β¨ Cinematic Stylization Β· Realistic Lighting Β· Enhanced 2.5D Depth
Noob from HaDeS v2 refines the balance between illustrated detail and environmental realism, establishing a polished 2.5D aesthetic with cinematic emotion.
It renders characters with near-tangible presence, illuminated by natural light and seamlessly integrated into realistic settings.
β Key Visual Traits:
π¨ 2.5D Stylization Core β merges sharp illustrative precision with volumetric shading and lifelike textures reminiscent of digital photography.
π€οΈ Realistic Lighting System β global light behavior and natural reflections; skin, fabrics, and materials react coherently to ambient conditions.
π Cinematic Color Tone β vibrant yet organic palettes, smooth contrast transitions, and nuanced skin tones.
πͺ Material Precision β expertly handles transparency, moisture, reflections, and complex fabrics without breaking realism or sharpness.
π§ Adaptive Rendering β reacts fluidly to a wide range of prompts, from intimate portraits to full scenic compositions, while maintaining aesthetic harmony.
βοΈ Recommended Settings (v2):
Sampler: Euler / Euler a
Steps: 28β35
CFG Scale: 3-5
Resolution: 1152Γ1536 or 1024x1536 or SDXL resolutions
VAE: baked
π‘ Notes:
Perfect for creators aiming for 2.5D expressive characters over realistic backgrounds, with polished and cohesive lighting control.
β DeViLDoNia / HaDeS
β¨ First Release Β· Noob AI Core Β· HaDeS Signature Refinement
Noob from HaDeS v1 marks the beginning of a brand-new branch in the illustrious from HaDeS lineup.
Unlike Illustrious from HaDeS, which was built on Illustrious XL, this model is based on Noob AI β adapted, refined, and reshaped with the HaDeS touch.
β Whatβs new in Noob from HaDeS v1:
π Style Variety β inherits Noob AIβs ability to shift between multiple artistic styles, from clean stylized illustration to semi-realistic scenes.
ποΈ Flexible Prompt Adherence β works reliably with both simple and complex prompts, producing diverse yet controlled outputs.
ποΈ Stability & Coherence β tuned for consistent generations, balancing detail with creative variety.
β‘ Foundation for a New Line β this first release sets the stage for future updates, combining Noob AIβs freedom with the refined direction of the HaDeS aesthetic.
π Recommended Settings (v1):
Sampler: Euler, Euler a (best results) or DPM++ 2M for more variety
Steps: 25β30
Resolution: 1024Γ1536 / 1152Γ1536
CFG Scale: 5β7
VAE: baked
π‘ Notes:
Noob from HaDeS is not a replacement for Illustrious from HaDeS β itβs a parallel path, built to explore new stylistic possibilities while keeping the HaDeS identity.
v1 is stable but experimental: expect consistent results even with minimal tweaking.
Future updates will further refine anatomy, lighting, and stylistic specialization.
β DeViLDoNia / HaDeS
NooB from HaDeS is a highly specialized Image generation AI Model of type Safetensors / Checkpoint AI Model created by AI community user DeViLDoNia. Derived from the powerful Stable Diffusion (Illustrious) model, NooB from HaDeS has undergone an extensive fine-tuning process, leveraging the power of a dataset consisting of images generated by other AI models or user-contributed data. This fine-tuning process ensures that NooB from HaDeS is capable of generating images that are highly relevant to the specific use-cases it was designed for, such as base model, refined, finetuned.
With a rating of 0 and over 0 ratings, NooB from HaDeS is a popular choice among users for generating high-quality images from text prompts.
Yes! You can download the latest version of NooB from HaDeS from here.
To use NooB from HaDeS, download the model checkpoint file and set up an UI for running Stable Diffusion models (for example, AUTOMATIC1111). Then, provide the model with a detailed text prompt to generate an image. Experiment with different prompts and settings to achieve the desired results. If this sounds a bit complicated, check out our initial guide to Stable Diffusion β it might be of help. And if you really want to dive deep into AI image generation and understand how set up AUTOMATIC1111 to use Safetensors / Checkpoint AI Models like NooB from HaDeS, check out our crash course in AI image generation.
V1
Go ahead and upload yours!
Your query returned no results β please try removing some filters or trying a different term.