Latent Consistency Models (v1.5/XL)

URL or the path to the embedding weights.

Path

The list of tokens to use for the embedding.

Tokens

Embedding

Detail

HTTPValidationError

Content Type

Height

Width

Image

ImageSize

If set to true, the safety checker will be enabled.

Enable Safety Checker

If set to true, the prompt will be expanded with additional prompts.

Expand Prompt

Format


            The CFG (Classifier Free Guidance) scale is a measure of how close you want
            the model to stick to your prompt when looking for a related image to show you.
        

Guidance scale (CFG)

Image Size

The URL of the image to use as a starting point for the generation.

Image Url

Model Name


            The negative prompt to use.Use it to address details that you don't want
            in the image. This could be colors, objects, scenery and even the small details
            (e.g. moustache, blurry, low resolution).
        

Negative Prompt

Num Images

The number of inference steps to perform.

Num Inference Steps

The prompt to use for generating the image. Be as descriptive as possible for best results.

Prompt

The version of the safety checker to use. v1 is the default CompVis safety checker. v2 uses a custom ViT model.

Safety Checker Version


            The same seed and the same prompt given to the same version of Stable Diffusion
            will output the same image every time.
        

Seed

determines how much the generated image resembles the initial image

Strength


            If set to true, the function will wait for the image to be generated and uploaded
            before returning the response. This will increase the latency of the function but
            it allows you to get the image directly in the response without going through the CDN.
        

Sync Mode

ImageToImageLCMInput

The URL of the mask to use for inpainting.

Mask Url

InpaintingLCMInput

URL or the path to the LoRA weights. Or HF model name.


            The scale of the LoRA weight. This is used to scale the LoRA weight
            before merging it with the base model.
        

Scale

LoraWeight

Whether the generated images contain NSFW concepts.

Has Nsfw Concepts

Images

The prompt used for generating the image.


            Seed of the generated Image. It will be the same value of the one passed in the
            input or the randomly generated that was used in case none was passed.
        

Timings

Output


            The negative prompt to use. Use it to address details that you don't want
            in the image. This could be colors, objects, scenery and even the small details
            (e.g. moustache, blurry, low resolution).
        

Latent Consistency Models (v1.5/XL)

Input

Result

Logs