JunkieMonkey69's picture
initial commit
4acfaa8 verified
|
Raw History Blame
7.97 kB
---
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.