Back to Nodes
Qwen Image Edit Relight

Qwen Image Edit Relight

Official

Relight provides soft, curtain-filtered relighting to change a scene's mood using golden-hour or moody tones.

Nodespell AI
AI / Image / Qwen

Relight provides soft, curtain-filtered relighting to change a scene's mood using golden-hour or moody tones.

Model Overview

Relight – A LoRA for soft, diffused lighting edits that paints scenes with golden-hour warmth or moody, cinematic glows. It's designed to subtly transform the lighting on images without altering the core composition.

Best At

Perfect for enhancing the ambiance of portraits, landscapes, and product photos by adding soft curtain-filtered light. Great for mood-based projects like storytelling, branding cobrands, or creating unique social media imagery.

Limitations / Not Good At

May struggle with dramatic lighting changes or high-contrast scenes. Edits can look less convincing with low-resolution inputs or images with complex, layered lighting setups.

Inputs (2)

Image

String

Image file uploaded to Cog (jpeg, png, gif, or webp).

Min: 0Max: 100

Prompt

String

Prompt hint: paste `重新照明,使用窗帘透光(柔和漫射)的光线对图片进行重新照明` (meaning “relight the scene with soft curtain-filtered light”), then continue in English with the mood or color temperature you want.

Multi InputMin: 0Max: 100
Parameters (12)

Seed

Number

Random seed. Set for reproducible generation.

Default: -1

Prompt

String

Prompt hint: paste `重新照明,使用窗帘透光(柔和漫射)的光线对图片进行重新照明` (meaning “relight the scene with soft curtain-filtered light”), then continue in English with the mood or color temperature you want.

Default: 重新照明,使用窗帘透光(柔和漫射)的光线对图片进行重新照明, 带来温暖的日落氛围. Relight with soft window glow and golden-hour warmth.

Go Fast

Boolean

If num_inference_steps is omitted, true runs the 8-step Lightning preset and false runs the 40-step detailed preset.

Default: false

Lora Scale

Number

Strength applied to the selected LoRA. Leave blank for the proxy default.

Default: 0

Aspect Ratio

String

Aspect ratio for the generated image

Default: match_input_image

Lora Weights

String

LoRA weights to apply. Leave blank to use the proxy's default adapter.

Default:

Output Format

String

Format of the output images.

Default: webp

Output Quality

Number

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

Default: 95

Num Inference Steps

Number

Explicit denoising step count (1-40). Leave blank to use the go_fast presets (fast = 8 steps, slow = 40 steps).

Default: 1

True Guidance Scale

Number

True classifier-free guidance scale passed to the pipeline.

Default: 1

Disable Safety Checker

Boolean

Disable safety checker for generated images.

Default: false

Advanced

String
Default:
Outputs (1)

Output

Inferred

Output

Nodespell

Nodespell

📍 London

Building the future. Join us!

nodespell.comnodespell.appNodespellAI

Type

Node

Status

Official

Package

Nodespell AI

Category

AI / Image / Qwen

Input

Image

Output

Image

Keywords

Image Edit
Use in Workflow