Codesota · Tasks · Image generationHome/Tasks/Computer Vision/Image generation

Image generation.

AI image generation uses generative AI to create new visual content from text prompts or existing images, by learning patterns from massive datasets of images and text. These trained algorithms, often neural networks, then produce novel images that are statistically likely to fit the provided prompt, mimicking styles, shapes, and colors they've learned. Examples of such models include Midjourney, Stable Diffusion, and DALL-E.

11
Datasets
0
Results
Canonical metric
§ 02 · Canonical benchmark

The reference dataset.

Seeking canonical benchmark for this task.

Suggest one →
§ 03 · Top 10

Leading models.

Leading models across all datasets in this task.

No results yet. Be the first to contribute.

What were you looking for on Image generation?

Didn't find the model, metric, or dataset you needed? Tell us in one line. We read every message and reply within 48 hours.

§ 04 · All datasets

Tracked datasets.

11 datasets tracked for this task.

CVTG-2K
0 results
GenEval
0 results
ICE-Bench (Task1-31 Overall)
0 results
ImageNet 1024x1024
0 results
ImageNet 256x256
0 results
ImageNet 512x512
0 results
LongText-Bench
0 results
OmniContext
0 results
OneIG-EN
0 results
OneIG-ZH
0 results
TIIF-Bench mini
0 results
§ 05 · Related tasks

Other tasks in Computer Vision.

3D Understanding3D generationDepth estimationFew-Shot Image ClassificationImage ClassificationImage editingImage segmentationOCR
Reply within 48 hours · No newsletter

Didn't find what you came for?

Still looking for something on Image generation? A missing model, a stale score, a benchmark we should cover — drop it here and we'll handle it.

Real humans read every message. We track what people are asking for and prioritize accordingly.