replicate

Cloudflare announces acquisition of AI model platform Replicate, planning to integrate its 50,000+ open-source/commercial models and developer tools into its global network and Workers AI platform.

The m1guelpf/nsfw-filter is an open-source AI model for NSFW content filtering, available on Replicate with low-cost execution on Nvidia T4 GPU hardware.

BiRefNet is an AI model for image segmentation available on Replicate, offering cost-effective inference on Nvidia A100 GPUs and is open-source.

mattsays/sam3-image is an AI model available on Replicate with a cost of $0.0015 per run, running on Nvidia L40S GPU, and open source for local execution via Docker.

Depth Anything V2 is a monocular depth estimation model that significantly outperforms V1 in fine-grained details and robustness, offering faster inference and higher accuracy than SD-based models. It is available on Replicate under varying licenses.

PrunaAI presents Flux Fast, an optimized endpoint for Black Forest Labs' FLUX.1-dev model, claiming the fastest Flux inference via compression, caching, and compilation.

Jina CLIP v2 is an improved multimodal embedding model supporting 89 languages, high-resolution images, and flexible embedding dimensions, with 3% better performance than v1 and state-of-the-art results on multilingual benchmarks.

PrunaAI's P-Image-Upscale is an AI model for fast image upscaling up to 8 megapixels, offering target and factor modes with optional realism and detail enhancements.

A web scraping tool that extracts emails, phone numbers, social links, and HTML/text content from websites. Available on Replicate and open source.

zsxkib/embedding-gemma-300m is a Replicate deployment of Google's EmbeddingGemma-300M model for generating 768-dimensional text embeddings, supporting flexible output dimensions via Matryoshka representation learning.

fofr/expression-editor is an open-source model for editing facial expressions, available on Replicate with a cost of ~$0.0073 per run and typical completion time of 8 seconds.

video-utils is a video processing utility hosted on Replicate, with over 18 million runs and available for use via playground and API.

moondream2 is a compact vision language model designed for efficient edge device inference, with benchmark results and usage instructions provided.

GFPGAN is a practical face restoration model by Tencent ARC, available on Replicate. It restores old or low-quality face images with high fidelity.

851-labs/background-remover is an open-source AI model for removing backgrounds from images, available on Replicate with low cost and fast inference on Nvidia T4 GPUs.

abiruyt/text-extract-ocr is an open-source OCR model available on Replicate, running on CPU with low cost and fast inference.

An AI model for removing image backgrounds, using the tracer_b7 neural network, available on Replicate with open-source code.

fottoai/remove-bg-2 is an open-source background removal model available on Replicate, running on A100 GPUs with ~2s inference time and $0.0018 per run.

This is a page for the Animagine XL v4 Opt model, an open-source fine-tune of Stable Diffusion XL optimized for anime-style image generation, available via Replicate.

A CLIP-based embedding model hosted on Replicate that generates 768-dimensional embeddings for both images and text using the clip-vit-large-patch14 architecture, costing ~$0.00022 per run.