AI Model Catalogue

Image to separate stems from a song, using demucs and spleeter

High-fidelity video generation with text-to-video, image-to-video, and start-end-to-video modes. Up to 16 seconds at 1080p with synchronized audio.

Generate and edit images with Alibaba's Wan 2.7

4x face image upscaler trained on FFHQ dataset using DAT (Dual Aggregation Transformer) architecture. Optimized for portrait and face photos.

The highest fidelity image model from Black Forest Labs

Generate professional e-commerce product photos from a single image. Automatically removes background, creates realistic studio scenes, and adds natural shadows.

A custom Flux LoRA model trained on painterly illustrated poster art inspired by Blade Runner 2049. The style features atmospheric cyberpunk cityscapes with dramatic scale — tiny silhouetted figures dwarfed by massive holographic projections and towering

Fastest image upscaler in the world (<1s) supporting outputs up to 128 MP.

GeoCalib (ECCV 2024): Single-image camera calibration. Estimates focal length, FoV, distortion, roll and pitch from one image using a deep net + Levenberg-Marquardt optimizer. Works on both outdoor and indoor scenes.

🔥 SeedVR2: one-step video & image restoration with 7B and Adjustable Resolution

Generate videos guided by reference images using xAI's Grok Imagine Video model

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

Get embeddings for image using siglip-large-patch16-384

ERNIE-Image is an open text-to-image generation model developed by the ERNIE-Image team at Baidu

Edit and transform videos with text prompts and reference images. Style transfers, object replacement, character transformation, and more.

A sub 1 second 0.01$ multi-image editing model built for production use cases. For image generation, check out p-image here: https://replicate.com/prunaai/p-image

FireRed-Image-Edit 1.1 is a general-purpose image editing model that delivers high-fidelity and consistent editing across a wide range of scenarios.

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

Stable Diffusion 3.5 Large is Stability AI's most capable text-to-image model, delivering photorealistic and creative imagery with excellent prompt adherence and detail. Features multimodal diffusion transformer architecture.

Amazon Nova Pro is a highly capable multimodal model with the best combination of accuracy, speed, and cost across a wide range of tasks. Supports text, image, and video inputs.

Amazon Nova Lite is a very low-cost multimodal model that can process image, video, and text inputs. Fast and accurate for a wide range of tasks requiring visual and language understanding.