MiniMax Image-01 / テキストから画像
MiniMax’s first text-to-image model with subject reference support. Delivers high-fidelity visuals, detailed lighting, and complex scene composition. Generates realistic human/object renders with natural textures, ideal for concept art, product visualization, and creative design.
Image-01Text & Subject-Reference Image Generation
Image-01 generates stills from text or subject references across eight aspect ratios, with optional prompt optimizer, seed control, and custom width/height.
At a Glance
Image-01 Capabilities
Reference-aware stills with flexible canvas control.
Subject-Reference I2I
Feed a subject reference so identity stays stable across campaign variants and product recompositions.
Eight Aspect Ratios
1:1, 16:9, 4:3, 3:2, 2:3, 3:4, 9:16, and 21:9 cover social, print, and cinematic placements.
Prompt Optimizer
Optional prompt_optimizer rewrites brief descriptions into richer generation prompts automatically.
Seed & Custom Canvas
Pin seeds for reproducible frames or set explicit width and height for fixed layouts.
How It Works
From brief to subject-aware still.
Write or Optimize Prompt
Enter a brief or enable prompt_optimizer for auto-enhanced prompts.
Optional Subject Reference
Add subject_reference for identity-locked I2I variants.
Pick Ratio or Custom Size
Choose from eight ratios or set explicit width and height.
Pin Seed if Needed
Lock a seed for reproducible campaign frames.
Image-01 Domains
Where subject identity and canvas control matter.
Character Campaigns
Lock talent identity across creative variants.
Social Carousels
Multi-ratio frames with consistent style.
Product Catalogs
Subject-aware packshots across channels.
Mood Boards
Prompt optimizer for exploration from short briefs.
Prompt Tips
Better Image-01 stills on the first pass.
Subject references work best when each image has a single clear job.
Enable prompt_optimizer when your brief is short and you want richer detail.
Reuse a seed so small brief edits do not re-roll the entire composition.
Image-01 Quickstart
Subject-aware image generation.
curl -X POST "https://api.powertokens.ai/v1/images/generations" \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type": "application/json" \
-d '{
"model": "image-01",
"prompt": "Editorial close-up portrait with sculptural hat, photorealistic studio light.",
"size": "2K",
"response_format": "url",
"watermark": false,
"aspect_ratio": "16:9"
}'Technical Specifications
Confirmed parameters and runtime execution protocols.
料金詳細
このモデルの実際の課金は、API リクエストで渡される特定のパラメータに基づいて動的に計算されます。以下は具体的な組み合わせとそれに対応する料金です：
| モダリティ | クレジット | 料金 (USD) |
|---|---|---|
| Standard | 4/ Image | $0.004 |
Recommended Related Models
Explore complementary video and multimodal models with your unified API key.
wan2.7-image
wan2.7-image
Alibaba's unified image generation and editing model supporting text-to-image, sequential image generation, instruction-based editing, multi-reference generation (up to 9 images), and interactive bbox editing. Features precise "face sculpting" for diverse, non-generic portraits and a "palette" function for exact Hex color control. Renders up to 3K tokens of long-form text (12 languages) at print quality. Generates up to 12 images per run
Seedream 5.0
seedream-5-0-260128
Supports text, single-image and multi-image inputs, and enables the generation of image sets
Wan 2.7 Image Pro
wan2.7-image-pro
Wan2.7–image-pro，supports text to image, text/image to sequential images, image editing, multi-image reference generation, and interactive editing. Delivers enhanced performance in text rendering, subject consistency, and complex instruction following.
Kling Image O1
kling-image-o1
Advanced image generation model from the Kling O1 family. Supports text-to-image and image-to-image workflows with deep semantic understanding. Features character/subject consistency across generations, multi-reference input (up to 7 images), and intelligent aspect ratio adaptation. Professional-grade output suitable for commercial creative pipelines
Frequently Asked Questions
Everything you need to know before integrating this model.
Start Building with Image-01 Today
Create an account in seconds to receive free test credits. No upfront payment or long-term contract required.