Nvidia Cosmos 3 Super Text To Image

Nvidia Cosmos 3 Super Text To Image

Playground

NVIDIA Cosmos 3 Super Text to Image is a fast AI image generation model that creates high-quality images from text prompts with configurable image size, inference steps, guidance, and output count. Ready-to-use REST inference API for creative design, marketing visuals, product mockups, concept art, brand assets, social media content, and professional text-to-image workflows with simple integration, no coldstarts, and affordable pricing.

Features

NVIDIA Cosmos 3 Super Text-to-Image

NVIDIA Cosmos 3 Super Text-to-Image generates high-quality images from natural-language prompts with support for negative prompting, size presets, inference step control, guidance scaling, and flexible output formats. It is suitable for portrait generation, editorial visuals, concept art, marketing creatives, and other prompt-driven image generation workflows.

Why Choose This?

• High-quality text-to-image generation Create polished, detailed images from natural-language prompts.

• Negative prompt support Use negative_prompt to suppress unwanted artifacts, styles, or scene elements.

• Flexible generation controls Adjust num_inference_steps and guidance_scale to balance quality, fidelity, and generation behavior.

• Preset sizing Use size presets for predictable output framing and composition.

• Multiple output formats Export the result in supported formats such as jpeg.

• Production-ready API Suitable for editorial visuals, concept exploration, commercial content, and creative ideation workflows.

Parameters

How to Use

1. Write your prompt — describe the subject, style, lighting, mood, and composition you want.
2. Add a negative prompt (optional) — specify anything you want the model to avoid.
3. Choose size (optional) — select the output aspect or size preset.
4. Adjust generation settings (optional) — tune num_inference_steps and guidance_scale as needed.
5. Choose output format (optional) — select the format that best fits your workflow.
6. Submit — run the model and download the generated image.

Example Prompt

A photorealistic high-fashion portrait of an adult female model standing in a minimalist art gallery, sculptural black dress, polished concrete floor, large abstract paintings, soft museum lighting, confident elegant pose, luxury editorial photography, clean composition, ultra-detailed

Pricing

Just $0.04 per image.

Billing Rules

• Each generated image costs $0.04
• Pricing is fixed per image
• size, num_inference_steps, guidance_scale, and output_format do not affect pricing

Best Use Cases

• Portrait generation — Create polished editorial or studio-style portraits.
• Fashion and luxury visuals — Generate refined commercial and magazine-style imagery.
• Concept art — Explore visual ideas and art directions quickly.
• Marketing creatives — Produce ad visuals, campaign concepts, and branded content.
• Prompt-based ideation — Iterate on scenes, outfits, settings, and visual moods from text.

Pro Tips

• Be specific in your prompt about subject, environment, lighting, and style.
• Use negative_prompt when you want to suppress clutter, artifacts, or undesired aesthetics.
• Increase num_inference_steps when you want more refined results, if generation time is acceptable.
• Adjust guidance_scale when you want tighter prompt adherence.
• Start with the default settings first, then tune generation controls only if needed.

Notes

• prompt is required.
• negative_prompt is optional but useful for tighter control.
• Pricing is fixed at $0.04 per image.
• Better prompts usually improve both consistency and visual quality.

Related Models

• Other NVIDIA image generation workflows — Useful when you need different quality, speed, or control trade-offs.
• Prompt-based visual generation models — Useful when you want alternate image generation styles or rendering characteristics.

# Submit the task
curl --location --request POST "https://api.wavespeed.ai/api/v3/nvidia/cosmos-3-super/text-to-image" \
--header "Content-Type: application/json" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}" \
--data-raw '{
    "negative_prompt": "",
    "size": "1:1",
    "num_inference_steps": 28,
    "guidance_scale": 4,
    "output_format": "jpeg"
}'

# Get the result
curl --location --request GET "https://api.wavespeed.ai/api/v3/predictions/${requestId}/result" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}"