A flat-lay product photo of a leather wallet on a marble surface, warm studio lighting with soft shadows, shot from directly above, commercial quality.
FLUX.2 Pro Text to image API
Create detailed images from a written brief or combine a prompt with visual references for controlled transformations.
Text-to-image uses a fixed frame; image editing accepts up to six references and can infer the output frame automatically.
Pricing
Image pricing
- Generated image
- $0.03
Playground Examples
Try production-style prompt starters.
A minimalist movie poster with the title 'ECLIPSE' in bold serif typography, a lone silhouette on a cliff against an orange sunset, cinematic composition.
A fantasy ranger, full-body front view on a white background, detailed leather armor with emerald accents, longbow across the back, semi-realistic concept art.
Similar Models
Compare adjacent capabilities before switching models.
ByteDance · Image
Seedream V5 Pro
ByteDanceByteDance image generation and editing for cinematic visuals, product shots, precise local edits, and reference-guided creative work.
OnlineTry model
ByteDance · Image
Seedream 4.5
ByteDanceByteDance image generation and editing for reference consistency, multi-image composition, typography, and polished visual creatives.
OnlineTry model
Google · Image
Nano Banana Pro
GoogleGoogle's premium image generation and editing model for readable text, product mockups, visual explainers, and reference-guided brand assets.
OnlineTry model
Model overview
FLUX.2 Pro for high-fidelity image generation and guided editing
FLUX.2 Pro on sjolt supports prompt-only generation and reference-guided editing. Use detailed natural-language direction for product imagery, campaign graphics, architectural scenes, character concepts, and typography-led layouts.
Photorealistic detail and lighting
Build product shots, portraits, interiors, and environmental scenes with sharp textures, believable materials, controlled light, and polished composition.
- Supports Text to image and reference-asset generation workflows.
- Fits product assets, ad previews, visual direction, and social content tests.
- Adjust configured inputs, media, and switches before generation.
Typography inside generated images
Describe headlines, labels, signs, and layout intent directly in the prompt for posters, campaign graphics, packaging concepts, and interface mockups.
Prompt-led generation
Multi-image visual guidance
Combine up to six reference images to guide subjects, products, style, color, materials, or composition while directing the transformation in plain language.
- Compare available models from Black Forest Labs, Google, MiniMax, OpenAI, ByteDance, Kuaishou, SJolt AI in one place.
- Copy the request body directly to the server to reduce frontend/backend parameter drift.
- Failure states, retries, result preview, and review checkpoints stay in the same workflow.
Model characteristics
Built for detailed creative direction across generation and editing workflows.
Prompt-only creation
Describe the subject, environment, composition, lighting, color, materials, and intended visual medium to generate a complete image from text.
Reference-guided editing
Use existing visuals for subject identity, styling, content remixing, or composition guidance, then explain the desired changes in the prompt.
Flexible framing
Choose square, landscape, or portrait output. Reference-guided tasks can also infer framing automatically from the supplied images.
Asynchronous API workflow
Submit a generation task, receive a task identifier, then poll the shared status route or use a callback to receive completion updates.
FAQ
These are the first questions to answer when evaluating this model.
Which FLUX.2 Pro workflows are available on sjolt?
Use text-to-image for prompt-only creation or image-edit when one or more visual references should guide the result.
How many reference images can I use?
The image-edit route accepts from one to 6 JPG, JPEG, PNG, or WebP references.
Which aspect ratios are supported?
Text-to-image supports 1:1, 4:3, 3:4, 16:9, 9:16. Image editing supports the same fixed frames plus auto framing.
How should I write a FLUX.2 Pro prompt?
Specify the subject, composition, lighting, visual style, colors, materials, camera perspective, and any exact text that should appear. For editing, also explain what to preserve and what to change.
How do API tasks complete?
A successful request returns a task_id. Poll the shared task-status endpoint until completion, or provide a top-level webhook URL for a terminal-state callback.