Qwen Image Edit Relight
Qwen relighting for changing the mood of an existing image.
Qwen relighting for changing the mood of an existing image.
Qwen Image Edit Relight is for lighting changes, not broad content replacement. It uses a relight-focused setup with strength, guidance, quality, step count, and seed controls.
Best when the composition is already right but the lighting direction, mood, or time-of-day feel needs a pass.
Image
StringImage file uploaded to Cog (jpeg, png, gif, or webp).
Prompt
StringPrompt 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.
Seed
NumberRandom seed. Set for reproducible generation.
Prompt
StringPrompt 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.
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
BooleanIf num_inference_steps is omitted, true runs the 8-step Lightning preset and false runs the 40-step detailed preset.
falseLora Scale
NumberStrength applied to the selected LoRA. Leave blank for the proxy default.
0Aspect Ratio
StringAspect ratio for the generated image
match_input_imageLora Weights
StringLoRA weights to apply. Leave blank to use the proxy's default adapter.
Output Format
StringFormat of the output images.
webpOutput Quality
NumberQuality when saving the output images, from 0 to 100. 100 is best quality, 0 is lowest quality. Not relevant for .png outputs.
95Num Inference Steps
NumberExplicit denoising step count (1-40). Leave blank to use the go_fast presets (fast = 8 steps, slow = 40 steps).
1True Guidance Scale
NumberTrue classifier-free guidance scale passed to the pipeline.
1Disable Safety Checker
BooleanDisable safety checker for generated images.
falseAdvanced
StringProvides additional configuration settings for fine-tuning the generation process.
Output
InferredOutput
Nodespell Team
Type
Node
Status
Official
Package
Nodespell AI
Category
AI / Image / QwenInput
Output