Text-to-Image
Diffusers
Safetensors
English
orbitquant
w4a8
4-bit precision
gptq
quantized
fibo
vgl
structured-prompts
image-editing
image-to-image
arxiv:2607.02461
Instructions to use WaveCut/Fibo-2.0-dev-OrbitQuant-W4A8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use WaveCut/Fibo-2.0-dev-OrbitQuant-W4A8 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("WaveCut/Fibo-2.0-dev-OrbitQuant-W4A8", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
- DiffusionBee
Download assets/evaluation_cases.json from WaveCut/Fibo-2.0-dev-OrbitQuant-W4A8: direct link, hf CLI and curl.
- Browser
- Download file 31.9 kB
-
https://huggingface.co/WaveCut/Fibo-2.0-dev-OrbitQuant-W4A8/resolve/main/assets/evaluation_cases.json
- Command line
-
hf download hf://WaveCut/Fibo-2.0-dev-OrbitQuant-W4A8/assets/evaluation_cases.json
-
curl -L -o evaluation_cases.json https://huggingface.co/WaveCut/Fibo-2.0-dev-OrbitQuant-W4A8/resolve/main/assets/evaluation_cases.json
31.9 kB
| { | |
| "t2i": [ | |
| { | |
| "name": "bicycle", | |
| "width": 1024, | |
| "height": 1024, | |
| "caption": { | |
| "short_description": "A red city bicycle with a wicker basket leans against a white brick wall on a quiet street on a sunny morning. A small wooden sign above it reads \"OPEN\".", | |
| "objects": [ | |
| { | |
| "description": "A red city bicycle with a step-through frame, black tyres and a wicker basket on the handlebars.", | |
| "location": "center", | |
| "relationship": "Leaning against the wall, below the sign.", | |
| "relative_size": "large within frame", | |
| "shape_and_color": "Classic upright bicycle frame, glossy cherry red.", | |
| "texture": "glossy painted metal and woven wicker", | |
| "orientation": "side-on, facing left" | |
| } | |
| ], | |
| "background_setting": "A white-painted brick wall with a green wooden door on the right and a cobblestone pavement below.", | |
| "lighting": { | |
| "conditions": "bright morning sun", | |
| "direction": "side-lit from the right", | |
| "shadows": "crisp shadow of the bicycle cast on the wall to the left" | |
| }, | |
| "aesthetics": { | |
| "composition": "centered, eye-level, with the bicycle filling the lower two thirds", | |
| "color_scheme": "red and green accents on white", | |
| "mood_atmosphere": "calm, cheerful" | |
| }, | |
| "photographic_characteristics": { | |
| "depth_of_field": "deep", | |
| "focus": "sharp focus on the bicycle", | |
| "camera_angle": "eye-level", | |
| "lens_focal_length": "standard lens (e.g., 35mm-50mm)" | |
| }, | |
| "style_medium": "photograph", | |
| "text_render": [ | |
| { | |
| "text": "OPEN", | |
| "location": "top center, on a sign above the bicycle", | |
| "size": "medium", | |
| "color": "white", | |
| "font": "hand-painted serif", | |
| "appearance_details": "painted on a small dark wooden board" | |
| } | |
| ], | |
| "context": "A lifestyle street photograph for a café's social media post.", | |
| "artistic_style": "realistic" | |
| }, | |
| "seed": 20261023 | |
| }, | |
| { | |
| "name": "origami_whale", | |
| "width": 1424, | |
| "height": 800, | |
| "caption": { | |
| "short_description": "A large origami whale folded from pale blue paper swims through a sky of white paper clouds, with tiny paper birds following it.", | |
| "objects": [ | |
| { | |
| "description": "An origami humpback whale folded from pale blue paper with crisp creases and a fan-shaped tail.", | |
| "location": "center", | |
| "relationship": "Swimming between the paper clouds.", | |
| "relative_size": "large within frame", | |
| "texture": "matte folded paper with visible fibres", | |
| "orientation": "facing right, tail raised" | |
| }, | |
| { | |
| "description": "Five small white origami birds in a loose line.", | |
| "location": "top-right", | |
| "relationship": "Flying ahead of the whale.", | |
| "relative_size": "small", | |
| "number_of_objects": 5 | |
| } | |
| ], | |
| "background_setting": "A soft gradient sky made of layered cut paper, pale peach at the bottom to light blue at the top, with puffy white paper clouds at different depths.", | |
| "lighting": { | |
| "conditions": "soft studio light", | |
| "direction": "front-lit from the upper left", | |
| "shadows": "gentle soft shadows under each paper layer" | |
| }, | |
| "aesthetics": { | |
