Next Scene (Qwen Image Edit Lora 2509)

Use with workflow: /model/2065461?modelVersionId=2337222

🎉 ✨ UPDATE - Version 2 Now Available! (21 Oct 2025) ✨ 🎉

🚀 New Model: next-scene_lora-v2-3000.safetensors

What's New in V2:

• 🎯 Trained on higher quality data for significantly improved results

• 💪 Better command responsiveness - the model follows your prompts more accurately

• 🖼️ Fixed black bar artifacts - no more unwanted black borders on generated images

• ⚡ Overall enhanced performance - smoother transitions and better cinematic flow

Recommended: Use V2 for all new projects.

📥 ComfyUI Workflow: /model/2065461?modelVersionId=2337222

🧠 What This Model Does

This LoRA brings cinematic storytelling continuity into AI image generation workflows.

Each output frame functions as the "Next Scene" in an evolving visual narrative, maintaining compositional coherence while introducing organic transitions such as:

• Camera movement: Dolly shots, push-ins, pull-backs, and tracking moves

• Framing evolution: Wide to close-up transitions, angle shifts, reframing

• Environmental reveals: New characters entering frame, expanded scenery, spatial progression

• Atmospheric shifts: Lighting changes, weather evolution, time-of-day transitions

Examples of Cinematic Logic:

• "Next Scene: The camera pulls back from a tight close-up on the airship to a sweeping aerial view, revealing an entire fleet of vessels soaring through a fantasy landscape."

• "Next Scene: The camera tracks forward and tilts down, bringing the sun and helicopters closer into frame as a strong lens flare intensifies."

• "Next Scene: The camera pans right, removing the dragon and rider from view while revealing more of the floating mountain range in the distance."

  ______

next-scene-qwen-image-lora-2509 is a LoRA adapter fine-tuned on Qwen-Image-Edit (build 2509), purpose-built to generate cinematic image sequences with natural visual progression from frame to frame.

This model enables Qwen Image Edit to think like a film director—understanding camera dynamics, visual composition, and narrative continuity to create shots that flow seamlessly into one another.

🧠 What This Model Does

This LoRA brings cinematic storytelling continuity into AI image generation workflows.

Each output frame functions as the "Next Scene" in an evolving visual narrative, maintaining compositional coherence while introducing organic transitions such as:

• Camera movement: Dolly shots, push-ins, pull-backs, and tracking moves

• Framing evolution: Wide to close-up transitions, angle shifts, reframing

• Environmental reveals: New characters entering frame, expanded scenery, spatial progression

• Atmospheric shifts: Lighting changes, weather evolution, time-of-day transitions

Examples of Cinematic Logic:

• "Next Scene: The camera pulls back from a tight close-up on the airship to a sweeping aerial view, revealing an entire fleet of vessels soaring through a fantasy landscape."

• "Next Scene: The camera tracks forward and tilts down, bringing the sun and helicopters closer into frame as a strong lens flare intensifies."

• "Next Scene: The camera pans right, removing the dragon and rider from view while revealing more of the floating mountain range in the distance."

⚙️ Usage Instructions

Basic Setup:

1. Load Qwen-Image-Edit 2509 as your base model

2. Add a LoRA Loader node and select next-scene-qwen-image-lora-2509

3. Set LoRA strength: 0.7 – 0.8 (recommended)

4. Structure your prompts with "Next Scene:" prefix for optimal results

Example Prompt:

Next Scene: The camera moves slightly forward as sunlight breaks through the clouds, casting a soft glow around the character's silhouette in the mist. Realistic cinematic style, atmospheric depth.

Pro Tips:

• Begin prompts with camera direction for stronger continuity

• Specify lighting and atmospheric changes for mood consistency

• Chain multiple generations to create sequential storyboards

• Works particularly well with landscape and establishing shots

next-scene-qwen-image-lora-2509 is a LoRA adapter fine-tuned on Qwen-Image-Edit (build 2509), purpose-built to generate cinematic image sequences with natural visual progression from frame to frame.

This model enables Qwen Image Edit to think like a film director—understanding camera dynamics, visual composition, and narrative continuity to create shots that flow seamlessly into one another.

---

🧠 What This Model Does

This LoRA brings cinematic storytelling continuity into AI image generation workflows.

Each output frame functions as the "Next Scene" in an evolving visual narrative, maintaining compositional coherence while introducing organic transitions such as:

• Camera movement: Dolly shots, push-ins, pull-backs, and tracking moves

• Framing evolution: Wide to close-up transitions, angle shifts, reframing

• Environmental reveals: New characters entering frame, expanded scenery, spatial progression

• Atmospheric shifts: Lighting changes, weather evolution, time-of-day transitions

Examples of Cinematic Logic:

• "Next Scene: The camera pulls back from a tight close-up on the airship to a sweeping aerial view, revealing an entire fleet of vessels soaring through a fantasy landscape."

• "Next Scene: The camera tracks forward and tilts down, bringing the sun and helicopters closer into frame as a strong lens flare intensifies."

• "Next Scene: The camera pans right, removing the dragon and rider from view while revealing more of the floating mountain range in the distance."

---

⚙️ Usage Instructions

Basic Setup:

1. Load Qwen-Image-Edit 2509 as your base model

2. Add a LoRA Loader node and select next-scene-qwen-image-lora-2509

3. Set LoRA strength: 0.7 – 0.8 (recommended)

4. Structure your prompts with "Next Scene:" prefix for optimal results

Example Prompt:

Next Scene: The camera moves slightly forward as sunlight breaks through the clouds, casting a soft glow around the character's silhouette in the mist. Realistic cinematic style, atmospheric depth.

Pro Tips:

• Begin prompts with camera direction for stronger continuity

• Specify lighting and atmospheric changes for mood consistency

• Chain multiple generations to create sequential storyboards

• Works particularly well with landscape and establishing shots