OmniConsistency: Stylized Image Pairs Across 22 Artistic Styles

A large-scale multi-style image translation dataset created by showlab and last updated on May 29, 2025. It contains aligned image pairs for 22 distinct artistic styles, each consisting of a source image, a stylized target image, and a descriptive text prompt. The dataset is suitable for style transfer and conditional generation tasks.

Use Cases

• Style transfer based on aligned source and stylized target image pairs.
• Image-to-image generation conditioned on the source image and style prompt.
• Conditional generation using the descriptive text prompts representing artistic styles.
• Training or benchmarking models for multi-style artistic image translation.

Strengths

• Covers 22 distinct artistic styles, providing variety.
• Contains aligned image pairs (source and target) for each style.
• Includes descriptive text prompts for each style, enabling multimodal tasks.

Limitations

• Row count and dataset size are unknown, which may limit suitability assessment.
• Column-level documentation is absent; field semantics must be inferred after download.
• Description metadata is limited; actual data quality requires manual inspection after download.

Provenance

Source

showlab via Hugging Face.

Collection Method

Likely curated or generated for image translation research.

Time Range

null

Freshness

Last updated 2025-05-29 04:20:39; freshness should be verified.

Geography

null