| "composition": "wide panoramic composition, whale on the left third", | |
| "color_scheme": "pastel blues and peach", | |
| "mood_atmosphere": "whimsical, serene" | |
| }, | |
| "photographic_characteristics": { | |
| "depth_of_field": "shallow", | |
| "focus": "sharp focus on the whale, distant clouds slightly soft", | |
| "camera_angle": "eye-level", | |
| "lens_focal_length": "standard lens (e.g., 35mm-50mm)" | |
| }, | |
| "style_medium": "photograph of a papercraft diorama", | |
| "context": "A children's book cover illustration made as a papercraft diorama.", | |
| "artistic_style": "whimsical, handcrafted" | |
| }, | |
| "seed": 20261024 | |
| }, | |
| { | |
| "name": "still_life", | |
| "width": 1024, | |
| "height": 1024, | |
| "caption": { | |
| "short_description": "On a white windowsill, a row of exactly five red apples and one green pear, the pear in the second position from the left. A small brass bell sits on top of the third apple from the right. Morning light, minimal still life.", | |
| "objects": [ | |
| { | |
| "description": "Five shiny red apples in a straight row.", | |
| "location": "center, along the windowsill", | |
| "relationship": "Side by side with the pear in the second position from the left.", | |
| "number_of_objects": 5, | |
| "relative_size": "medium" | |
| }, | |
| { | |
| "description": "One green pear.", | |
| "location": "second from the left in the row", | |
| "relationship": "Between the first and second apple.", | |
| "relative_size": "medium" | |
| }, | |
| { | |
| "description": "A small polished brass bell with a wooden handle.", | |
| "location": "on top of the third apple from the right", | |
| "relationship": "Balanced on that apple.", | |
| "relative_size": "small" | |
| } | |
| ], | |
| "background_setting": "A white painted wooden windowsill and a pale grey wall, a sheer curtain at the edge of the frame.", | |
| "lighting": { | |
| "conditions": "soft morning daylight", | |
| "direction": "side-lit from the left through the window", | |
| "shadows": "soft elongated shadows to the right" | |
| }, | |
| "aesthetics": { | |
| "composition": "centered horizontal row, eye-level", | |
| "color_scheme": "red and green on white", | |
| "mood_atmosphere": "minimal, quiet" | |
| }, | |
| "photographic_characteristics": { | |
| "depth_of_field": "deep", | |
| "focus": "sharp focus across the row", | |
| "camera_angle": "eye-level", | |
| "lens_focal_length": "standard lens (e.g., 35mm-50mm)" | |
| }, | |
| "style_medium": "photograph", | |
| "context": "A minimal still-life photograph for an art print.", | |
| "artistic_style": "minimalist, realistic" | |
| }, | |
| "seed": 20261025 | |
| }, | |
| { | |
| "name": "fisherman", | |
| "width": 832, | |
| "height": 1248, | |
| "caption": { | |
| "short_description": "A close-up portrait of an elderly fisherman with a white beard and deep wrinkles, wearing a navy knitted cap, looking into the camera on a foggy harbour.", | |
| "objects": [ | |
| { | |
| "description": "An elderly man in his seventies with a thick white beard, weathered skin and pale blue eyes.", | |
| "location": "center", | |
| "relationship": "The only subject, framed from the chest up.", | |
| "relative_size": "large within frame", | |
| "pose": "facing the camera, shoulders slightly turned", | |
| "expression": "calm, faint smile", | |
| "clothing": "navy knitted wool cap and a yellow oilskin jacket", | |
| "gender": "male", | |
| "skin_tone_and_texture": "fair, sun-weathered skin with deep wrinkles, visible pores and freckles" | |
| } | |
| ], | |
| "background_setting": "A foggy harbour with blurred fishing boats and mooring posts.", | |
| "lighting": { | |
| "conditions": "overcast diffused daylight", | |
| "direction": "soft front light from the left", | |
| "shadows": "very soft shadows" | |
| }, | |
| "aesthetics": { | |
| "composition": "close-up, centered, rule of thirds on the eyes", | |
| "color_scheme": "muted blues and yellow", | |
| "mood_atmosphere": "contemplative" | |
| }, | |
| "photographic_characteristics": { | |
| "depth_of_field": "shallow", | |
| "focus": "sharp focus on the eyes", | |
| "camera_angle": "eye-level", | |
| "lens_focal_length": "portrait lens (e.g., 85mm)" | |
| }, | |
| "style_medium": "photograph", | |
