--- license: other base_model: black-forest-labs/FLUX.1-dev tags: - flux - flux-diffusers - text-to-image - diffusers - simpletuner - safe-for-work - lora - template:sd-lora - standard inference: true widget: - text: unconditional (blank prompt) parameters: negative_prompt: blurry, cropped, ugly output: url: ./assets/image_0_0.png - text: >- In the style of a b3nbr4nd painting, A steaming bowl of ramen with chopsticks resting on the edge, against a background of concentric orange and blue circles. The noodles are detailed in a geometric pattern and the steam creates a rhythmic design. parameters: negative_prompt: blurry, cropped, ugly output: url: ./assets/image_1_0.png - text: >- In the style of a b3nbr4nd painting, A vintage record player with vinyl spinning, set on a yellow table. The background features an alternating chevron pattern in purple and green. The turntable's mechanical parts are rendered in precise geometric shapes. parameters: negative_prompt: blurry, cropped, ugly output: url: ./assets/image_2_0.png - text: >- In the style of a b3nbr4nd painting, A sleeping cat curled up in a modernist chair, with a background of interlocking hexagons in red and blue. The cat's fur is stylized into rhythmic curves, matching the geometric environment. parameters: negative_prompt: blurry, cropped, ugly output: url: ./assets/image_3_0.png - text: >- In the style of a b3nbr4nd painting, A classic motorcycle viewed from the side, against a backdrop of radiating diamond patterns in teal and gold. The chrome parts reflect abstract shapes, and the wheels create circular motifs in the composition. parameters: negative_prompt: blurry, cropped, ugly output: url: ./assets/image_4_0.png - text: >- In the style of a b3nbr4nd painting, Portrait of a woman with silver hair wearing dotted blue glasses and a white lace collar, against a swirling background of green and yellow patterns. The background features geometric circles and zigzag designs. parameters: negative_prompt: blurry, cropped, ugly output: url: ./assets/image_5_0.png - text: >- In the style of a b3nbr4nd painting, A storefront sign for 'Golden Palace Noodles' in both English and Chinese characters, mounted on a tall pole against a geometric cityscape with blue and tan buildings. A small arrow points to available parking. parameters: negative_prompt: blurry, cropped, ugly output: url: ./assets/image_6_0.png - text: >- In the style of a b3nbr4nd painting, Dark purple figs sliced in half on a terra cotta plate, revealing their seeded interiors. The background features a repeating pattern of blue and yellow squares, with wavy lines creating a dynamic lower section. parameters: negative_prompt: blurry, cropped, ugly output: url: ./assets/image_7_0.png - text: >- In the style of a b3nbr4nd painting, Two young people wearing matching navy shirts and light gray face masks, posed against a warm yellow background. Their curly hair and gentle head tilts create a symmetrical composition. parameters: negative_prompt: blurry, cropped, ugly output: url: ./assets/image_8_0.png - text: >- In the style of a b3nbr4nd painting, A hamster wearing tiny glasses and a bowtie sitting at a miniature desk with a tiny laptop, against a background of spiral patterns in teal and orange. Office supplies scaled to hamster-size are arranged neatly on the desk. parameters: negative_prompt: blurry, cropped, ugly output: url: ./assets/image_9_0.png - text: >- In the style of a b3nbr4nd painting, A bearded man in a plaid shirt and denim apron carefully sanding a mid-century modern chair, surrounded by woodworking tools. The background features overlapping triangles in rust and navy blue colors, with sawdust creating delicate patterns in the air. parameters: negative_prompt: blurry, cropped, ugly output: url: ./assets/image_10_0.png - text: >- In the style of a b3nbr4nd painting, The Fractured Cathedral – Ruined temple standing between timelines, stained glass windows refracting multiple realities, golden gears turning in the vaulted