CivArchive
    2025-08-30-15-37-22-another-midjourney-release-old-man - V3
    NSFW
    Preview undefined
    Preview undefined
    Preview undefined

    The Storyline

    A data scientist embarks on an ambitious project: to use artificial intelligence to preserve a piece of their personal history. The goal is to train a model to generate images of their "father," their "grandfather," and even an image combining the two.

    The project starts with a collection of 73 image files. These images are not just data; they are memories, moments captured in time. The AI begins its arduous task of learning, processing the images over 18 epochs. The training logs reveal the struggle of this process, with the system encountering technical warnings and a loss function that slowly decreases, indicating the model is learning but the process is challenging and takes many hours.

    The AI, named Illustrious, diligently works through the provided photos, learning the nuances of each person's face. The progress is a long, methodical journey, documented by the regular saving of intermediate checkpoints after each epoch.

    In the end, the AI succeeds, creating a new image that combines the features of both their father and grandfather. The final output isn't just a generated image; it's a testament to the power of AI to create something new from cherished memories, a digital family portrait that couldn't exist in the real world.

    {
      "training_parameters": {
        "engine": "kohya",
        "loraType": "lora",
        "resolution": 1024,
        "maxTrainEpochs": 18,
        "trainBatchSize": 4,
        "targetSteps": 9855,
        "learning_rate": 0.0005,
        "unet_lr": 0.0005,
        "text_encoder_lr": 5e-5,
        "network_dim": 32,
        "network_alpha": 16,
        "lr_scheduler": "cosine_with_restarts",
        "lr_scheduler_num_cycles": 3,
        "min_snr_gamma": 5.0,
        "noise_offset": 0.1,
        "clip_skip": 1,
        "optimizer_type": "Adafactor",
        "save_every_n_epochs": 1,
        "sample_every_n_epochs": 1,
        "shuffleCaption": true,
        "flipAugmentation": true,
        "keepTokens": 3,
        "save_precision": "bf16",
        "mixed_precision": "bf16"
      },
      "dataset_configuration": {
        "num_repeats": 30,
        "image_resolution": 1024,
        "caption_extension": ".txt",
        "enable_bucket": true,
        "bucket_reso_steps": 64,
        "min_bucket_reso": 256,
        "max_bucket_reso": 2048,
        "files": 73
      },
      "sample_prompts": [
        {
          "prompt": "my father"
        },
        {
          "prompt": "my grandfather"
        },
        {
          "prompt": "my father and my grandfather"
        }
      ]
    }

    Description

    Illustrious AI Model

    Illustrious is a next-generation AI model specifically fine-tuned for generating high-quality anime and illustration-style images. It is a derivative of Stable Diffusion XL (SDXL), a popular family of image generation models. The orig file you provided indicates that your LoRA model was trained on the Illustrious base model.

    Unlike more general-purpose models like SDXL, Illustrious has been trained on a massive dataset of anime and illustration art, which gives it several key advantages.

    Illustrious vs. Other Models

    Illustrious vs. SDXL:

    • Illustrious is a specialized version of the general-purpose SDXL.

    • It excels in character depiction, with improved handling of hands, feet, and faces, which were often problem areas for earlier SDXL models.

    • Illustrious maintains the high-quality background and object generation capabilities of SDXL while significantly improving character-focused art.

    Illustrious vs. Pony:

    • Pony Diffusion is another popular SDXL-based model for anime and illustration.

    • Illustrious is often considered a "better" or more advanced alternative to Pony.

    • A key difference is that Illustrious has superior prompt adherence, meaning it follows complex and detailed prompts more accurately than Pony.

    • Illustrious also has a more extensive knowledge of anime characters and art styles, and it handles artist tags better than Pony.

    • While Pony's base model sometimes struggles with non-character objects, Illustrious is generally more versatile and consistent.

    Illustrious is a powerful tool for creators, offering a specialized model that combines the strengths of the SDXL architecture with a deep focus on anime and illustration.

