Skip to content

Trending AI Today

Image-to-image models trending today

Models · image-to-image · Saturday, October 24, 2026

2 of the 40 models on Hugging Face’s trending list carry this task tag today, in Hugging Face’s order, with entries held back when likes are not matched by downloads.

Collected · snapshot shipped with the site build, not a live feed

2 of 2 models · Hugging Face order

  1. Number 1: black-forest-labs/flux-3-image-klein-comfy

    Image to image

    No. 3 by Hugging Face trending score (624) · repository created 9 days ago · +8 likes since 2026-10-23.

    535K downloads in 30 days · 1,430 likes

    Other (custom terms)· read the terms

  2. Number 2: black-forest-labs/flux-3-image-klein

    Image to image5.55B parameters

    No. 22 by Hugging Face trending score (188) · repository created 10 days ago · +3 likes since 2026-10-23.

    106K downloads in 30 days · 659 likes

    Other (custom terms)· read the terms

Positions follow Hugging Face’s trending order with 0 of 40 entries held back for likes that downloads do not confirm. Sorting by another column changes the order on your screen only.

Source: Hugging Face public API · updated

About image-to-image models

Task tag image-to-image

Image-to-image is the tag for models that take a picture and return a changed picture: editing by instruction, style transfer, relighting, changing the camera angle, swapping a face or an object. Most trending entries are adapters trained on top of a large image model, not standalone models.

Before you pick one

  1. Identify the base model

    An adapter only works with the exact base model family it was trained on. The model page shows the declared base; if none is declared, read the card before downloading.

  2. Consider what the edit is for

    Face-swap and identity-transfer models are listed because they trend, not because they are endorsed. Using a real person’s likeness without consent is illegal in many places and against most platform rules.

  3. Downloads can be zero for honest reasons

    Adapters are often fetched through an interface tool or a file link that Hugging Face does not count as a model download. When likes are high and downloads are zero, the entry is held back and the numbers are shown so you can decide.

Questions readers ask

What is the difference between image-to-image and text-to-image?

Text-to-image starts from a prompt alone. Image-to-image starts from an existing picture, usually with a prompt that says what to change.

Why do these repositories rarely show a parameter count?

Adapters and single-file checkpoints often lack the safetensors metadata the API reads, so the field stays empty.

Do I need the base model as well?

For an adapter, yes: you load the base model and then the adapter on top. The adapter repository is small because it holds only the difference.