Explore
Fine-tune FLUX fast
Customize FLUX.1 [dev] with the fast FLUX trainer on Replicate
Train the model to recognize and generate new concepts using a small set of example images, for specific styles, characters, or objects. It's fast (under 2 minutes), cheap (under $2), and gives you a warm, runnable model plus LoRA weights to download.
Featured models
minimax / hailuo-02
Hailuo 2 is a text-to-video and image-to-video model that can make 6s or 10s videos at 768p (standard) or 1080p (pro). It excels at real world physics.
minimax / hailuo-02-fast
A low cost and fast version of Hailuo 02. Generate 6s and 10s videos in 512p
bytedance / omni-human
Turns your audio/video/images into professional-quality animated videos
google / veo-3-fast
A faster and cheaper version of Google’s Veo 3 video model, with audio
google / veo-3
Sound on: Google’s flagship Veo 3 text to video model, with audio
flux-kontext-apps / kontext-emoji-maker
Use kontext to turn any image into an emoji, using a lora by starsfriday
wan-video / wan-2.2-t2v-fast
A very fast and cheap PrunaAI optimized version of Wan 2.2 A14B text-to-video
black-forest-labs / flux-krea-dev
An opinionated text-to-image model from Black Forest Labs in collaboration with Krea that excels in photorealism. Creates images that avoid the oversaturated "AI look".
wan-video / wan-2.2-i2v-a14b
Image-to-video at 720p and 480p with Wan 2.2 A14B
Official models
Official models are always on, maintained, and have predictable pricing.
I want to…
Generate images
Use AI To Generate Images & Photos with an API
Caption videos
Use AI To Caption Videos with an API
Generate speech
Convert text to speech
Use a face to make images
Make realistic images of people instantly
Generate videos
Use AI To Generate Videos with an API
Upscale images
Upscaling models that create high-quality images from low-quality images
Generate music
Use AI To Generate Music with an API
Edit images
Use AI To Edit Any Image with an API
Transcribe speech
Models that convert speech to text
Extract text from images
Optical character recognition (OCR) and text extraction
Remove backgrounds
Models that remove backgrounds from images and videos
Use the FLUX family of models
The FLUX family of text-to-image models from Black Forest Labs
Restore images
Models that improve or restore images by deblurring, colorization, and removing noise
Enhance videos
Upscaling models that create high-quality video from low-quality videos
Edit Videos
Tools for editing videos.
Videos from images
Use AI To Generate Videos from images with an API
Make videos with Wan
Generate videos with Wan, the fastest and highest quality open-source video generation model.
Use Kontext fine-tunes
Browse the diverse range of fine-tunes the community has custom-trained on Replicate
Caption images
Use AI To Caption Images with an API
Chat with images
Ask language models about images
Use LLMs
Models that can understand and generate text
Make 3D stuff
Models that generate 3D objects, scenes, radiance fields, textures and multi-views.
Use handy tools
Toolbelt-type models for videos and images.
Control image generation
Guide image generation with more than just text. Use edge detection, depth maps, and sketches to get the results you want.
Sing with voices
Voice-to-voice cloning and musical prosody
Get embeddings
Models that generate embeddings from inputs
Try for free
Get started with these models without adding a credit card. Whether you're making videos, generating images, or upscaling photos, these are great starting points.
Use official models
Official models are always on, maintained, and have predictable pricing.
Detect objects
Models that detect or segment objects in images and videos.
Use FLUX fine-tunes
Browse the diverse range of fine-tunes the community has custom-trained on Replicate
Popular models
This is the fastest Flux Dev endpoint in the world, contact us for more at pruna.ai
whisper-large-v3, incredibly fast, with video transcription
Return CLIP features for the clip-vit-large-patch14 model
Practical face restoration algorithm for *old photos* or *AI-generated faces*
SDXL-Lightning by ByteDance: a fast text-to-image model that makes high-quality images in 4 steps
Latest models
Hailuo 2 is a text-to-video and image-to-video model that can make 6s or 10s videos at 768p (standard) or 1080p (pro). It excels at real world physics.
A low cost and fast version of Hailuo 02. Generate 6s and 10s videos in 512p
Turns your audio/video/images into professional-quality animated videos
A faster and cheaper version of Google’s Veo 3 video model, with audio
Use kontext to turn any image into an emoji, using a lora by starsfriday
A very fast and cheap PrunaAI optimized version of Wan 2.2 A14B text-to-video
A very fast and cheap PrunaAI optimized version of Wan 2.2 A14B image-to-video
PartCrafter is a structured 3D mesh generation model that creates multiple parts and objects from a single RGB image.
The image generation model tailored for local development and personal use
Mediapipe Blendshape Labeler - Predicts the blend shapes of an image.
wan-video/wan-2.2 (all variants) + topazlabs/video-upscale + zsxkib/smart-thinksound
Text-guided image editing model that preserves original details while making targeted modifications like lighting changes, object removal, and style conversion
Official CLIP models, generate CLIP (clip-vit-large-patch14) text & image embeddings
Granite-speech-3.3-8b is a compact and efficient speech-language model, specifically designed for automatic speech recognition (ASR) and automatic speech translation (AST).
Automatically generates expert ThinkSound prompts by analyzing your video w/ Claude 4 - no more struggling with complex audio descriptions
An opinionated text-to-image model from Black Forest Labs in collaboration with Krea that excels in photorealism. Creates images that avoid the oversaturated "AI look".
Voxtral Small is an enhancement of Mistral Small 3 that incorporates state-of-the-art audio input capabilities and excels at speech transcription, translation and audio understanding.
Make a very realistic looking real-world AI video via FLUX 1.1 Pro and Wan 2.2 i2v
Seed-X-PPO-7B by ByteDance-Seed, a powerful series of open-source multilingual translation language models
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.
Granite-3.3-8B-Instruct is a 8-billion parameter 128K context length language model fine-tuned for improved reasoning and instruction-following capabilities.
Granite-vision-3.3-2b is a compact and efficient vision-language model, specifically designed for visual document understanding, enabling automated content extraction from tables, charts, infographics, plots, diagrams, and more.
Higgs Audio v2, a powerful text-to-speech audio foundation model that excels in expressive audio generation
Run any ComfyUI workflow. Guide: https://github.com/replicate/cog-comfyui
🎤The best open-source speech-to-text model as of Jul 2025, transcribing audio with record 5.63% WER and enabling AI tasks like summarization directly from speech✨
InScene is a LoRA by Peter O’Malley (POM) that's designed to generate images that maintain scene consistency with a source image. It is trained on top of Flux.1-Kontext.dev.
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
Edit an image with a prompt. This is the hidream-e1.1 model accelerated with the pruna optimisation engine.
MOSS-TTSD (text to spoken dialogue) is an open-source bilingual spoken dialogue synthesis model that supports both Chinese and English. It can transform dialogue scripts between two speakers into natural, expressive conversational speech.
Generate an image using the previously generated image as the input with a recursive prompt.
Accelerated variant of Photon prioritizing speed while maintaining quality