Chat History
Image Generator (Extended)
Image is not selected
Scale for classifier-free guidance (min: 1; max: 20)
Number of denoising steps. The value accepts 21,31,41 and 51.
How strictly the diffusion process adheres to the prompt text (higher values keep your image closer to your prompt)
Number of diffusion steps to run.
Seed is used to reproduce results, same seed will give you same image in return again. Pass 0 for a random number.
You can see a list of available models here (filter by type LoRA)
Limits per hour: 12 images for all visitors and up to 2 requests from a single visitor.
Used: 0 images, 0 requests.
Image Generator (Extended) 2var
Image is not selected
Limits per hour: 12 images for all visitors and up to 2 requests from a single visitor.
Used: 0 images, 0 requests.
Audio Generator
Audio is not selected
The speed of the generated audio. Select a value from 0.25 to 4.0. Default is 1.0
The sampling temperature, between 0 and 1. Default is 0. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic.
Rate of control for generated voice leakage (between 0 and 1). Higher values bias model towards training data. Default is 0.5
Median filtering length to reduce voice artifacts (floating point between 0 and 3). Default is 3.
Controls similarity to original vocals' voiceless constants (floating point between 0 and 1). Default is 0.33.
List of voices: modelslab.com
List of models: modelslab.com
Voice is not selected
Limits per hour: 12 audios for all visitors and up to 2 requests from a single visitor.
Used: 0 audios, 0 requests.
Music Generator
Mgenerator: AI Music Generator is not available - token for access to the API for music generation is not specified