ceiling, priests in robes of shifting colors, a mechanical choir humming in binary, relics of forgotten AI scattered on an altar, static crackling like divine whispers. output: url: images/example_a42xk8qba.png - text: >- In the style of a b3nbr4nd painting, The Cartographer of Lost Time – A hunched figure tracing glowing lines across an ancient map, ink shifting as if alive, continents forming and vanishing, thousands of tiny golden orbs orbiting the parchment, the map itself whispering of places that no longer exist, candlelight flickering in unknown patterns. output: url: images/example_0916y8ymq.png - text: >- In the style of a b3nbr4nd painting, A steaming outdoor pool carved from volcanic rock, floating lanterns casting rippling golden reflections, pale steam curling upwards into a canopy of sapphire sky, koi fish with silver scales swimming in slow, deliberate circles. output: url: images/example_aych9v4t1.png - text: >- In the style of a b3nbr4nd painting, A spiraling staircase covered in deep red velvet, disappearing into a hazy golden glow, framed by walls of dark mahogany, intricate carvings of animals moving subtly when not directly observed. output: url: images/example_xm1y3tb6v.png - text: >- In the style of a b3nbr4nd painting, A vast, half-built cathedral where stained-glass windows flicker between scenes, as though buffering reality itself. The stone pillars extend endlessly into the sky, sometimes breaking apart into pixels before reforming. At the altar, a priest made of light raises their hands, their face cycling through a thousand unreadable expressions. output: url: images/example_05vukxmgl.png - text: >- In the style of a b3nbr4nd painting, A spiraling stone staircase wrapped around itself, leading both up and down in an endless paradox. Footsteps echo from ahead and behind, but the traveler never sees another person. Hanging lanterns flicker in rhythmic pulses, illuminating carvings of eyes that seem to watch, waiting for the moment someone understands the pattern. output: url: images/example_xizv9nrx2.png - text: >- In the style of a b3nbr4nd painting, starry night sky, tall buildings, skyscrapers, windows, connected buildings, walkway, green checkerboard pattern walkway, arched windows, trees with lights, urban landscape, geometric architecture, city night scene, multicolored buildings, modern cityscape, midground walkway, background buildings, illuminated windows, high-rise structures, blue building, city park with lights output: url: images/example_naqqp69cu.png - text: >- In the style of a b3nbr4nd painting, blue vases, pink tulips, table with patterned tablecloth, orange mugs, green teapot, posters on wall, red poster, text on red poster, white text, yellow wall, drawers in background, multiple cups, ceramic kettle, lid on kettle, floral mug, window with striped curtains, indoor scene, objects on table, vase in center, tea set output: url: images/example_gfqdxqy36.png - text: >- In the style of a b3nbr4nd painting, Towering red clocktower, golden clock hands frozen at midnight, gears visible through glass windows, standing in a misty valley, deep blue sky, orange and pink clouds, warm glowing lanterns on stone pathway, ivy creeping up brick walls, metal staircase leading to a rooftop observatory. output: url: images/example_6507viyod.png --- # Ben-Brand-LoRA This is a standard PEFT LoRA derived from [black-forest-labs/FLUX.1-dev](https://huggingface.co/black-forest-labs/FLUX.1-dev). No validation prompt was used during training. None ## Validation settings - CFG: `3.0` - CFG Rescale: `0.0` - Steps: `20` - Sampler: `FlowMatchEulerDiscreteScheduler` - Seed: `42` - Resolution: `1024x1024` - Skip-layer guidance: Note: The validation settings are not necessarily the same as the [training settings](#training-settings). You can find some example images in the following gallery: The text encoder **was not** trained. You may reuse the base model text encoder for inference. ## Training settings - Training epochs: 1 - Training