Nateraw
Rank:Average Model Cost: $0.0014
Number of Runs: 1,192,044
Models by this creator
vit-age-classifier
vit-age-classifier
The vit-age-classifier model is an image classification model that can predict the age of a person based on an input image. It utilizes the Vision Transformer (ViT) architecture, which combines the power of transformers and convolutional neural networks (CNN) for image analysis. The model is trained on a large dataset of labeled images to accurately classify the age groups.
$-/run
1.0M
Huggingface
bert-base-uncased-emotion
$-/run
69.6K
Huggingface
stable-diffusion-videos
stable-diffusion-videos
The stable-diffusion-videos model is a tool that generates videos by interpolating the latent space of Stable Diffusion. It is designed to be used by technical users who have a good understanding of Stable Diffusion and can leverage its latent space to create visually appealing and coherent video sequences.
$-/run
53.5K
Replicate
qrcode-stable-diffusion
The qrcode-stable-diffusion model is an AI model that generates stylish QR codes using stable diffusion. QR codes are two-dimensional barcodes that contain information and can be scanned using smartphones. This model uses stable diffusion, a technique that helps create high-resolution, stable, and visually appealing QR codes. The generated QR codes can be customized with different colors, patterns, and other design elements. This model offers a convenient way to create unique and attractive QR codes for various applications.
$0.014/run
22.6K
Replicate
audio-super-resolution
audio-super-resolution
The audio-super-resolution model, also known as AudioSR, is an AI model created to enhance the quality of audio files. Using the provided URL of an audio file, the model applies a super-resolution process to increase the quality of the sound. The model's input schema requires a seed, ddim_steps, an input_file URL, and a guidance scale. The output produced by the model is a URL where the super-resolution audio file can be accessed. The model's primary focus is on versatility and scalability in enhancing audio quality.
$-/run
7.5K
Replicate
mistral-7b-openorca
mistral-7b-openorca
Mistral-7B-OpenOrca is a text-to-text model fine-tuned with the OpenOrca dataset. It has a pre-set input template that prompts for user queries and formats the response. The model holds discourse by writing out reasoning step-by-step for accurate responses. For every user input, the model generates a detailed explanation. It is suitable for applications that require in-depth context-based conversation.
$-/run
5.7K
Replicate
bge-large-en-v1.5
$-/run
3.1K
Replicate
wizard-mega-13b-awq
wizard-mega-13b-awq
The wizard-mega-13b-awq model, tagged as Text-to-Text, is a textual input and output model with automated weight quantization and service provisioning through vLLM. It receives as input variables such as a message, top_k, top_p, temperature, max_new_tokens, and presence_penalty in a specific format. It uses these parameters to generate a relevant response as output, which is a piece of well-generated text. In the given example, it creates an itinerary for a dog's birthday party based on the input request.
$-/run
3.0K
Replicate
openchat_3.5-awq
openchat_3.5-awq
OpenChat: Advancing Open-source Language Models with Mixed-Quality Data
$-/run
2.8K
Replicate
vit-base-beans
$-/run
1.9K
Huggingface