# Tornado - V3.0 >

🔸 Tornado V3 (The Quiet Voice) – Version Notes

Tornado V3 marks a meaningful shift in tone and technique. Where V2 was bold, loud, and brash — trying to be everything all at once — V3 takes a deep breath and grows up. It doesn't chase spectacle; it embraces nuance. This version is quieter, but more self-assured.

It leans into elegance, focus, and painterly restraint. No longer seeking to impress by volume, V3 instead invites you in with its calm confidence and a more mature artistic voice.

This is an emerging voice. A quiet voice — but a firm one.

V3 finds Tornado stepping into its own stylistic niche: fine-art fantasy with painterly softness. It is intentionally biased toward painterly hues, dreamlike settings, and concept art with an artistic edge. The goal isn’t to mimic reality — it’s to elevate it.

That said, realism is absolutely possible. With prompt refinement, cleaner descriptor structure, and lighting cues, you can steer Tornado into subdued, grounded looks — but it naturally prefers a softer, surreal, aesthetic-first composition by default.

🔁 Because of this firm creative identity, Tornado V3 now holds pole position for future updates. Its vision is clear, and future work will aim to refine and deepen this established aesthetic rather than reinvent the wheel.

🧠 Prompting Behavior

V3 introduces semi-tag-style prompting — it's more responsive to clean descriptors, though still forgiving of longer sentence prompts.

Prompt adherence has noticeably improved, yielding more reliable compositions from the same core input.

Use a mix of artistic keywords (e.g. oil painting, cinematic, studio light, rimlight, concept art) for best results. Less is more.

👁️ Rendering Improvements

Eyes are improved but may still need help — ADetailer is recommended for best clarity, especially, however it handles eyes well in extreme close-ups.

Lighting behavior has matured: more controlled, more natural, with subtle cinematic contrast and painterly diffusion.

Texture fidelity is also stronger, especially in fabric, hair, and soft surface rendering. Details are much more pronounced.

🔞 NSFW Handling

NSFW rendering is better than V1 and V2, particularly in softer, more artistic nude studies.

However: Tornado V3 is not tuned for pornography, and it will not handle hardcore explicit prompts well. It avoids that space on purpose.

Best used for tasteful figure studies, romantic composition, or sensual fantasy illustration. Best results are found in artistic, romantic, or emotionally toned settings.

🎨 Stylistic Anchors

Soft anime and fine art were intentionally blended into this version’s training data. That influence is subtle but effective — visible in the graceful linework, pastel color palettes, and overall mood.

While not a full anime model, Tornado V3 shows a clear synergy with soft anime aesthetics, especially in expressive portraiture, ambient lighting, and character framing. It leans more painterly than toon-like — but the influence is undeniably present.

It is also naturally biased toward painterly softness and pastel color harmony — think muted lilacs, airy peaches, dreamy teals. However, if you prefer bold saturation or punchy palettes, just prompt with terms like “bright,” “colorful,” or “vibrant” — V3 handles them effortlessly.

V3 is biased toward painterly elegance — but knows how to be subtle when asked.

