Minimax Music 2.5Vidu Contest
WaveSpeed.ai
홈/탐색/Flux Image Tools/wavespeed-ai/flux-srpo
text-to-image

text-to-image

Flux SRPO Text-To-Image Model

wavespeed-ai/flux-srpo

FLUX SRPO [dev] is a 12-billion-parameter flow transformer that generates high-quality, aesthetically rich images from text prompts for personal and commercial use. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Input
width
height
1024 × 1024 px
Range: 256 - 1536
If enabled, the output will be encoded into a BASE64 string instead of a URL. This property is only available through the API.
If set to true, the function will wait for the result to be generated and uploaded before returning the response. It allows you to get the result directly in the response. This property is only available through the API.

Idle

A young woman with braided hair, wearing a linen dress, picking wildflowers in a sun-drenched meadow, a wicker basket in her hand, impressionistic style, soft focus, golden hour lighting.

이 요청에는 $0.025 실행당가 필요합니다.

$1으로 이 모델을 약 40회 실행할 수 있습니다.

추가 안내:

예시전체 보기

A young woman with braided hair, wearing a linen dress, picking wildflowers in a sun-drenched meadow, a wicker basket in her hand, impressionistic style, soft focus, golden hour lighting.
A cozy reading nook in a rustic cabin, a soft blanket draped over an armchair, a steaming mug of coffee on a wooden stool, morning sunlight streaming through the window, peaceful and serene atmosphere, photorealistic, warm tones.
Minimalist apartment living room in Scandinavia, clean lines, neutral color palette with a pop of green from a monstera plant, soft diffused light from a large window, Eames lounge chair, realistic 3D render, tranquil.
Epic cinematic wide shot of the Swiss Alps at sunrise, jagged snow-capped peaks breaking through a sea of low-hanging clouds, vibrant alpenglow painting the sky in hues of orange and pink, a lone eagle soaring, hyperrealistic, 8K, breathtaking.
A portrait of a pensive woman looking out a rain-streaked window at a bustling city street at night, neon signs reflecting on the glass, moody, Blade Runner aesthetic, shallow depth of field, bokeh lights.
A sprawling, mystical elven city built into giant, ancient trees, connected by glowing rope bridges, waterfalls cascading down, ethereal light, high fantasy concept art, hyper-detailed, Lord of the Rings aesthetic.
ultra realistic photo, a beautiful young woman with freckles and messy blonde hair, soft natural light filtering through a window, gentle smile, detailed skin texture, shallow depth of field, 8k, photorealistic
cozy and rustic still life, a steaming cup of coffee on a wooden table, an open book with worn pages, a lit candle casting a warm glow, autumn leaves scattered around, soft focus, warm and inviting atmosphere, hyper-detailed
cinematic film still from a romantic movie, a couple dancing in the rain on a Parisian street at night, warm glow from the streetlights, reflections on the wet cobblestone, joyful expressions, shallow depth of field, anamorphic lens flare, moody and atmospheric, photorealistic, 8k
epic landscape painting of the Scottish Highlands, a dramatic storm clearing at sunset, sunbeams breaking through dark clouds over a vast, misty valley with a serene loch, hyper-detailed, powerful and majestic, style of Albert Bierstadt, digital painting
An explosive burst of colorful powder paint captured in mid-air against a stark black background, dynamic motion, high-speed photography, abstract art, vibrant and energetic, macro details.

README

FLUX SRPO

FLUX SRPO is a high-quality image generation model that creates stunning visuals from text descriptions. Built on the FLUX architecture with SRPO optimization, it delivers exceptional detail, composition, and artistic quality at an affordable price.

Why It Stands Out

  • High-quality generation: Produces sharp, detailed images with excellent composition and aesthetics.
  • Prompt Enhancer: Built-in AI-powered prompt optimization helps craft better descriptions for improved results.
  • Flexible resolution: Customize width and height independently for any aspect ratio.
  • Fine-tuned control: Adjust guidance scale and inference steps to balance quality and creativity.
  • Multiple output formats: Export as JPEG or PNG based on your needs.
  • Reproducibility: Use the seed parameter to recreate exact results or explore variations.

Parameters

ParameterRequiredDescription
promptYesText description of the image you want to generate.
widthNoOutput width in pixels (default: 1024).
heightNoOutput height in pixels (default: 1024).
strengthNoGeneration strength (default: 0.8).
num_inference_stepsNoQuality/speed trade-off (default: 28).
seedNoSet for reproducibility; -1 for random.
guidance_scaleNoPrompt adherence strength (default: 3.5).
output_formatNoOutput format: jpeg or png (default: jpeg).
enable_base64_outputNoReturn base64 string instead of URL (API only).
enable_sync_modeNoWait for result before returning response (API only).

How to Use

  1. Write a prompt describing the image you want. Use the Prompt Enhancer for AI-assisted optimization.
  2. Set dimensions — adjust width and height for your desired aspect ratio.
  3. Adjust parameters — fine-tune guidance scale and inference steps as needed.
  4. Choose output format — select JPEG or PNG.
  5. Click Run and download your image.

Best Use Cases

  • Creative Art & Illustration — Generate unique artwork, concept art, and digital illustrations.
  • Marketing & Social Media — Produce eye-catching visuals for campaigns and posts.
  • Product Visualization — Create product mockups and lifestyle imagery.
  • Design Prototyping — Quickly visualize ideas before committing to full production.
  • Personal Projects — Bring any imaginable scene to life for art and experimentation.

Pricing

OutputPrice
Per image$0.025

Pro Tips for Best Quality

  • Be descriptive in your prompt — include style, mood, lighting, composition, and specific details.
  • Use style keywords like "cinematic," "photorealistic," "watercolor," or "digital art" to guide the aesthetic.
  • Lower guidance scale (2–4) allows more creativity; higher values (5–7) follow prompts more strictly.
  • Fix the seed when iterating to compare the effect of different parameters.
  • Start with default inference steps, then increase for finer detail if needed.

Notes

  • Processing time varies based on resolution and current queue load.
  • Please ensure your prompts comply with content guidelines.