<p>☕ <strong>Support My Work:</strong> If you enjoy my local tools and models and want to support me with real cents rather than just platform Buzz, you can do so here: <a target="_blank" rel="ugc" href="https://ko-fi.com/monsieurbaka">https://ko-fi.com/monsieurbaka</a>. Your support directly speeds up new software updates and model releases!</p><h3 id="klein-4b">Klein 4b </h3><p>Requested by hawaiianpizz. Surprisingly, the model (4b) performs quite well. In my opinion, the images need some refinement. I generated a showcase at 1440 by 896 - which is supposedly a bit too high for this model. In any case, give it a try. Version 9b is still the best option if you’re critically short on VRAM -&gt; download the Int4/int8 convrot version; it should work on most computers.</p><h2 id="anima">Anima</h2><p>In my opinion, Anima is a model designed for drawing characters, which it does very well. Geometry and architecture aren’t its strong suits. However, this Lora creates an interesting effect in the background of images, so I decided to release it. For some 3rd party loras it may be used as a background enhancer. Consider Klein 9b and Krea 2 to be the main releases.</p><h2 id="krea-2">Krea 2</h2><p>This release is specifically at the request of ElGordoAI.</p><h3 id="klein-9b">Klein 9b</h3><p>My personal favorite. The main release for this Lora model Klein 9b works absolutely wonderfully; it’s the only model that consistently renders English text and the expected geometry.</p><h2 id="visual-novel-backgrounds"><strong>Visual Novel Backgrounds</strong></h2><p>A new LoRA specialized in generating <strong>visual novel style backgrounds</strong>.</p><p>This LoRA is designed exclusively for creating <strong>backgrounds</strong> (backdrops / sceneries) in classic visual novel aesthetic.</p><h3 id="key-trigger-words">Key Trigger Words</h3><p><code>VNsprite, visual novel style, background,</code></p><h3 id="recommended-settings">Recommended Settings</h3><p>- <strong>Resolution:</strong> 1280×720, 1440×900</p><p>- <strong>Steps:</strong> 6-12 (good starting point)</p><p>- <strong>Sampler:</strong> res_multistep</p><p>Experimenting with different samplers and step counts can give varied and interesting results.</p><h3 id="style-description">Style Description</h3><p>The LoRA produces clean, atmospheric visual novel backgrounds with soft lighting, nice color harmony and a characteristic anime/VN look — perfect for school classrooms, serene nature scenes, forests, beaches, and everyday locations.</p><h3 id="quality-and-usage-tips">Quality &amp; Usage Tips</h3><p>- The better and more detailed your prompt — the better the result.</p><p>- If you struggle with writing prompts, I recommend using an LLM (like Grok or similar) and feeding it examples from the Showcase and Gallery.</p><h3 id="known-limitations-(klein-9b):"><strong>Known limitations (Klein 9b):</strong></h3><p>Occasional issues with complex architecture, precise perspective, shadows and lighting in very complicated scenes. In such cases try different seeds or do minor fixes in Photoshop/Post-processing.</p><h3 id="this-lora-works-very-well-for-img2img-editing.">This LoRA works very well for <strong>img2img editing</strong>.</h3><p>Example workflow:</p><p><strong>Base generation:</strong></p><p><code>VNsprite, visual novel style, background, classroom interior, [detailed description], bright midday sun high in the sky...</code></p><p><strong>Edit (img2img):</strong></p><p><code>Change to: VNsprite, visual novel style, background, [detailed description], night during heavy rain, dark stormy sky, heavy diagonal rain streaks, wet reflective surfaces, moody dramatic atmosphere...</code></p><p>If the model sometimes adds unwanted people/characters during editing — add <code>no humans, no characters</code> at the end of the prompt.</p><p>For maximum composition and geometry preservation, I recommend using <a target="_blank" rel="ugc" href="https://huggingface.co/dx8152/Flux2-Klein-9B-Consistency">this supporting LoRA </a>together with this one.</p><p>You can also try combining it with <a target="_blank" rel="ugc" href="https://civarchive.com/models/2554039">character LoRA</a> to create CG scenes, but results may be unpredictable with complex compositions.</p><h3 id="training-information">Training Information</h3><p>- <strong>Dataset:</strong> 95 images</p><p>- <strong>Main source:</strong> ~60 images from <em>Clannad</em></p><p>- <strong>Nature &amp; forests:</strong> ~20 images from <em>Everlasting Summer</em></p><p>- <strong>Modern buildings:</strong> ~15 images from <em>Love Money Rock'n'Roll</em></p>

Visual Novel Backgrounds

VNBack4b.safetensors

F2K4B

Anima

Krea 2

F2K9b

### You are viewing the default Readme template as no detailed model-card was provided by the model’s contributors. You can access the model files in the "Files and versions" tab.
#### Model files may be downloaded with ModelScope SDK or through git clone directly.

Download with ModelScope’s Python SDK
```bash
#Install ModelScope
pip install modelscope
```
```python
#Download with ModelScope’s Python SDK
from modelscope import snapshot_download
model_dir = snapshot_download('abdubambas12/backs4b')
```
Download with Git clone
```
git clone https://www.modelscope.ai/abdubambas12/backs4b.git
```

<p style="color: lightgrey;">If you are a contributor to this model, we invite you to promptly update the model card content according to <a href="https://www.modelscope.ai/docs/contribute/model-integration" style="color: lightgrey; text-decoration: underline;">the model contribution documentation</a>.</p>


Files with SHA256: eeb6a7212fcd940ab49fc0fb54ed1d1c09546e025673b141dcb715814caf16d5