📸 Image Showcase Notes

⚙️ Recommended Use Cases

## Overview - **Model ID**: `tornado-v30` - **Category**: stable diffusion xl - **Provider**: modelslab - **Status**: model_ready - **Screenshot**: `https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/47d286e6-be01-40e1-8bd7-48bfcf7cfec6/width=720/79219205.mp4` ## API Information This model can be used via our HTTP API. See the API documentation and usage examples below. ### Endpoint - **URL**: `https://modelslab.com/api/v6/images/text2img` - **Method**: POST ### Parameters - **`prompt`** (required): prompt help in image generation - Type: textarea - Example: Enter prompt - **`model_id`** (required): Enter model_id that can help in image generation - Type: text - Example: Enter model_id here - **`lora_model`** (required): - Type: multiple_models - **`width`** (required): width of the image - Type: number (range: 512-1024) - **`height`** (required): height of the image - Type: number (range: 512-1024) - **`negative_prompt`** (optional): Negative prompt help in avoid things that you do not want in image - Type: textarea - Example: Enter negative prompt that you do not want see in image - **`scheduler`** (optional): - Type: select (options: DPM++ 2M, DPM++ SDE, Euler, Euler a) - **`guidance_scale`** (optional): - Type: number (range: 1-10) ## Usage Examples ### cURL ```bash curl --request POST \ --url https://modelslab.com/api/v6/images/text2img \ --header "Content-Type: application/json" \ --data '{ "key": "YOUR_API_KEY", "model_id": "tornado-v30", "prompt": "R3alisticF, hauntingly beautiful oriental necromancer, long flowing brown hair, bangs, darkly tanned skin, earrings, bone necklaces, dark eyeshadow, red lips, vibrant, front-laced transparent, filmy silk blouse, cleavage, holding skull, in a sandstone room lit by candles, High Detail, Perfect Composition, high contrast, silhouetted, chiascuro", "width": "1024", "height": "1024", "negative_prompt": "(worst quality:2), (low quality:2), (normal quality:2), (jpeg artifacts), (blurry), (duplicate), (morbid), (mutilated), (out of frame), (extra limbs), (bad anatomy), (disfigured), (deformed), (cross-eye), (glitch), (oversaturated), (overexposed), (underexposed), (bad proportions), (bad hands), (bad feet), (cloned face), (long neck), (missing arms), (missing legs), (extra fingers), (fused fingers), (poorly drawn hands), (poorly drawn face), (mutation), (deformed eyes), watermark, text, logo, signature, grainy, tiling, censored, nsfw, ugly, blurry eyes, noisy image, bad lighting, unnatural skin, asymmetry", "scheduler": "DPMSolverMultistepScheduler", "guidance_scale": "7.5" }' ``` ### Python ```python import requests response = requests.post( "https://modelslab.com/api/v6/images/text2img", headers={ "Content-Type": "application/json" }, json={ "key": "YOUR_API_KEY", "model_id": "tornado-v30", "prompt": "R3alisticF, hauntingly beautiful oriental necromancer, long flowing brown hair, bangs, darkly tanned skin, earrings, bone necklaces, dark eyeshadow, red lips, vibrant, front-laced transparent, filmy silk blouse, cleavage, holding skull, in a sandstone room lit by candles, High Detail, Perfect Composition, high contrast, silhouetted, chiascuro", "width": "1024", "height": "1024", "negative_prompt": "(worst quality:2), (low quality:2), (normal quality:2), (jpeg artifacts), (blurry), (duplicate), (morbid), (mutilated), (out of frame), (extra limbs), (bad anatomy), (disfigured), (deformed), (cross-eye), (glitch), (oversaturated), (overexposed), (underexposed), (bad proportions), (bad hands), (bad feet), (cloned face), (long neck), (missing arms), (missing legs), (extra fingers), (fused fingers), (poorly drawn hands), (poorly drawn face), (mutation), (deformed eyes), watermark, text, logo, signature, grainy, tiling, censored, nsfw, ugly, blurry eyes, noisy image, bad lighting, unnatural skin, asymmetry", "scheduler": "DPMSolverMultistepScheduler", "guidance_scale": "7.5" } ) print(response.json()) ``` ### JavaScript ```javascript fetch("https://modelslab.com/api/v6/images/text2img", { method: "POST", headers: { "Content-Type": "application/json" }, body: JSON.stringify({ "key": "YOUR_API_KEY", "model_id": "tornado-v30", "prompt": "R3alisticF, hauntingly beautiful oriental necromancer, long flowing brown hair, bangs, darkly tanned skin, earrings, bone necklaces, dark eyeshadow, red lips, vibrant, front-laced transparent, filmy silk blouse, cleavage, holding skull, in a sandstone room lit by candles, High Detail, Perfect Composition, high contrast, silhouetted, chiascuro", "width": "1024", "height": "1024", "negative_prompt": "(worst quality:2), (low quality:2), (normal quality:2), (jpeg artifacts), (blurry), (duplicate), (morbid), (mutilated), (out of frame), (extra limbs), (bad anatomy), (disfigured), (deformed), (cross-eye), (glitch), (oversaturated), (overexposed), (underexposed), (bad proportions), (bad hands), (bad feet), (cloned face), (long neck), (missing arms), (missing legs), (extra fingers), (fused fingers), (poorly drawn hands), (poorly drawn face), (mutation), (deformed eyes), watermark, text, logo, signature, grainy, tiling, censored, nsfw, ugly, blurry eyes, noisy image, bad lighting, unnatural skin, asymmetry", "scheduler": "DPMSolverMultistepScheduler", "guidance_scale": "7.5" }) }) .then(response => response.json()) .then(data => console.log(data)); ``` ## Links - [Model Playground](https://modelslab.com/models/community-model/tornado-v30) - [API Documentation](https://docs.modelslab.com) - [ModelsLab Platform](https://modelslab.com)