steps: 3500 - Learning rate: 0.0001 - Learning rate schedule: polynomial - Warmup steps: 100 - Max grad norm: 0.1 - Effective batch size: 6 - Micro-batch size: 2 - Gradient accumulation steps: 3 - Number of GPUs: 1 - Gradient checkpointing: True - Prediction type: flow-matching (extra parameters=['shift=3', 'flux_guidance_mode=constant', 'flux_guidance_value=1.0', 'flow_matching_loss=compatible', 'flux_lora_target=all']) - Optimizer: adamw_bf16 - Trainable parameter precision: Pure BF16 - Caption dropout probability: 10.0% - LoRA Rank: 64 - LoRA Alpha: None - LoRA Dropout: 0.1 - LoRA initialisation style: default ## Datasets ### ben-brand-256 - Repeats: 10 - Total number of images: 98 - Total number of aspect buckets: 1 - Resolution: 0.065536 megapixels - Cropped: False - Crop style: None - Crop aspect: None - Used for regularisation data: No ### ben-brand-crop-256 - Repeats: 10 - Total number of images: 98 - Total number of aspect buckets: 1 - Resolution: 0.065536 megapixels - Cropped: True - Crop style: center - Crop aspect: square - Used for regularisation data: No ### ben-brand-512 - Repeats: 10 - Total number of images: 98 - Total number of aspect buckets: 3 - Resolution: 0.262144 megapixels - Cropped: False - Crop style: None - Crop aspect: None - Used for regularisation data: No ### ben-brand-crop-512 - Repeats: 10 - Total number of images: 98 - Total number of aspect buckets: 1 - Resolution: 0.262144 megapixels - Cropped: True - Crop style: center - Crop aspect: square - Used for regularisation data: No ### ben-brand-768 - Repeats: 10 - Total number of images: 98 - Total number of aspect buckets: 6 - Resolution: 0.589824 megapixels - Cropped: False - Crop style: None - Crop aspect: None - Used for regularisation data: No ### ben-brand-crop-768 - Repeats: 10 - Total number of images: 98 - Total number of aspect buckets: 1 - Resolution: 0.589824 megapixels - Cropped: True - Crop style: center - Crop aspect: square - Used for regularisation data: No ### ben-brand-1024 - Repeats: 10 - Total number of images: 98 - Total number of aspect buckets: 7 - Resolution: 1.048576 megapixels - Cropped: False - Crop style: None - Crop aspect: None - Used for regularisation data: No ### ben-brand-crop-1024 - Repeats: 10 - Total number of images: 98 - Total number of aspect buckets: 1 - Resolution: 1.048576 megapixels - Cropped: True - Crop style: center - Crop aspect: square - Used for regularisation data: No ### ben-brand-1440 - Repeats: 10 - Total number of images: 98 - Total number of aspect buckets: 4 - Resolution: 2.0736 megapixels - Cropped: False - Crop style: None - Crop aspect: None - Used for regularisation data: No ### ben-brand-crop-1440 - Repeats: 10 - Total number of images: 98 - Total number of aspect buckets: 1 - Resolution: 2.0736 megapixels - Cropped: True - Crop style: center - Crop aspect: square - Used for regularisation data: No ## Inference ```python import torch from diffusers import DiffusionPipeline model_id = 'black-forest-labs/FLUX.1-dev' adapter_id = 'davidrd123/Ben-Brand-LoRA' pipeline = DiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.bfloat16) # loading directly in bf16 pipeline.load_lora_weights(adapter_id) prompt = "An astronaut is riding a horse through the jungles of Thailand." ## Optional: quantise the model to save on vram. ## Note: The model was quantised during training, and so it is recommended to do the same during inference time. from optimum.quanto import quantize, freeze, qint8 quantize(pipeline.transformer, weights=qint8) freeze(pipeline.transformer) pipeline.to('cuda' if torch.cuda.is_available() else 'mps' if torch.backends.mps.is_available() else 'cpu') # the pipeline is already in its target precision level image = pipeline( prompt=prompt, num_inference_steps=20, generator=torch.Generator(device='cuda' if torch.cuda.is_available() else 'mps' if torch.backends.mps.is_available() else 'cpu').manual_seed(42), width=1024, height=1024, guidance_scale=3.0, ).images[0] image.save("output.png", format="PNG") ```