Qwen Edit Multiangle
Camera-aware Qwen editing for angle, tilt, zoom, and wide-angle changes.
Camera-aware Qwen editing for angle, tilt, zoom, and wide-angle changes.
Qwen Edit Multiangle is a specialized edit node for changing viewpoint rather than general image generation. Controls include rotation, vertical tilt, move-forward, wide-angle, LoRA scale, guidance, steps, quality, and seed.
Use it when camera position is the edit. For ordinary object or style changes, use Qwen Image Edit or Edit Plus.
Image
StringImage file uploaded to Cog (jpeg, png, gif, or webp).
Prompt
StringOptional text instruction appended after the camera directive.
Seed
NumberRandom seed. Set for reproducible generation.
Prompt
StringOptional text instruction appended after the camera directive.
Go Fast
BooleanIf num_inference_steps is omitted, true runs the 4-step fast preset and false runs the 40-step detailed preset.
trueLora Scale
NumberStrength applied to the selected LoRA.
1.25Aspect Ratio
StringAspect ratio for the generated image
match_input_imageLora Weights
StringLoRA weights to apply. Pass a Hugging Face repo slug like 'dx8152/Qwen-Edit-2509-Multiple-angles' or a direct .safetensors/zip/tar URL (for example, 'https://huggingface.co/flymy-ai/qwen-image-lora/resolve/main/pytorch_lora_weights.safetensors', 'https://example.com/lora_weights.tar.gz', or 'https://example.com/lora_weights.zip').
dx8152/Qwen-Edit-2509-Multiple-anglesMove Forward
NumberMove the camera forward (zoom in). Higher values push toward a close-up framing.
0Output Format
StringFormat of the output images.
webpVertical Tilt
NumberVertical camera tilt. -1 = bird's-eye, 0 = level, 1 = worm's-eye.
0Output Quality
NumberQuality when saving the output images, from 0 to 100. 100 is best quality, 0 is lowest quality. Not relevant for .png outputs.
95Rotate Degrees
NumberCamera rotation in degrees. Positive rotates left, negative rotates right.
0Use Wide Angle
BooleanSwitch to a wide-angle lens instruction.
falseNum Inference Steps
NumberExplicit denoising step count (1-40). Leave blank to use the go_fast presets (4 or 40 steps).
1True Guidance Scale
NumberTrue classifier-free guidance scale passed to the pipeline.
1Disable Safety Checker
BooleanDisable safety checker for generated images.
falseAdvanced
StringConfigures advanced camera motion and LoRA parameters.
Output
InferredOutput
Nodespell Team
Type
Node
Status
Official
Package
Nodespell AI
Category
AI / Image / QwenInput
Output