--- license: creativeml-openrail-m language: - en base_model: - OnomaAIResearch/Illustrious-XL-v2.0 - MidnightRunner/MDNT_Illus tags: - SDXL - mdnt-illus - 3D-hybrid - anaglyph - photoreal - cinematic - text-to-image - ComfyUI - Automatic1111 - diffusers pipeline_tag: text-to-image library_name: diffusers metrics: - FID - IS widget: - text: >- (masterpiece), extremely aesthetic, newest, very vibrant colors, (ultra-HD), (cinematic lighting), (photorealistic), high detail, depth of field, best quality, absurdres, parameters: negative_prompt: >- bad hands, extra digits, (multiple views:1.1), (bad:1.05), fewer, extra, missing, worst quality, jpeg artifacts, bad quality, watermark, unfinished, displeasing, sepia, sketch, flat color, signature, artistic error, username, scan, (blurry, lowres, worst quality, (low quality:1.1), ugly, (bad anatomy:1.05), artist name, (patreon username:1.2) output: url: mdnt_illus_3d_sample.jpeg --- # MDNT_Illus_3D Model type: diffusion-based text-to-image Base model: Illustrious XL v2.0 Merged with: MIDNIGHT Illustrious, MDNT_Illus, Hyphorias, Nova3D-CGXL, BetterDaysIllus License: CreativeML Open RAIL++-M ## Model description MDNT_Illus_3D is a precision finetune focused on a 3D-hybrid aesthetic, balancing photoreal fidelity with simulated depth and sculpted form. It emphasizes anaglyphic layering, volumetric lighting, cinematic depth of field, and richly detailed textures to produce imagery that feels tactile, immersive, and dramatically lit. ## Usage recommendations ### Sampling methods - Euler A (Euler ancestral) - DPM++ 2M Karras - DPM++ 2M SDE Karras - DPM++ 3M SDE Exponential ### Settings - Steps: 25–45 - CFG scale: 4 (range 3–4) - Clip skip: 1 ### Workflow Compatible with ComfyUI and Automatic1111. A tailored ComfyUI workflow may be added later to maximize spatial layering and volumetric light behavior. ## Prompt guidance Positive (example) ``` realistic, photorealistic, very aesthetic, best quality, absurdres, masterpiece, amazing quality, newest, scenery, depth of field, high-resolution, high definition, visually intense anaglyphic experience, volumetric lighting, cinematic, sculpted 3D form ``` Negative (example) ``` bad hands, extra digits, (multiple views:1.1), (bad:1.05), fewer, extra, missing, worst quality, jpeg artifacts, watermark, unfinished, sketch, flat color, signature, artist name, blurry, lowres, (bad anatomy:1.05), (patreon username:1.2) ``` ## Version changes / notes - v1.0 (initial release) - Introduces 3D-hybrid realism with anaglyphic depth and volumetric lighting - Blended with Hyphorias, Nova 3DCG XL, BetterDaysIllus for expanded range ## Acknowledgments Base: Illustrious XL v2.0 Merges: MIDNIGHT Illustrious, MDNT_Illus, Hyphorias, Nova 3DCG XL, BetterDaysIllus ## Additional Resources - **Creative Solutions and Services:** [Magnabos.co](https://magnabos.co/) ## License This model is licensed under the [CreativeML Open RAIL++-M License](https://github.com/CompVis/stable-diffusion/blob/main/LICENSE). By using this model, you agree to the terms and conditions outlined in the license.