metadata
license: apache-2.0
base_model: Qwen/Qwen-VL
tags:
- lora
- qwen-image
- anime
- background
- visual-novel
language:
- en
pipeline_tag: text-to-image
library_name: peft
π¨ Anime Visual Novel Backgrounds LoRA
β‘ Current Version Stats
| Metric | Value |
|---|---|
| Training Images | 80 anime-style backgrounds generated by seedream-4 |
| LoRA Rank | 8 |
| Training Steps | 600 |
| Base Model | Qwen-Image-Edit |
| Trigger Word | anim3bg |
| Recommended Weight | 0.7 - 0.9 |
πΈ Example Outputs: Before vs After Comparison (Simple Prompts)
Testing how well the LoRA performs with minimal prompt detail
Example 1:
β Without LoRA![]() Prompt: anime-style background, library |
β
With LoRA (trigger word 'anim3bg')![]() Prompt: anim3bg, library |
Example 2:
β Without LoRA![]() Prompt: anime-style background, forest path |
β
With LoRA (trigger word 'anim3bg')![]() Prompt: anim3bg, forest path |
Example 3:
β Without LoRA![]() Prompt: anime-style background, school courtyard |
β
With LoRA (trigger word 'anim3bg')![]() Prompt: anim3bg, school courtyard |
Example 4:
β Without LoRA![]() Prompt: anime-style background, park pathway |
β
With LoRA (trigger word 'anim3bg')![]() Prompt: anim3bg, park pathway |
Example 5:
β Without LoRA![]() Prompt: anime-style background, train station |
β
With LoRA (trigger word 'anim3bg')![]() Prompt: anim3bg, trains station |
πΈ Example Outputs: Before vs After Comparison (Detailed Prompts)
Testing how well the LoRA handles complex, detailed descriptions
Example 6:
β Without LoRA![]() Prompt: anime-style background, mountain lake at sunset, narrow japanese alley, neon signs with japanese text, vending machines, bicycle parked on street |
β
With LoRA (trigger word 'anim3bg')![]() Prompt: anim3bg, mountain lake at sunset, narrow japanese alley, neon signs with japanese text, vending machines, bicycle parked on street |
Example 7:
β Without LoRA![]() Prompt: anime-style background, beach with wooden boardwalk, seagulls flying, beach umbrellas and chairs in distance, white foam on turquoise water |
β
With LoRA (trigger word 'anim3bg')![]() Prompt: anim3bg, beach with wooden boardwalk, seagulls flying, beach umbrellas and chairs in distance, white foam on turquoise water |
Example 8:
β Without LoRA![]() Prompt: anime-style background, traditional japanese garden at night, stone lanterns with warm glowing light, wooden arched bridge over koi pond, koi fish swimming |
β
With LoRA (trigger word 'anim3bg')![]() Prompt: anim3bg, traditional japanese garden at night, stone lanterns with warm glowing light, wooden arched bridge over koi pond, koi fish swimming |
Example 9:
β Without LoRA![]() Prompt: anime-style background, park pathway in autumn with falling maple leaves, ornate street lamp, wooden bench, no people |
β
With LoRA (trigger word 'anim3bg')![]() Prompt: anim3bg, park pathway in autumn with falling maple leaves, ornate street lamp, wooden bench, no people |
Example 10:
β Without LoRA![]() Prompt: anime-style background, |
β
With LoRA (trigger word 'anim3bg')![]() Prompt: anim3bg, |
π Version History
Version 2.0 (Current)
Training Configuration
- Dataset: 80 images
- Steps: 600
- LoRA Rank: 8
- Learning Rate: 0.0001
- Batch Size: 1
Version 1.0
Training Configuration
- Dataset: 80 images
- Steps: 1000
- LoRA Rank: 16
- Learning Rate: 0.0004
- Batch Size: 1
π¬ Trigger Word
Required: anim3bg
π Usage
Simple Prompts:
anim3bg, [location]
Detailed Prompts:
anim3bg, [detailed location description], [time], [weather], no characters, high quality
π₯ Download & Use
- Download
anime_background_lora.safetensors - Load in Wavespeed AI or compatible platform
- Set weight to 0.8
- Include
anim3bgtrigger word in prompt - Generate!



















