qwen/qwen-image-edit-plus-lora

Qwen Image Edit 2509 LoRA explorer, uses HuggingFace URLs to load any safetensor

Capabilities

Reference ImagesSeed

Cost

Community model (estimated from hardware time)

Input Parameters

Name	Type	Description	Default	Constraints
`image`*	array	Images to use as reference. Must be jpeg, png, gif, or webp.	`—`	—
`prompt`*	string	Text instruction on how to edit the given image.	`—`	—
`aspect_ratio`	string	Aspect ratio for the generated image	`"match_input_image"`	1:116:99:164:33:4match_input_image
`disable_safety_checker`	boolean	Disable safety checker for generated images.	`false`	—
`go_fast`	boolean	Run faster predictions with additional optimizations.	`true`	—
`lora_scale`	number	Strength applied to the selected LoRA.	`1`	min: 0, max: 4
`lora_weights`	string	LoRA weights to apply. Pass a Hugging Face repo slug (for example 'owner/model') or a direct .safetensors/zip/tar URL such as 'https://huggingface.co/flymy-ai/qwen-image-lora/resolve/main/pytorch_lora_weights.safetensors'. Leave blank to run without a LoRA.	`""`	—
`output_format`	string	Format of the output images	`"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	`95`	min: 0, max: 100
`seed`	integer	Random seed. Set for reproducible generation	`—`	—

imagerequiredarray

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

promptrequiredstring

Text instruction on how to edit the given image.

aspect_ratiostring

Aspect ratio for the generated image

Default: "match_input_image"

1:116:99:164:33:4match_input_image

disable_safety_checkerboolean

Disable safety checker for generated images.

Default: false

go_fastboolean

Run faster predictions with additional optimizations.

Default: true

lora_scalenumber

Strength applied to the selected LoRA.

Default: 1min: 0, max: 4

lora_weightsstring

LoRA weights to apply. Pass a Hugging Face repo slug (for example 'owner/model') or a direct .safetensors/zip/tar URL such as 'https://huggingface.co/flymy-ai/qwen-image-lora/resolve/main/pytorch_lora_weights.safetensors'. Leave blank to run without a LoRA.

Default: ""

output_formatstring

Format of the output images

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: 95min: 0, max: 100

seedinteger

Random seed. Set for reproducible generation

Version: b37d69a6b944Updated: 7/25/2026436.2K runs