| "context": "An editorial documentary portrait for a magazine.", | |
| "artistic_style": "realistic" | |
| }, | |
| "seed": 20261026 | |
| }, | |
| { | |
| "name": "neon_cafe", | |
| "width": 1248, | |
| "height": 832, | |
| "caption": { | |
| "short_description": "A glowing pink neon sign reading \"NIGHT OWL CAFE\" on a dark red brick wall at night, with a smaller blue neon sign below reading \"OPEN 24/7\".", | |
| "objects": [ | |
| { | |
| "description": "A neon owl outline in warm yellow tubing beside the main sign.", | |
| "location": "left of the text", | |
| "relationship": "Part of the sign installation.", | |
| "relative_size": "medium" | |
| } | |
| ], | |
| "background_setting": "A dark red brick wall wet from rain, with a window reflecting the neon glow.", | |
| "lighting": { | |
| "conditions": "night, neon glow", | |
| "direction": "front-lit by the signs", | |
| "shadows": "deep shadows around the glow" | |
| }, | |
| "aesthetics": { | |
| "composition": "centered", | |
| "color_scheme": "pink, blue and yellow neon on dark red", | |
| "mood_atmosphere": "moody, urban" | |
| }, | |
| "photographic_characteristics": { | |
| "depth_of_field": "shallow", | |
| "focus": "sharp focus on the signs", | |
| "camera_angle": "eye-level", | |
| "lens_focal_length": "standard lens (e.g., 35mm-50mm)" | |
| }, | |
| "style_medium": "photograph", | |
| "text_render": [ | |
| { | |
| "text": "NIGHT OWL CAFE", | |
| "location": "center", | |
| "size": "large within frame", | |
| "color": "hot pink", | |
| "font": "neon script", | |
| "appearance_details": "glowing neon tubes" | |
| }, | |
| { | |
| "text": "OPEN 24/7", | |
| "location": "below the main sign", | |
| "size": "medium", | |
| "color": "electric blue", | |
| "font": "neon sans-serif", | |
| "appearance_details": "glowing neon tubes" | |
| } | |
| ], | |
| "context": "A night street photograph of a café sign.", | |
| "artistic_style": "realistic, moody" | |
| }, | |
| "seed": 20261027 | |
| }, | |
| { | |
| "name": "travel_poster", | |
| "width": 832, | |
| "height": 1248, | |
| "caption": { | |
| "short_description": "A vintage travel poster of a Norwegian fjord with steep green cliffs and a red sailboat, with the title \"VISIT NORWAY\" at the top and \"LAND OF THE FJORDS\" at the bottom.", | |
| "objects": [ | |
| { | |
| "description": "A small red sailboat with white sails.", | |
| "location": "lower center on the water", | |
| "relationship": "Sailing between the cliffs.", | |
| "relative_size": "small" | |
| } | |
| ], | |
| "background_setting": "A deep blue fjord between steep green cliffs, a waterfall on the right, snowy peaks and a pale yellow sky.", | |
| "lighting": { | |
| "conditions": "flat poster lighting", | |
| "direction": "none", | |
| "shadows": "simplified graphic shadows" | |
| }, | |
| "aesthetics": { | |
| "composition": "vertical poster layout with title band at top", | |
| "color_scheme": "limited palette of teal, green, red and cream", | |
| "mood_atmosphere": "nostalgic, adventurous" | |
| }, | |
| "style_medium": "vintage lithograph poster illustration", | |
| "text_render": [ | |
| { | |
| "text": "VISIT NORWAY", | |
| "location": "top center", | |
| "size": "large within frame", | |
| "color": "cream", | |
| "font": "bold art deco sans-serif" | |
| }, | |
| { | |
| "text": "LAND OF THE FJORDS", | |
| "location": "bottom center", | |
| "size": "medium", | |
| "color": "cream", | |
| "font": "art deco sans-serif" | |
| } | |
| ], | |
| "context": "A 1930s style tourism poster.", | |
| "artistic_style": "art deco, flat" | |
| }, | |
| "seed": 20261028 | |
| }, | |
| { | |
| "name": "pianist_hands", | |
| "width": 1248, | |
| "height": 832, | |
| "caption": { | |
| "short_description": "A close-up of a pianist's two hands playing a grand piano, all ten fingers clearly visible on the black and white keys.", | |
| "objects": [ | |
| { | |
| "description": "Two adult hands with slender fingers, a silver ring on the right ring finger.", | |
| "location": "center", | |
| "relationship": "Pressing the keys of the piano.", | |
| "relative_size": "large within frame", | |
| "action": "playing a chord", | |
| "skin_tone_and_texture": "light olive skin with natural creases and knuckle detail" | |
| } | |
