qwen-edit-apps/qwen-image-edit-plus-lora-next-scene 🔢🖼️📝✓❓ → 🖼️

⭐ Official ▶️ 4.2K runs 📅 Nov 2025 ⚙️ Cog 0.16.9 📄 Paper ⚖️ License

image-consistent-character-generation image-editing image-to-image

About

Next Scene – “Next beat” cinematic edits that keep subject identity while steering to the next camera move via the Next Scene LoRA

Example Output

Prompt:

"Next Scene: The camera pulls back to reveal the entire landscape"

Output

Performance Metrics

38.22s Prediction Time

38.23s Total Time

All Input Parameters

{
  "image": "https://replicate.delivery/pbxt/O3fiuTB3N374OG5EWNd0KxNfAJ5gwbzm6uspz1h45MHtLeM2/image.png",
  "prompt": "Next Scene: The camera pulls back to reveal the entire landscape",
  "lora_scale": 1.25,
  "aspect_ratio": "match_input_image",
  "lora_weights": "",
  "output_format": "webp",
  "output_quality": 95,
  "true_guidance_scale": 1
}

Input Parameters

seed Type: integer: Random seed. Set for reproducible generation.
image (required) Type: string: Image file uploaded to Cog (jpeg, png, gif, or webp).
prompt Type: stringDefault: Next Scene: The camera glides forward as warm cinematic light reveals the wider setting.: Prompt hint: start with `Next Scene:` then describe the new camera move, framing, and lighting so the shot feels like the next beat in a cinematic sequence.
go_fast Type: boolean: If num_inference_steps is omitted, true runs the 8-step Lightning preset and false runs the 40-step detailed preset.
lora_scale Type: numberRange: 0 - 4: Strength applied to the selected LoRA. Leave blank for the proxy default.
aspect_ratio Default: match_input_image: Aspect ratio for the generated image
lora_weights Type: stringDefault:: LoRA weights to apply. Leave blank to use the proxy's default adapter.
output_format Default: webp: Format of the output images.
output_quality Type: integerDefault: 95Range: 0 - 100: Quality when saving the output images, from 0 to 100. 100 is best quality, 0 is lowest quality. Not relevant for .png outputs.
num_inference_steps Type: integerRange: 1 - 40: Explicit denoising step count (1-40). Leave blank to use the go_fast presets (fast = 8 steps, slow = 40 steps).
true_guidance_scale Type: numberDefault: 1Range: 0 - 10: True classifier-free guidance scale passed to the pipeline.
disable_safety_checker Type: booleanDefault: false: Disable safety checker for generated images.

Output Schema

Output

Type: array • Items Type: string • Items Format: uri

Example Execution Logs

Proxy call -> model=qwen/qwen-image-edit-plus-lora, adapter=lovis93/next-scene-qwen-image-lora-2509/next-scene_lora-v2-3000.safetensors, scale=1.25

Version Details

Version ID: 8a060e5c901515797bcfa1ab9050575be0dec05fa6c96e6decd3c6d4d8e17aa8
Version Created: November 14, 2025

Run on Replicate →