Stats
Actions
Tags
From model-bridge
Generate optimized prompts for FLUX.1 models (schnell/dev) and execute image generation.
How this skill is triggered — by the user, by Claude, or both
Slash command
/model-bridge:flux-promptThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Generate optimized prompts for FLUX.1 models (schnell/dev) and execute image generation.
Generate optimized prompts for FLUX.1 models (schnell/dev) and execute image generation.
Use this skill when the user wants to:
FLUX uses dual text encoders (T5 + CLIP) with strong natural language understanding. Front-load important elements - FLUX weighs earlier content more heavily.
[SUBJECT] + [ACTION/POSE] + [STYLE] + [LIGHTING] + [COLOR/ATMOSPHERE] + [TECHNICAL DETAILS]
the text "HELLO" in bold letterscolor #FF6B35shot on Canon EOS R5, 85mm f/1.4golden hour light casting long shadows++, --, :1.2) - NOT SUPPORTEDFLUX excels at rendering text in images:
the text "HELLO WORLD" in elegant copper foil sans-serif typography
a neon sign reading "OPEN 24/7" glowing pink against a dark alley
vintage travel poster with "TOKYO" in large Art Deco geometric font
Photography:
shot on [camera] - iPhone 16, Canon EOS R5, Hasselblad[focal length]mm lens - 24mm wide angle, 85mm portrait, 200mm telephotof/[aperture] - f/1.4 shallow DoF, f/8 sharp focus[lighting] - golden hour, Rembrandt lighting, rim light, soft boxStyles:
photorealistic, cinematic, documentary styleeditorial, fashion photography, film grainhyperrealistic, studio photographyComposition:
close-up, medium shot, wide shot, bird's-eye viewrule of thirds, centered compositionbokeh background, shallow depth of field./scripts/flux-generate.sh "YOUR PROMPT HERE"
./scripts/flux-generate.sh "YOUR PROMPT HERE" --model dev --steps 28
When user requests a FLUX image:
Understand the request - What's the main subject? Style? Purpose?
Construct optimized prompt following this pattern:
Generate the image using the appropriate script
Offer refinements - Seed variations, style adjustments, composition changes
Young woman with auburn hair and freckles, warm genuine smile, golden hour
sunlight streaming through a window, soft bokeh background of a cozy cafe
interior, shot on Canon EOS R5 with 85mm f/1.4 lens, natural skin tones,
editorial portrait style
Minimalist coffee packaging design on a marble surface, the text "DAWN BREW"
in elegant copper foil sans-serif typography at center, steam rising from a
cup in soft focus background, warm morning light from the left, color palette
#8B4513 brown and #D4AF37 gold accents, commercial product photography
Massive bioluminescent mushroom forest at twilight, towering fungi with caps
glowing vibrant pink and blue, soft mist between thick stalks, winding stone
path leading to a cozy cottage with warm amber light from windows, tiny glowing
particles drifting like embers, digital fantasy painting, rich saturated colors
Professional headshot of a confident businesswoman in her 40s, navy blazer,
neutral gray backdrop, Rembrandt lighting with soft fill, hair color #4A3728,
shot at f/5.6 for sharp features with slightly soft background, corporate
portrait, high quality
npx claudepluginhub lando-labs/claude-plugins --plugin model-bridgeGenerates images from text prompts using fal.ai FLUX.1/2 Pro/Dev/Schnell and SDXL models. Configures image sizes, guidance scale, inference steps, LoRA, seeds, batching via TypeScript/Python APIs.
Enhances image generation prompts with Subject-Context-Style structure, lighting physics, camera terminology, and character consistency patterns. Useful for creating detailed, physically coherent image prompts.
Generates optimized prompts for Gemini 2.5 Flash Image (Nano Banana) using best practices for photorealistic shots, art styles, and multi-turn editing workflows.