| ], | |
| "background_setting": "The polished black body of a grand piano blurred in the background.", | |
| "lighting": { | |
| "conditions": "warm stage spotlight", | |
| "direction": "top-lit from above", | |
| "shadows": "soft shadows between the keys" | |
| }, | |
| "aesthetics": { | |
| "composition": "close-up, slightly high angle", | |
| "color_scheme": "black, white and warm skin tones", | |
| "mood_atmosphere": "elegant, focused" | |
| }, | |
| "photographic_characteristics": { | |
| "depth_of_field": "shallow", | |
| "focus": "sharp focus on the fingers", | |
| "camera_angle": "high angle", | |
| "lens_focal_length": "macro" | |
| }, | |
| "style_medium": "photograph", | |
| "context": "A concert promotion photograph.", | |
| "artistic_style": "realistic" | |
| }, | |
| "seed": 20261029 | |
| }, | |
| { | |
| "name": "perfume", | |
| "width": 1024, | |
| "height": 1024, | |
| "caption": { | |
| "short_description": "A faceted glass perfume bottle with a gold cap on a white marble slab, surrounded by water droplets and a few white rose petals.", | |
| "objects": [ | |
| { | |
| "description": "A square faceted glass perfume bottle filled with pale pink liquid and topped with a ribbed gold cap.", | |
| "location": "center", | |
| "relationship": "Standing on the marble.", | |
| "relative_size": "large within frame", | |
| "texture": "clear glass with sharp facets and reflections" | |
| }, | |
| { | |
| "description": "Three white rose petals.", | |
| "location": "bottom-left foreground", | |
| "relationship": "Scattered next to the bottle.", | |
| "number_of_objects": 3 | |
| } | |
| ], | |
| "background_setting": "A seamless soft pink backdrop and a white marble slab with grey veins covered with tiny water droplets.", | |
| "lighting": { | |
| "conditions": "studio lighting", | |
| "direction": "back-lit with a soft front fill", | |
| "shadows": "soft reflection on the marble" | |
| }, | |
| "aesthetics": { | |
| "composition": "centered product shot", | |
| "color_scheme": "pink, gold and white", | |
| "mood_atmosphere": "luxurious, fresh" | |
| }, | |
| "photographic_characteristics": { | |
| "depth_of_field": "shallow", | |
| "focus": "sharp focus on the bottle", | |
| "camera_angle": "eye-level", | |
| "lens_focal_length": "macro" | |
| }, | |
| "style_medium": "photograph", | |
| "context": "An e-commerce product shot for a fragrance brand.", | |
| "artistic_style": "realistic, commercial" | |
| }, | |
| "seed": 20261030 | |
| }, | |
| { | |
| "name": "cyrillic_menu", | |
| "width": 1024, | |
| "height": 1024, | |
| "caption": { | |
| "short_description": "A chalkboard menu on a café wall with handwritten white chalk text in Russian: the title \"МЕНЮ ДНЯ\" and two lines \"Борщ — 350 ₽\" and \"Пельмени — 420 ₽\".", | |
| "objects": [ | |
| { | |
| "description": "A black chalkboard in a wooden frame with small chalk doodles of a steaming bowl.", | |
| "location": "center", | |
| "relationship": "Hanging on the wall.", | |
| "relative_size": "large within frame" | |
| } | |
| ], | |
| "background_setting": "A warm café interior wall of exposed brick, a hanging plant at the edge.", | |
| "lighting": { | |
| "conditions": "warm indoor light", | |
| "direction": "front-lit", | |
| "shadows": "soft shadows" | |
| }, | |
| "aesthetics": { | |
| "composition": "centered, straight-on", | |
| "color_scheme": "black board with white chalk on warm brick", | |
| "mood_atmosphere": "cozy" | |
| }, | |
| "photographic_characteristics": { | |
| "depth_of_field": "deep", | |
| "focus": "sharp focus on the text", | |
| "camera_angle": "eye-level", | |
| "lens_focal_length": "standard lens (e.g., 35mm-50mm)" | |
| }, | |
| "style_medium": "photograph", | |
| "text_render": [ | |
| { | |
| "text": "МЕНЮ ДНЯ", | |
| "location": "top center of the board", | |
| "size": "large within frame", | |
| "color": "white", | |
| "font": "handwritten chalk capitals" | |
| }, | |
| { | |
| "text": "Борщ — 350 ₽", | |
| "location": "middle of the board", | |
| "size": "medium", | |
| "color": "white", | |
| "font": "handwritten chalk" | |
| }, | |
| { | |
| "text": "Пельмени — 420 ₽", | |
| "location": "below the first line", | |
| "size": "medium", | |
| "color": "white", | |
| "font": "handwritten chalk" | |
| } | |
