⚡ Flux Model Training Summary (LoRA)
This job customized the Flux base model, which is a different architecture from Stable Diffusion XL. This run featured several key changes in its configuration, resulting in a longer duration.
1. Job Status and Timeline
Base Model Used: Flux (A modern, likely newer or different image generation model).
Job ID: 563759-20251018091302678
Training Start: October 18, 2025 at 05:13:06 PM
Completion Time (Ready): October 19, 2025 at 12:03:14 PM
Total Duration: Approximately 18 hours and 50 minutes (significantly longer than the previous job).
Dataset Used: 27 Files / 27 Labels.
Label Type: Caption (using full descriptive sentences, rather than just short tags, which is ideal for a complex model like Flux).
2. Key Training Parameters (The Differences)
This configuration is notably different from the previous SDXL job, suggesting an attempt to train a very lightweight, highly specialized LoRA.
Model Intensity & Focus
Network Dimension (networkDim): 2 (This is extremely low compared to 32 in the last job. This makes the resulting LoRA file much smaller but potentially less capable of capturing complex details).
Network Alpha (networkAlpha): 16 (Used for LoRA stabilization).
LoRA Type: lora.
Engine: kohya.
Learning Process
Image Resolution: 512 (Lower resolution than the previous 1024).
Maximum Epochs: 35 (Higher than the previous 20, meaning the data was shown to the model more often to compensate for the small network size).
Text Encoder Learning Rate (textEncoderLR): 0 (This is crucial: The text understanding part of the model was frozen and did not learn. Only the image generation part (U-Net) was updated).
U-Net Learning Rate (unetLR): 0.0005.
Optimizer Type: AdamW8Bit (Different from Adafactor).
Shuffle Caption: false (Captions were fed in the same order each time).
Keep Tokens: 0 (No specific caption words were prioritized, unlike 3 previously).
Description
Training Tags Exhaustive List (Chweee1 Focus)
This is the complete, consolidated list of all tags used to train the LoRA model based on the second dataset.
Subject & Physical Attributes
Subject: chweee1, male, Asian, muscular man, artist, everyday hero, mature 60 year old daddy
Physique/Body: muscular, medium build, muscular arms, abs, defined abs, six-pack, flexing bicep, tan skin, light skin, arm hair, chest hair, slight hair on stomach, visible arm veins, natural body
Tattoos & Grooming: palm tree tattoo on left shoulder, tribal tattoo on right shoulder, visible pubic hair, slight tan lines, clean-shaven, unshaven, casual haircut
Facial Features: short black hair, glasses, slight smile, relaxed expression, confident pose, neutral expression
Clothing & Accessories
Casual Tops: dark gray t-shirt, black t-shirt, grey t-shirt, black and white striped shirt, sleeveless gray tank top, grey polo shirt
Casual Bottoms: gray camouflage pants, blue camouflage pants, grey camo shorts, gray sweatpants, beige pants, black pants
NSFW/Underwear: naked, shirtless, blue boxer briefs, blue underwear, white drawstring
Accessories: black smartwatch, pocket on t-shirt
NSFW Content Details
Explicit: erect cock, large cock, medium-sized cock, hand on cock, uncircumcised tip, visible veins on cock, flaccid foreskin
Contextual: nsfw, lifting shirt, exposing abs, showing abs, low-angle shot, close-up, focus on torso and cock
Environments & Settings
Home: bedroom, living room, white walls, bed with white pillows, gray headboard, wooden stool, wooden coffee table, TV, gray leather couch
Work/Studio: office setting, art studio, white desk, office cubicles, cityscape background, framed art, air conditioning unit, computer monitors
Art/Decor: abstract painting, colorful abstract painting, paintings on wall, paint palette, brushes, mixed media
Lighting/Composition: photograph, sfw, medium close-up, eye-level shot, rule of thirds, natural light, soft lighting, sunlight, strong shadows