initial commit

.gitattributes

@@ -0,0 +1,55 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.lz4 filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+# Audio files - uncompressed
+*.pcm filter=lfs diff=lfs merge=lfs -text
+*.sam filter=lfs diff=lfs merge=lfs -text
+*.raw filter=lfs diff=lfs merge=lfs -text
+# Audio files - compressed
+*.aac filter=lfs diff=lfs merge=lfs -text
+*.flac filter=lfs diff=lfs merge=lfs -text
+*.mp3 filter=lfs diff=lfs merge=lfs -text
+*.ogg filter=lfs diff=lfs merge=lfs -text
+*.wav filter=lfs diff=lfs merge=lfs -text
+# Image files - uncompressed
+*.bmp filter=lfs diff=lfs merge=lfs -text
+*.gif filter=lfs diff=lfs merge=lfs -text
+*.png filter=lfs diff=lfs merge=lfs -text
+*.tiff filter=lfs diff=lfs merge=lfs -text
+# Image files - compressed
+*.jpg filter=lfs diff=lfs merge=lfs -text
+*.jpeg filter=lfs diff=lfs merge=lfs -text
+*.webp filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,165 @@
+---
+tags:
+- text-to-image
+- lora
+- diffusers
+- template:diffusion-lora
+widget:
+- output:
+    url: images/Image01_00234_.png
+  text: >-
+    Joaquin Phoenix, European male,  A black-and-white editorial portrait of a
+    man reclining in a vintage wooden rocking chair, positioned diagonally
+    across the frame. The chair has curved runners and a slightly worn texture,
+    emphasizing a timeless, intimate atmosphere. Pose & body language: The man
+    is half-reclined, legs relaxed and slightly bent, body sunk into the chair.
+    One arm is raised, holding an open book above chest level, tilted toward the
+    light source. The other arm rests casually along the chair, posture calm but
+    alert. His gaze is directed toward the camera with a quiet, introspective
+    expression — thoughtful, distant, slightly defiant. Loose white button-up
+    shirt with sleeves casually rolled up, soft fabric with visible folds.
+    Light-colored trousers, relaxed fit, natural draping. No emphasis on
+    hairstyle or hair details. An open book with visible printed text on the
+    page; typography clean and minimal. A large decorative bow or cushion with a
+    black-and-white checkered pattern is strapped or placed across the lower
+    torso area, adding a surreal, slightly ironic contrast. Single soft
+    directional light from the side, creating gentle highlights on the face,
+    hands, and book. Deep shadows around the chair and background for a
+    cinematic, moody contrast. Classic chiaroscuro effect, high tonal range.
+    Plain wall with subtle texture, no distractions. Minimalist interior, focus
+    entirely on subject, chair, and book. Intellectual, quiet rebellion,
+    cinematic stillness. Editorial fine-art photography, timeless, slightly
+    surreal. High contrast black-and-white, sharp focus on subject, soft falloff
+    into shadows. Medium shot, eye-level angle. 50mm lens look, natural
+    perspective, shallow-to-medium depth of field. Ultra-realistic, high-detail
+    editorial finish.
+- output:
+    url: images/Image01_00238_.png
+  text: >-
+    Joaquin Phoenix, European male,A young man sitting casually on a metal bench
+    at a modern urban coffee shop, crossing one leg over the other while sipping
+    from a small glass of dark coffee. He has ultra-realistic skin texture with
+    visible pores, a smooth natural complexion, and a completely clean-shaven
+    face, maintaining a highly photorealistic human appearance.  He is wearing a
+    cream cable-knit sweater paired with relaxed black trousers and minimalist
+    cream suede loafers, creating a clean, refined masculine café look.
+    Rectangular black sunglasses cover his eyes. A silver watch and a simple
+    ring subtly complete the styling.  In front of him is a small round
+    stainless-steel table holding a wooden plate with a slice of cake and a
+    smartphone placed beside it. The background features dark stone walls and a
+    perforated metal panel, with tropical green plants peeking over the top,
+    forming a quiet, refined urban café atmosphere.  Soft natural daylight casts
+    gentle shadows across his face and sweater, emphasizing the knit texture and
+    subtle reflections on metal surfaces. Artsy Pinterest aesthetic, minimalist
+    urban coffee-culture mood, eye-level medium-full shot, high-fashion
+    lifestyle photography, ultra-detailed, 8k resolution, RAW natural tones.