| ], | |
| "context": "A photograph of a café menu board.", | |
| "artistic_style": "realistic" | |
| }, | |
| "seed": 20261031 | |
| }, | |
| { | |
| "name": "iso_island", | |
| "width": 1024, | |
| "height": 1024, | |
| "caption": { | |
| "short_description": "An isometric 3D render of a tiny floating island with a red-roofed cottage, a windmill, a pond and pine trees, drifting above clouds.", | |
| "objects": [ | |
| { | |
| "description": "A small white cottage with a red roof and a smoking chimney.", | |
| "location": "center", | |
| "relationship": "Next to the pond.", | |
| "relative_size": "medium" | |
| }, | |
| { | |
| "description": "A wooden windmill with four sails.", | |
| "location": "left", | |
| "relationship": "On the edge of the island.", | |
| "relative_size": "medium" | |
| } | |
| ], | |
| "background_setting": "A pale blue sky with soft clouds below the island, which shows layered soil and rocks underneath.", | |
| "lighting": { | |
| "conditions": "soft global illumination", | |
| "direction": "top-left", | |
| "shadows": "soft ambient occlusion" | |
| }, | |
| "aesthetics": { | |
| "composition": "isometric, centered", | |
| "color_scheme": "saturated greens, red and blue", | |
| "mood_atmosphere": "cozy, playful" | |
| }, | |
| "style_medium": "3D render", | |
| "context": "A game concept illustration.", | |
| "artistic_style": "stylized, clean" | |
| }, | |
| "seed": 20261032 | |
| }, | |
| { | |
| "name": "autumn_kids", | |
| "width": 1248, | |
| "height": 832, | |
| "caption": { | |
| "short_description": "Three children laughing and throwing orange autumn leaves in the air in a park at golden hour.", | |
| "objects": [ | |
| { | |
| "description": "Three children aged about seven to ten: a girl in a yellow raincoat, a boy in a green sweater and a girl with braids in a red scarf.", | |
| "location": "center", | |
| "relationship": "Standing together and throwing leaves.", | |
| "number_of_objects": 3, | |
| "relative_size": "large within frame", | |
| "action": "throwing leaves upward", | |
| "expression": "joyful laughter" | |
| } | |
| ], | |
| "background_setting": "A park with tall maple trees in orange and red, a path covered with leaves.", | |
| "lighting": { | |
| "conditions": "golden hour", | |
| "direction": "back-lit", | |
| "shadows": "long soft shadows" | |
| }, | |
| "aesthetics": { | |
| "composition": "medium shot, rule of thirds", | |
| "color_scheme": "warm oranges and reds", | |
| "mood_atmosphere": "joyful, energetic" | |
| }, | |
| "photographic_characteristics": { | |
| "depth_of_field": "shallow", | |
| "focus": "sharp focus on the children", | |
| "camera_angle": "eye-level", | |
| "lens_focal_length": "portrait lens (e.g., 50mm-85mm)" | |
| }, | |
| "style_medium": "photograph", | |
| "context": "A family lifestyle photograph.", | |
| "artistic_style": "realistic" | |
| }, | |
| "seed": 20261033 | |
| }, | |
| { | |
| "name": "whiteboard", | |
| "width": 1248, | |
| "height": 832, | |
| "caption": { | |
| "short_description": "A whiteboard in an office with a handwritten list in blue marker: the title \"Q3 GOALS\" and three numbered lines \"1. Ship v2\", \"2. Hire 3 engineers\", \"3. Cut latency 40%\".", | |
| "objects": [ | |
| { | |
| "description": "A white wall-mounted whiteboard with an aluminium frame and a blue marker on its tray.", | |
| "location": "center", | |
| "relationship": "Mounted on the office wall.", | |
| "relative_size": "large within frame" | |
| } | |
| ], | |
| "background_setting": "A bright modern office wall, a potted plant at the left edge.", | |
| "lighting": { | |
| "conditions": "bright office lighting", | |
| "direction": "front-lit", | |
| "shadows": "minimal shadows" | |
| }, | |
| "aesthetics": { | |
| "composition": "straight-on, centered", | |
| "color_scheme": "white, blue and green", | |
| "mood_atmosphere": "productive" | |
| }, | |
| "photographic_characteristics": { | |
| "depth_of_field": "deep", | |
| "focus": "sharp focus on the text", | |
| "camera_angle": "eye-level", | |
| "lens_focal_length": "standard lens (e.g., 35mm-50mm)" | |
| }, | |
| "style_medium": "photograph", | |
| "text_render": [ | |
| { | |
| "text": "Q3 GOALS", | |
| "location": "top left of the board", | |
| "size": "large within frame", | |
