license: apache-2.0 language:

• en base_model:
• Wan-AI/Wan2.1-T2V-14B pipeline_tag: text-to-video tags:
• text-to-video
• text-to-image
• lora
• diffusers
• template:diffusion-lora widget:
• text: >- f11m_n01r film noir, black and white video, a man in a dark trench coat and fedora stands under a flickering streetlamp in a deserted alley. Smoke drifts from a cigarette in his hand, and his face is partially obscured by the shadow of his hat. Rain slicks the pavement, reflecting the glow of distant headlights. output: url: example_videos/1.mp4
• text: >- f11m_n01r film noir, black and white video, a private investigator tails a suspect through a crowded speakeasy. The air is thick with cigarette smoke, and a jazz band plays softly as the suspect disappears into the shadows. output: url: example_videos/2.mp4
• text: >- f11m_n01r film noir, black and white video, two men in overcoats face off beneath an old iron bridge. One lights a match with a shaking hand, illuminating the barrel of a gun pointed at him. A train rumbles in the distance. output: url: example_videos/3.mp4
• text: >- f11m_n01r film noir, black and white video, a woman in a long coat and gloves leans against the bar, a half-empty glass of whiskey in front of her. A jazz band plays in the background, their silhouettes blurred by the hazy cigarette smoke that fills the dimly lit club. She glances toward the door as if waiting for someone. output: url: example_videos/4.mp4

Model File and Inference Workflow

📥 Download Links:

• film_noir_10_epochs.safetensors - LoRA Model File
• wan_txt2vid_lora_workflow.json - Wan T2V with LoRA Workflow for ComfyUI

---

Recommended Settings

• LoRA Strength: 1.0
• Embedded Guidance Scale: 6.0
• Flow Shift: 5.0

Trigger Words

The key trigger phrase is: f11m_n01r film noir, black and white video

Prompt Template

For prompting, check out the example prompts; this way of prompting seems to work very well.

ComfyUI Workflow

This LoRA works with a modified version of Kijai's Wan Video Wrapper workflow. The main modification is adding a Wan LoRA node connected to the base model.

See the Downloads section above for the modified workflow.

Model Information

The model weights are available in Safetensors format. See the Downloads section above.

Training Details

• Base Model: Wan2.1 14B T2V
• Training Data: Trained on 3 minutes of video comprised of 34 short clips (each clip captioned separately) of various Film Noir clips.
• Epochs: 10

Additional Information

Training was done using Diffusion Pipe for Training

Acknowledgments

Special thanks to Kijai for the ComfyUI Wan Video Wrapper and tdrussell for the training scripts!