Qwen Image 2.1 release

Suggested tags: Blend the <object> into the image seamlessly

Suggested strength: 1.0

The purpose is to run a single image that already has a roughly cutout image of objects, people, cars, etc and run it through the model to make it blend seamlessly into backgrounds, onto people, all kinds of things, see examples.

Still getting my ideal Qwen 2.1 workflow where I like it, seems to work great at 2.0 megapixels, some things work better on Klein still but figured I'd port this over at least. Pretty flexible with prompting, can say Blend the Fat Pikachu into the bath tub seamlessly instead of image etc.

Flux Klein 9B/4B releases:

Suggested tags: Blend the <object> into the image seamlessly

Suggested strength: 0.8-1.0

Suggested usage: Inspired by the Image Fusion model for Qwen Image Edit 2511.

The purpose is to run a single image that already has a roughly cutout image of objects, people, cars, etc and run it through the model to make it blend seamlessly into backgrounds, onto people, all kinds of things. The more simple the task the better it does. See the before/after examples for what it can do currently. The after images should still have their workflow if you need a workflow.

Tried something complex like a UFO floating in a city and it created a dropshadow in the sky unfortunately, but that may be for a V2.