    Explicit Content
    This group contains terms related to male nudity and sexual acts. It is found across multiple files and describes a variety of scenarios and details about the subjects' bodies.
    
    
    penis, male focus, realistic, 1boy, solo, nipple piercing, nude, testicles, navel, piercing, foreskin, nipples, pubic hair, looking at viewer, black hair, male pubic hair, flaccid, facial hair, plump, uncensored, bara, pectorals, short hair, completely nude, erection, fat, chest hair, sitting, muscular male, thick thighs, squatting 
    
    
    penis, nipples, muscular male, solo, bara, chest hair, muscular, ring, pectorals, navel, jewelry, erection, large pectorals, short hair, nude, arm hair, testicles, abs, thighs, leg hair, realistic, thick thighs, hairy, veins, completely nude, nipple piercing, male pubic hair, stomach 
    
    
    male focus, veins, ring, nipple piercing, bara, penis, nipples, muscular male, muscular, chain PA, PA insertion, chain insert in urethra, chain PA, padlock insert, padlock PA, nsfw, hyperrealistic photo 
    
    
    male focus, ring, nipple piercing, solo, penis, nipples, piercing, muscular male, pants, realistic, muscular, bara, pectorals, erection, jewelry, veins, navel, belt, looking at viewer, short hair, large pectorals, motor vehicle, sitting, car, uncensored, abs, testicles, closed mouth, black hair, chain insert into urethra, urethral chain insertion, chain in urethra, padlock chain urethra, PA, padlock PA, chain PA 
    The Subject: Chweeee1
    This group contains descriptions of a subject referred to as "chweeee1" and his various attributes and actions.
    
    
    chweeee1 is a middle-aged man with a slightly chubby physique, wearing a blue striped shirt and beige pants, holding his large erect cock with his right hand.
    
    
    chweeee1 is a muscular older man with gray hair and beard, sitting on a wooden bench, naked, holding his large erect cock with a chain around it.
    
    
    chweeee1 is a muscular Asian man with very large muscles, shirtless, wearing white shorts, standing against a plain white wall.
    
    
    chweeee1 has short dark hair, glasses, muscular legs, serious expression, green grass in foreground.
    
    
    Settings and Contexts
    These phrases describe the various backgrounds and environments where the subjects are located.
    
    
    standing in a modern office-like room, medium close-up, eye-level angle, realistic style, realistic lighting, artificial lighting, no watermark, JPEG artifacts 
    
    
    sitting on a bed, naked, cock erect, circumcised, hairy chest and legs, gray hair, beard, medium build, tan skin 
    
    
    sitting in the driver's seat of a car, shirtless, wearing blue and white patterned pajama pants 
    
    
    standing in a church, other men in suits sitting in pews in the background, stained glass windows 
    
    
    outdoors, collared shirt, short sleeves, leg hair, photo background, photograph of chweeee1, medium shot, eye-level angle 
    
    
    standing against a plain white wall, sunlight casting shadows on his body 
    
    
    Photography and Technical Details
    This group includes technical descriptions of the images, such as camera models, lighting, and other photographic elements.
    
    
    Canon EOS 5D Mark IV, f/8, 1/125 sec, ISO 400, medium depth of field, background slightly blurred 
    
    
    Canon EOS 5D Mark IV, 50mm lens, f/2.8 aperture, 1/100 sec shutter speed, ISO 400, no JPEG artifacts 
    
    
    Canon EOS 5D Mark IV, f/2.8, 1/125 sec, ISO 400, artificial lighting, dark tiled wall in the background 
    
    
    Canon EOS 5D Mark IV, 50mm lens, f/1.8 aperture, 1/100s shutter speed, ISO 400, no watermark, no JPEG artifacts, realistic, detailed 
    
    
    Canon EOS 5D Mark IV, 85mm lens, f/1.8 aperture, 1/200 sec shutter speed, ISO 400, detailed skin texture, realistic lighting, soft shadows, no JPEG artifacts 
    
    
    realistic lighting, leading lines from pews, rule of thirds, background in focus, depth of field 
    
    
    Canon EOS 5D Mark IV, 50mm lens, f/1.8, 1/250s, ISO 100, depth of field with the background slightly blurred, medium wide shot, leading lines from the car door and seat 
    
    
    Canon DSLR camera, likely aperture f/8, shutter speed 1/250s, ISO 100, medium to high aesthetic quality, chweeee1 has short dark hair 
    
    
    
    LORA
    Illustrious

    Details

    Downloads
    1
    Platform
    CivitAI
    Platform Status
    Available
    Created
    8/31/2025
    Updated
    8/25/2026
    Deleted
    -
    Trigger Words:
    bara

    Files

    2025-08-30-15-37-22-another-midjourney-release-old-man.safetensors