| "color": "blue", | |
| "font": "handwritten marker capitals" | |
| }, | |
| { | |
| "text": "1. Ship v2", | |
| "location": "below the title", | |
| "size": "medium", | |
| "color": "blue", | |
| "font": "handwritten marker" | |
| }, | |
| { | |
| "text": "2. Hire 3 engineers", | |
| "location": "below the first line", | |
| "size": "medium", | |
| "color": "blue", | |
| "font": "handwritten marker" | |
| }, | |
| { | |
| "text": "3. Cut latency 40%", | |
| "location": "below the second line", | |
| "size": "medium", | |
| "color": "blue", | |
| "font": "handwritten marker" | |
| } | |
| ], | |
| "context": "A candid office photograph.", | |
| "artistic_style": "realistic" | |
| }, | |
| "seed": 20261034 | |
| } | |
| ], | |
| "edit": [ | |
| { | |
| "name": "red_jacket", | |
| "images": [ | |
| "jacket.png" | |
| ], | |
| "caption": { | |
| "short_description": "A young man with short dark hair in a red leather biker jacket holds a black game controller and looks at the camera, against a plain lavender backdrop.", | |
| "objects": [ | |
| { | |
| "description": "A young man with short dark hair and a straight fringe.", | |
| "location": "center", | |
| "relationship": "The only subject.", | |
| "relative_size": "large within frame", | |
| "pose": "standing, holding a game controller with both hands", | |
| "expression": "focused, slight squint", | |
| "clothing": "a red leather biker jacket with silver zips and studs over a black top" | |
| } | |
| ], | |
| "background_setting": "A plain lavender studio backdrop.", | |
| "lighting": { | |
| "conditions": "studio lighting", | |
| "direction": "front-lit", | |
| "shadows": "soft shadows" | |
| }, | |
| "aesthetics": { | |
| "composition": "medium shot, centered", | |
| "color_scheme": "red on lavender", | |
| "mood_atmosphere": "playful" | |
| }, | |
| "photographic_characteristics": { | |
| "depth_of_field": "shallow", | |
| "focus": "sharp focus on the subject", | |
| "camera_angle": "eye-level", | |
| "lens_focal_length": "standard lens (e.g., 35mm-50mm)" | |
| }, | |
| "style_medium": "photograph", | |
| "context": "A studio portrait.", | |
| "artistic_style": "realistic", | |
| "edit_instruction": "Change the subject's black leather jacket to a red leather jacket." | |
| }, | |
| "seed": 20261123 | |
| }, | |
| { | |
| "name": "suitcase_mask", | |
| "images": [ | |
| "suitcase.png" | |
| ], | |
| "mask": "suitcase_mask.png", | |
| "caption": { | |
| "short_description": "A surprised woman in a straw hat and a denim dress holds a vintage brown leather suitcase under her arm against a white wooden wall.", | |
| "objects": [ | |
| { | |
| "description": "A young woman with a shoulder-length bob, a straw hat and a blue denim shirt dress.", | |
| "location": "center", | |
| "relationship": "The only subject.", | |
| "relative_size": "large within frame", | |
| "pose": "one hand on her temple", | |
| "expression": "surprised, mouth open" | |
| }, | |
| { | |
| "description": "A vintage brown leather suitcase with straps and brass corners.", | |
| "location": "lower right", | |
| "relationship": "Held under the woman's left arm.", | |
| "relative_size": "medium" | |
| } | |
| ], | |
| "background_setting": "A white painted wooden plank wall.", | |
| "lighting": { | |
| "conditions": "bright studio light", | |
| "direction": "front-lit", | |
| "shadows": "minimal shadows" | |
| }, | |
| "aesthetics": { | |
| "composition": "medium shot", | |
| "color_scheme": "blue, brown and white", | |
| "mood_atmosphere": "playful surprise" | |
| }, | |
| "photographic_characteristics": { | |
| "depth_of_field": "shallow", | |
| "focus": "sharp focus on the subject", | |
| "camera_angle": "eye-level", | |
| "lens_focal_length": "standard lens (e.g., 35mm-50mm)" | |
| }, | |
| "style_medium": "photograph", | |
| "context": "A stock travel photograph.", | |
| "artistic_style": "realistic", | |
| "edit_instruction": "Replace the yellow suitcase with a vintage brown leather suitcase." | |
| }, | |
| "seed": 20261124 | |
| }, | |
| { | |
| "name": "goose_farm", | |
| "images": [ | |
| "strip_woman.png" | |
| ], | |
| "caption": { | |
| "short_description": "A laughing young woman with long brown hair and bangs, in a white blouse and brown suede vest, sits on a farm holding a white goose, with a wooden barn behind her.", | |
