Passer au contenu principal

MetaAdded Sep 3, 2026Image generation and editingAnonymized

Muse Image

Muse Image is Meta’s image model, known for faithful instruction following, accurate text and fine detail. It pairs with Muse Image Edit, which changes only what you ask and can compose from several reference images.

muse-imagePOST https://api.venice.ai/api/v1/image/generate
Price per image
$0.02
Aspect ratios
7 ratios
default 1:1
Reference images
Up to 6
combined in one edit
Prompt limit
10,000
characters

Pricing

USD per image
Per image
$0.02
Edit
$0.02

Optional upscale: $0.02 at 2x and $0.08 at 4x.

Examples

Specs

Model ID
muse-image
Edit model ID
muse-image-edit
Endpoint
POST /api/v1/image/generate
Aspect ratios
1:13:216:921:99:162:33:4
Prompt limit
10,000 characters
Steps
default 20, max 50
Added
Sep 3, 2026

Capabilities

Modalities
Text
Input
Image
Input and output
Features
Image editing
muse-image-edit
Multi-image editing
up to 6 images
Web-grounded generation
Not supported
Style references
Not supported
Upscale
2x and 4x
POST/api/v1/image/generateRecommended
curl https://api.venice.ai/api/v1/image/generate \
-H "Authorization: Bearer $VENICE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "muse-image",
"prompt": "A retro travel poster with the bold headline \"VENICE\" in large condensed serif type, sunset color palette",
"aspect_ratio": "1:1"
}'

Privacy

Tier 1 · this model
Anonymized

Venice hides your identity and stores no prompts. Meta still sees the content.

Tier 2
Private

Not available

Tier 3
TEE

Not available

Tier 4
End-to-end encrypted

Not available

Variants

VariantModel IDPrivacyPriceAdded
muse-imageAnonymized$0.02 / imageSep 2026
muse-image-editAnonymized$0.02 / editSep 2026