Muse Image, a new place to start.
Turn an idea into an image with Meta's Muse Image. The Auto default for free users, at just 1 credit per image in Playground. Try it free below.
Free, no sign-up required.
How Muse Image works
1. Start with a packaging idea
2. See it as a realistic mockup
3. Explore another colorway
Try a realistic product mockup
Start with the packaging, materials and light. A specific brief helps you explore how your brand could look on a real product before arranging a shoot.
Create a hyperrealistic perfume packaging mockup for “FORME”: a clear glass bottle with pale amber perfume, a champagne metal cap, an ivory label and matching carton. Set them on travertine in warm window light. Use olive lettering reading “FORME”, “EAU DE PARFUM” and “50 mL”. Show realistic glass reflections, paper texture and soft shadows.Try this prompt free
The images above are illustrative mockups of the workflow. Run the prompt to see your own Muse Image result.
Independent model rankings
Muse Image on Arena
See how Muse compares in Arena’s image generation and editing evaluations, where people vote for the results they prefer. Each score links to its original leaderboard.
Text-to-image generation
- #7 · Muse Image
- 1,277 ± 6
- Votes
- 26,045
Single-image editing
- #6 · Muse Image
- 1,403 ± 5
- Votes
- 83,408
Arena snapshot dated , checked . The ± values are Arena’s reported uncertainty. Scores reflect human preferences, not accuracy percentages; rankings can change as votes accumulate. These scores evaluate the model, not Playground’s trial settings.
How Muse Image compares
Three of the most capable image models in the world, side by side. Pick the one that matches the job.
Meta
Muse Image
On this pageA starting point for new ideas, at 1 credit per image.
- Speed
- Varies by prompt
- Output
- Native image output
- Pricing
- 1 credit / image; 3 free trials / month
Best for
Creating from scratch, reference-guided compositions, and everyday image generation.
- Text-to-image generation
- Reference-guided editing
- Auto default for free users
OpenAI
GPT Image 2
An earlier GPT Image model for typography, text rendering, and instruction following.
- Speed
- ~15-25s
- Output
- Up to 1024 × 1536
- Pricing
- Free — 3 / month
Best for
Posters, ads, packaging, infographics, and any image with legible text.
- Reads dense prompts and complex layouts
- Renders crisp typography and on-image text
- Edits with strict prompt fidelity
Google Gemini 3 Pro Image
Nano Banana Pro
The highest-fidelity Gemini model. 4K native output, sharper detail, and improved photorealism.
- Speed
- ~25-40s
- Output
- Up to 4K, 10 ARs
- Pricing
- 1 free / 30 days, no sign-up
Best for
Photoreal hero shots, large-format prints, and detailed scene composition.
- 4K native resolution output
- Best-in-class photorealism
- Improved text + spatial reasoning
Looking for OpenAI’s newer models? Try GPT Image 2.5 and compare Sunburst with Flare.