lucataco/kontext-meta-cars

Change your car into a CDMX Meta Car

Capabilities

Reference ImagesSeed

Community model (estimated from hardware time)

Name	Type	Description	Default	Constraints
`input_image`*	string(uri)	Image to use as reference. Must be jpeg, png, gif, or webp.	`—`	—
`prompt`*	string	Text description of what you want to generate, or the instruction on how to edit the given image.	`—`	—
`aspect_ratio`	string	Aspect ratio of the generated image. Use 'match_input_image' to match the aspect ratio of the input image.	`"match_input_image"`	1:116:921:93:22:34:55:43:44:39:169:21match_input_image
`disable_safety_checker`	boolean	Disable NSFW safety checker	`false`	—
`guidance`	number	Guidance scale for generation	`2.5`	min: 0, max: 10
`lora_strength`	number	Strength of the lora	`1`	—
`megapixels`	string	Approximate number of megapixels for generated image	`"1"`	10.25
`num_inference_steps`	integer	Number of inference steps	`30`	min: 4, max: 50
`output_format`	string	Output image format	`"webp"`	webpjpgpng
`output_quality`	integer	Quality when saving the output images, from 0 to 100. 100 is best quality, 0 is lowest quality. Not relevant for .png outputs	`80`	min: 0, max: 100
`replicate_weights`	string	Path to the lora weights	`—`	—
`seed`	integer	Random seed for reproducible generation. Leave blank for random.	`—`	—

input_imagerequiredstring

Image to use as reference. Must be jpeg, png, gif, or webp.

promptrequiredstring

Text description of what you want to generate, or the instruction on how to edit the given image.

aspect_ratiostring

Aspect ratio of the generated image. Use 'match_input_image' to match the aspect ratio of the input image.

Default: "match_input_image"

1:116:921:93:22:34:55:43:44:39:169:21match_input_image

disable_safety_checkerboolean

Disable NSFW safety checker

Default: false

guidancenumber

Guidance scale for generation

Default: 2.5min: 0, max: 10

lora_strengthnumber

Strength of the lora

Default: 1

megapixelsstring

Approximate number of megapixels for generated image

Default: "1"

10.25

num_inference_stepsinteger

Number of inference steps

Default: 30min: 4, max: 50

output_formatstring

Output image format

Default: "webp"

webpjpgpng

output_qualityinteger

Quality when saving the output images, from 0 to 100. 100 is best quality, 0 is lowest quality. Not relevant for .png outputs

Default: 80min: 0, max: 100

replicate_weightsstring

Path to the lora weights

seedinteger

Random seed for reproducible generation. Leave blank for random.

Version: 981b1881832bUpdated: 7/25/2026168 runs