+- output:
+    url: images/Image01_00239_.png
+  text: >-
+    Joaquin Phoenix, European male, A cinematic still of a middle-aged man
+    standing indoors beside a large glass window, captured at chest level with a
+    slightly off-center composition. He has light skin, a slim build, curly
+    slightly unkempt brown hair, and a thick mustache. He wears round,
+    dark-framed prescription glasses and a mustard-yellow button-down shirt with
+    the collar casually open, the fabric softly wrinkled and natural. His
+    expression is pensive and quietly troubled, eyes focused slightly past the
+    camera as if caught mid-thought, conveying loneliness, introspection, and
+    emotional distance.  The background is a hazy, muted city skyline viewed
+    through the glass—tall concrete and glass buildings softened by atmospheric
+    smog, dust, or overcast light. The window creates subtle reflections,
+    faintly mirroring parts of his face and glasses, adding visual depth and
+    psychological tension. Lighting is soft and diffused, with warm beige and
+    yellow tones dominating the scene, contrasted by cool gray urban forms
+    outside. The color grading feels melancholic and subdued, reminiscent of
+    arthouse cinema, with gentle film grain and shallow depth of field.  Shot on
+    a high-end cinematic camera, realistic skin texture, natural imperfections,
+    soft focus falloff, emotionally intimate mood, modern yet timeless
+    aesthetic, cinematic realism, 4K detail, dramatic but restrained visual
+    storytelling.
+base_model: Tongyi-MAI/Z-Image-Turbo
+instance_prompt: Joaquin Phoenix, European male
+license: apache-2.0
+---
+# JoaquinPhoenix
+
+<Gallery />
+
+## Model description 
+
+🧩 **LoRA Name:** **Theodore_HER_2013**
+
+&gt; Base Model: Tongyi-MAI &#x2F; Z-Image-Turbo
+&gt; LoRA Type: Character &#x2F; Film Character
+&gt; Trigger Word(s): Theodore Twombly *(name-based prompting recommended; actor descriptors are learned implicitly)*
+&gt; Recommended Weight: 0.6 – 0.85 (sweet spot ≈ 0.75)
+
+---
+
+✨ **Overview**
+
+&gt; This LoRA is trained to reproduce the visual identity and emotional presence of **Theodore Twombly**, the character portrayed by Joaquin Phoenix in *Her (2013)*. It focuses on capturing the character’s distinctive facial structure, body language, and understated vulnerability, optimized for ZimageTurbo’s low-guidance, cinematic rendering style.
+
+The model excels at quiet, introspective portrayals—balancing realism with a soft, melancholic tone—making it ideal for cinematic stills, editorial portraits, and narrative-driven scenes inspired by contemporary arthouse cinema.
+
+---
+
+🎨 **What This LoRA Is Good At**
+
+&gt; Strong likeness fidelity to Theodore Twombly across moods and settings
+&gt; Expressive, introspective facial expressions and eye focus
+&gt; Cinematic realism with natural skin texture and subtle imperfections
+&gt; Works well in both color-graded and black-and-white compositions
+&gt; Excellent for narrative, editorial, and emotionally driven imagery
+
+---
+
+⚙️ **Usage Notes**
+
+&gt; Best results with portrait, medium-shot, and cinematic framing
+&gt; Prompting **“Theodore Twombly”** is sufficient; avoid stacking other character LoRAs
+&gt; Performs especially well with soft, diffused lighting and subdued color palettes
+&gt; Guidance scale ≤ 1 is recommended for native ZimageTurbo behavior
+
+---
+
+🧪 **Example Prompt**
+Joaquin Phoenix, European male,  cinematic portrait, soft diffused light,
+introspective expression, shallow depth of field, emotional realism
+
+---
+
+📐 **Training Details**
+
+&gt; Dataset Size: Captioned image set
+&gt; Training Resolutions: 512 &#x2F; 768
+&gt; Total Steps: 3,300
+&gt; Batch Size: 1
+&gt; Content vs Style: Balanced
+&gt; Noise Scheduler: FlowMatch
+&gt; Optimizer: AdamW 8-bit
+&gt; Learning Rate: 1e-4
+&gt; Precision: BF16
+&gt; Text Encoder Training: Disabled
+&gt; UNet Training: Enabled
+&gt; Quantization: QFloat8 (model + text encoder)
+&gt; Architecture: ZImage Turbo LoRA (LoKR full-rank enabled)
+
+---
+
+⚠️ **Limitations &#x2F; Notes**
+
+&gt; Not intended for anime or heavily stylized cartoon outputs
+&gt; Extreme facial exaggeration or aggressive lenses may reduce character fidelity
+&gt; Designed for grounded, cinematic realism rather than exaggerated fantasy scenes
+
+## Trigger words
+
+You should use `Joaquin Phoenix` to trigger the image generation.
+
+You should use `European male` to trigger the image generation.
+
+
+## Download model
+
+
+[Download](/JunkieMonkey69/JoaquinPhoenix_ZimageTurbo/tree/main) them in the Files & versions tab.