| "objects": [ | |
| { | |
| "description": "A young woman with long brown hair and bangs.", | |
| "location": "center", | |
| "relationship": "The only subject.", | |
| "relative_size": "large within frame", | |
| "pose": "sitting, holding a goose", | |
| "expression": "laughing", | |
| "clothing": "white puff-sleeve blouse, brown suede fringed vest, striped skirt" | |
| }, | |
| { | |
| "description": "A white domestic goose with an orange beak.", | |
| "location": "center right", | |
| "relationship": "Held in the woman's arms.", | |
| "relative_size": "medium" | |
| } | |
| ], | |
| "background_setting": "A rustic farm with an old wooden barn, a wooden fence and green hills under a blue sky.", | |
| "lighting": { | |
| "conditions": "bright daylight", | |
| "direction": "side-lit from the right", | |
| "shadows": "natural shadows" | |
| }, | |
| "aesthetics": { | |
| "composition": "medium shot", | |
| "color_scheme": "warm browns and greens", | |
| "mood_atmosphere": "joyful, rustic" | |
| }, | |
| "photographic_characteristics": { | |
| "depth_of_field": "shallow", | |
| "focus": "sharp focus on the subject", | |
| "camera_angle": "eye-level", | |
| "lens_focal_length": "standard lens (e.g., 35mm-50mm)" | |
| }, | |
| "style_medium": "photograph", | |
| "context": "A lifestyle photograph.", | |
| "artistic_style": "realistic", | |
| "edit_instruction": "Change the background to a farm with a wooden barn and make the woman hold a white goose." | |
| }, | |
| "seed": 20261125 | |
| }, | |
| { | |
| "name": "pixel_art", | |
| "images": [ | |
| "strip_woman.png" | |
| ], | |
| "caption": { | |
| "short_description": "A pixel art picture of a laughing young woman with long brown hair eating breakfast with a fork in a camper van.", | |
| "objects": [ | |
| { | |
| "description": "A young woman with long brown hair and bangs.", | |
| "location": "center", | |
| "relationship": "The only subject.", | |
| "relative_size": "large within frame", | |
| "pose": "sitting at a small table, holding a fork", | |
| "expression": "laughing", | |
| "clothing": "white blouse and brown vest" | |
| } | |
| ], | |
| "background_setting": "The inside of a camper van with round windows, curtains and string lights, a plate of food on the table.", | |
| "lighting": { | |
| "conditions": "bright daylight", | |
| "direction": "from the window", | |
| "shadows": "simple pixel shadows" | |
| }, | |
| "aesthetics": { | |
| "composition": "medium shot", | |
| "color_scheme": "warm retro palette", | |
| "mood_atmosphere": "cheerful" | |
| }, | |
| "style_medium": "pixel art", | |
| "context": "A retro game illustration.", | |
| "artistic_style": "pixel art", | |
| "edit_instruction": "Turn the image into the pixel art style." | |
| }, | |
| "seed": 20261126 | |
| }, | |
| { | |
| "name": "blue_whale", | |
| "images": [ | |
| "origami_whale.png" | |
| ], | |
| "caption": { | |
| "short_description": "A deep blue origami whale swims through bright orange paper clouds, with tiny paper birds following it.", | |
| "objects": [ | |
| { | |
| "description": "An origami whale folded from deep blue paper.", | |
| "location": "center", | |
| "relationship": "Swimming between orange paper clouds.", | |
| "relative_size": "large within frame" | |
| } | |
| ], | |
| "background_setting": "A cut-paper sky with bright orange paper clouds.", | |
| "lighting": { | |
| "conditions": "soft studio light", | |
| "direction": "front-lit", | |
| "shadows": "soft paper shadows" | |
| }, | |
| "aesthetics": { | |
| "composition": "wide composition", | |
| "color_scheme": "deep blue and orange", | |
| "mood_atmosphere": "whimsical" | |
| }, | |
| "style_medium": "photograph of a papercraft diorama", | |
| "context": "A papercraft illustration.", | |
| "artistic_style": "whimsical", | |
| "edit_instruction": "Change the whale's color to blue and the clouds to orange." | |
| }, | |
| "seed": 20261127 | |
| }, | |
| { | |
| "name": "no_bell", | |
| "images": [ | |
| "still_life.png" | |
| ], | |
| "caption": { | |
| "short_description": "On a white windowsill, a row of five red apples and one green pear in morning light, minimal still life.", | |
| "objects": [ | |
| { | |
