prunaai/p-image-edit-lora

OfficialView on Replicate →

Use trained LoRAs from the https://replicate.com/prunaai/p-image-edit-trainer. Find or contribute LoRAs here: https://huggingface.co/collections/PrunaAI/p-image-edit-loras.

Capabilities

Seed

Cost

Community model (estimated from hardware time)

Input Parameters

Name	Type	Description	Default	Constraints
`lora_weights`*	string	Load LoRA weights. Supports HuggingFace URLs in the format huggingface.co/<owner>/<model-name>[/<lora-weights-file.safetensors>]. HuggingFace LoRAs may require an API token to access, which you can provide in the `hf_api_token` input.	`—`	—
`prompt`*	string	Text prompt for image generation. Make sure to describe your edit task clearly. You can refer to the images as 'image 1' and 'image 2' and so on.	`—`	—
`aspect_ratio`	string	Aspect ratio for the generated image. `match_input_image` will match the aspect ratio of the first image.	`"match_input_image"`	match_input_image1:116:99:164:33:43:22:3
`disable_safety_checker`	boolean	Disable safety checker for generated images.	`false`	—
`hf_api_token`	string(password)	HuggingFace API token. If you're using a HuggingFace LoRAs that needs authentication, you'll need to provide an API token.	`—`	—
`images`	array	Images to use as a reference. For editing task, provide the main image as the first image.		—
`lora_scale`	number	Determines how strongly the main LoRA should be applied.	`1`	min: -1, max: 3
`seed`	integer	Random seed. Set for reproducible generation.	`—`	—
`turbo`	boolean	If turned on, the model will run faster with additional optimizations. For complicated tasks, it is recommended to turn this off.	`true`	—

lora_weightsrequiredstring

Load LoRA weights. Supports HuggingFace URLs in the format huggingface.co/<owner>/<model-name>[/<lora-weights-file.safetensors>]. HuggingFace LoRAs may require an API token to access, which you can provide in the `hf_api_token` input.

promptrequiredstring

Text prompt for image generation. Make sure to describe your edit task clearly. You can refer to the images as 'image 1' and 'image 2' and so on.

aspect_ratiostring

Aspect ratio for the generated image. `match_input_image` will match the aspect ratio of the first image.

Default: "match_input_image"

match_input_image1:116:99:164:33:43:22:3

disable_safety_checkerboolean

Disable safety checker for generated images.

Default: false

hf_api_tokenstring

HuggingFace API token. If you're using a HuggingFace LoRAs that needs authentication, you'll need to provide an API token.

imagesarray

Images to use as a reference. For editing task, provide the main image as the first image.

Default:

lora_scalenumber

Determines how strongly the main LoRA should be applied.

Default: 1min: -1, max: 3

seedinteger

Random seed. Set for reproducible generation.

turboboolean

If turned on, the model will run faster with additional optimizations. For complicated tasks, it is recommended to turn this off.

Default: true

Version: 344e6631da82Updated: 9/20/2026372.0K runs