natural languag…

A state-of-the-art text-based image editing model that delivers high-quality outputs with excellent prompt following and consistent results for transforming…

An opinionated text-to-image model from Black Forest Labs in collaboration with Krea that excels in photorealism.

State-of-the-art image generation with top of the line prompt following, visual quality, image detail and output diversity.

Inference model for FLUX.1 [pro] using custom `finetune_id`

Open-weight image variation model.

Fast, efficient image variation model for rapid iteration and experimentation.

The fastest image generation model tailored for local development and personal use

The fastest image generation model tailored for fine-tuned use

SOTA Object removal, enables precise removal of unwanted objects from images while maintaining high-quality outputs.

Alibaba's Happy Horse 1.0 generates videos from text prompts or animates a single image into video.

Alibaba's Happy Horse 1.1 generates videos from text, animates a single image, or builds a video from multiple reference images.

Inpainting and video2video experiments with Wan 2.1

Zeroscope V2 XL & 576w

Add colours to old video footage.

extract foreground of a video

A high-fidelity capability for erasing unwanted objects, people, or visual elements from videos while maintaining aesthetic quality and temporal consistency

Upscale videos up to 8K output resolution.

Automatically remove backgrounds from videos -perfect for creating clean, professional content without a green screen.

Animate any character, humans, cartoons, animals, even non-humans, from a single image + driving video

LatentSync: generate high-quality lip sync animations

Turns your audio/video/images into professional-quality animated videos

A film-grade digital human model that generates realistic video from a single image, audio clip, and optional text prompt.

A video generation model that offers text-to-video and image-to-video support for 5s or 10s videos, at 480p and 720p resolution

A pro version of Seedance that offers text-to-video and image-to-video support for 5s or 10s videos, at 480p and 1080p resolution

A faster and cheaper version of Seedance 1 Pro

A joint audio-video model that accurately follows complex instructions.

ByteDance's multimodal video generation model with native audio, multimodal reference inputs, and intelligent duration control.

A faster variant of Seedance 2.0 for quicker video generation with multimodal inputs and native audio.

A lower-cost variant of Seedance 2.0 for high-volume video generation with multimodal inputs and native audio.

Upscale and enhance video up to 4K at 60fps, with scene-aware presets for AI-generated content, short dramas, UGC, and film restoration.

Ovi: generate videos with audio from image and text inputs

Audio-based Lip Synchronization for Talking Head Video

Audio-Driven Synthesis of Photorealistic Portrait Animations

Stylized Audio-Driven Single Image Talking Face Animation

Edit and transform videos with text prompts and reference images.

Use one or two face images to create AI avatars

Automatically add captions to a video

Use flux-kontext-pro to change the first or last frame of a video.

Create a waveform video from audio

FLUX Kontext fine-tune that let's you restyle any image as a PS1 or PS2 video game

State of the art video generation model.

Sound on: Google’s flagship Veo 3 text to video model, with audio

A faster and cheaper version of Google’s Veo 3 video model, with audio

New and improved version of Veo 3, with higher-fidelity video, context-aware audio, reference image and last frame support

New and improved version of Veo 3 Fast, with higher-fidelity video, context-aware audio and last frame support

Google's cost-efficient video generation model with native audio, optimized for high-volume applications

Create realistic talking avatar videos from text with HeyGen's Avatar IV engine

Create realistic talking avatar videos from text with HeyGen's Avatar V engine — the newest, highest-quality avatar engine with cross-reference-driven animat…

High-accuracy lip-sync: replace or dub audio on any video with avatar-inference lip sync

Generates speech from text

Generate speech from text, clone voices from mp3 files.

Generate fixed-bpm loops from text prompts

Updated to OpenVoice v2: Versatile Instant Voice Cloning

lightweight text-to-speech (TTS) model, trained on 10.5K hours of audio data

Zero-Shot Speech Editing and Text-to-Speech in the Wild

ElevenLabs's fastest speech synthesis model

Compose a song from a prompt or a composition plan

High quality, low latency text to speech in 32 languages

Generate multilingual text-to-speech audio in over 30 languages

The most expressive Text to Speech model

A F5-TTS fine-tuned for Spanish

Google's fast, expressive text-to-speech model with 30 voices and 70+ language support

Lyria 2 is a music generation model that produces 48kHz stereo audio through text-based prompts

Generate 30-second music clips from text prompts or images with Lyria 3, Google's music generation model

Generate full-length songs up to 3 minutes from text prompts or images with Lyria 3 Pro, Google's most capable music generation model

Highest-quality realtime text-to-speech with <200ms latency, emotion control, and 15-language support

Ultra-fast, cost-efficient realtime text-to-speech with ~120ms latency and 15-language support

Most expressive text-to-speech model from Inworld, with natural-language steering, real-time latency, and multilingual support across 100+ languages.

Highest-quality text-to-speech with <200ms latency, emotion control, and 15-language support

Ultra-fast, cost-efficient text-to-speech with ~120ms latency and 15-language support

Kokoro v1.0 - text-to-speech (82M params, based on StyleTTS2)

A Step Towards Music Generation Foundation Model text2music

CSM (Conversational Speech Model) is a speech generation model from Sesame that generates RVQ audio codes from text and audio inputs

A simple OCR Model that can easily extract text from an image.

E5-mistral-7b-instruct language embedding model

Answers questions about images

Return CLIP features for the clip-vit-large-patch14 model

Return CLIP features for the clip-vit-large-patch14 model

Llama2 13B with embedding output

Anthropic's fastest, most cost-effective model, with a 200K token context window (claude-3-5-haiku-20241022)

The most intelligent Claude model and the first hybrid reasoning model on the market (claude-3-7-sonnet-20250219)