| "description": "Five red apples and one green pear in a row.", | |
| "location": "center", | |
| "relationship": "Side by side on the windowsill.", | |
| "relative_size": "medium" | |
| } | |
| ], | |
| "background_setting": "A white windowsill and a pale wall.", | |
| "lighting": { | |
| "conditions": "soft morning daylight", | |
| "direction": "side-lit from the left", | |
| "shadows": "soft shadows" | |
| }, | |
| "aesthetics": { | |
| "composition": "centered row", | |
| "color_scheme": "red and green on white", | |
| "mood_atmosphere": "minimal" | |
| }, | |
| "photographic_characteristics": { | |
| "depth_of_field": "deep", | |
| "focus": "sharp focus on the subject", | |
| "camera_angle": "eye-level", | |
| "lens_focal_length": "standard lens (e.g., 35mm-50mm)" | |
| }, | |
| "style_medium": "photograph", | |
| "context": "A still-life photograph.", | |
| "artistic_style": "realistic", | |
| "edit_instruction": "Remove the brass bell from the apple." | |
| }, | |
| "seed": 20261128 | |
| }, | |
| { | |
| "name": "red_dress", | |
| "images": [ | |
| "dress_person.png", | |
| "dress_item.png" | |
| ], | |
| "caption": { | |
| "short_description": "A young woman with curly black hair stands with crossed legs in a red pleated knee-length dress with ruffled hem and black heeled sandals, against a white studio backdrop.", | |
| "objects": [ | |
| { | |
| "description": "A young woman with voluminous curly black hair.", | |
| "location": "center", | |
| "relationship": "The only subject.", | |
| "relative_size": "large within frame", | |
| "pose": "standing, hands behind her back, legs crossed", | |
| "expression": "neutral", | |
| "clothing": "a red pleated cap-sleeve dress with an elastic waist and a ruffled hem, black heeled sandals" | |
| } | |
| ], | |
| "background_setting": "A plain white studio backdrop.", | |
| "lighting": { | |
| "conditions": "studio lighting", | |
| "direction": "front-lit", | |
| "shadows": "soft floor shadow" | |
| }, | |
| "aesthetics": { | |
| "composition": "full-body shot, centered", | |
| "color_scheme": "red on white", | |
| "mood_atmosphere": "elegant" | |
| }, | |
| "photographic_characteristics": { | |
| "depth_of_field": "shallow", | |
| "focus": "sharp focus on the subject", | |
| "camera_angle": "eye-level", | |
| "lens_focal_length": "standard lens (e.g., 35mm-50mm)" | |
| }, | |
| "style_medium": "photograph", | |
| "context": "A fashion catalogue photograph.", | |
| "artistic_style": "realistic", | |
| "edit_instruction": "Dress the person in <image_1> in the dress from <image_2>." | |
| }, | |
| "seed": 20261129 | |
| }, | |
| { | |
| "name": "sign_text", | |
| "images": [ | |
| "bicycle_src.png" | |
| ], | |
| "caption": { | |
| "short_description": "A red city bicycle with a wicker basket leans against a white brick wall on a sunny morning. A small wooden sign above it reads \"CLOSED\".", | |
| "objects": [ | |
| { | |
| "description": "A red city bicycle with a wicker basket.", | |
| "location": "center", | |
| "relationship": "Leaning against the wall, below the sign.", | |
| "relative_size": "large within frame" | |
| } | |
| ], | |
| "background_setting": "A white brick wall with a green wooden door and a cobblestone pavement.", | |
| "lighting": { | |
| "conditions": "bright morning sun", | |
| "direction": "side-lit from the right", | |
| "shadows": "crisp shadows" | |
| }, | |
| "aesthetics": { | |
| "composition": "centered", | |
| "color_scheme": "red and green on white", | |
| "mood_atmosphere": "calm" | |
| }, | |
| "photographic_characteristics": { | |
| "depth_of_field": "deep", | |
| "focus": "sharp focus on the subject", | |
| "camera_angle": "eye-level", | |
| "lens_focal_length": "standard lens (e.g., 35mm-50mm)" | |
| }, | |
| "style_medium": "photograph", | |
| "text_render": [ | |
| { | |
| "text": "CLOSED", | |
| "location": "top center, on a sign above the bicycle", | |
| "size": "medium", | |
| "color": "white", | |
| "font": "hand-painted serif", | |
| "appearance_details": "painted on a small dark wooden board" | |
| } | |
| ], | |
| "context": "A street photograph.", | |
| "artistic_style": "realistic", | |
| "edit_instruction": "Change the text \"OPEN\" to \"CLOSED\"." | |
| }, | |
| "seed": 20261130 | |
| } | |
| ] | |
| } |