Fofr
Rank:Average Model Cost: $0.0039
Number of Runs: 3,709,271
Models by this creator
sdxl-emoji
sdxl-emoji
The SDXL-Emoji model is a text-to-image AI model that generates images based on descriptive text input. This fine-tuned model uses prompts supplied in its input schema, such as "A TOK emoji of a man", to create emoji-like images. The model allows adjustments for width and height of the output image, the degree of refinement, scheduling, scale, quantity of outputs, guidance scale, application of watermark, noise fraction, prompt strength and inference steps. The output of the model is an image URL. The model is specifically designed to generate Apple Emoji-like images.
$-/run
1.6M
Replicate
prompt-classifier
prompt-classifier
The model, prompt-classifier, is a text-to-text model that analyzes the toxicity of text-to-image prompts. Based on a fine-tuned version of the llama-13b model, it assigns a safety ranking between 0 (safe) and 10 (toxic). The model requires certain parameters such as "top_k", "top_p", "prompt", "temperature", "max_new_tokens", "min_new_tokens", and "stop_sequences". It returns a safety ranking for the prompt.
$-/run
1.2M
Replicate
sdxl-emoji
sdxl-emoji
The SDXL-Emoji is an image-to-image model designed to generate digital illustrations based on Apple Emojis. To accomplish this, the model utilizes a combination of algorithms and parameters, which result in a unique model's input schema. Upon receiving a description, such as "A TOK emoji of a man", the model will generate a corresponding image, akin to the style of Apple Emojis whilst adhering to the other parameters like width, height, scheduler, lora scale etc. The model's output is a URL link to a .png image that fulfills the criteria of the prompt.
$-/run
690.3K
Replicate
audio-to-waveform
The audio-to-waveform model takes an audio file as input and generates a video with a visual representation of the audio waveform. This model is useful for tasks such as creating visualizations of audio tracks or adding waveform visualizations to videos.
$0.002/run
158.0K
Replicate
sdxl-barbie
sdxl-barbie is an image-to-image model that is based on the SDXL lora architecture and has been fine-tuned on images from the Barbie movie. The model is designed to generate images that are similar in style to the Barbie movie, allowing users to transform images into the vibrant and colorful aesthetic of the movie.
$-/run
12.3K
Replicate
sdxl-2004
sdxl-2004
The sdxl-2004 is a model specifically designed for image-to-image tasks. Developed based on digital photography from 2004, it can transform input images according to specific prompts. The model has been fine-tuned to accept an input of image parameters such as width, height, prompt, refining parameters, guidance scale, noise level, negative prompt, and output strength. It produces an image as an output corresponding to these input parameters. The objective is to enhance, refine, and stylize the image in a specific way, as indicated by the input prompts, all while maintaining a 2004-styled aesthetic. The model doesn't apply any watermarks on the resulting outputs.
$-/run
7.7K
Replicate
sdxl-tron
The sdxl-tron model is a fine-tuned version of the SDXL lora model, based on the Tron Legacy movie. It is designed to generate new images based on text input, using a combination of text-to-image conversion techniques. This model is a useful tool for researchers and developers working on text-to-image generation tasks.
$-/run
7.3K
Replicate
latent-consistency-model
$-/run
4.0K
Replicate