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.
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.
Description
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.
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.
FAQ
Comments (12)
Cant wait for V2
What kind of images would you be making with this V2 that the V1 cannot do?
@cranpeach nothing yet testing out just seen that you put v2 at the end. love the lora a lot so far
I figured, if you run into something let me know so I can add it to my v2 dataset
I've been searching for exactly this lora for flux klein just yesterday, this is really awesome, can't wait to try it out
Same, I've been looking for a minute but couldn't find it. Would love to see your images/review when you get a chance!
谢谢,找了很久,终于有人做这个了,感谢
this looks REALLY useful
I love the LoRA! It really replaced an entire workflow in Photoshop. Since it even handles shadows, it's even better! Also, thanks a lot for the 100-Buzz tip and the pin :)
Of course! Would love to see the random shit people make using this lol
The LoRA works exceptionally well! I could only achieve this effect with Flux.2 Dev which is a much heavier model. Thank you!
Thank you so much! Been looking for this, it's like Photoshop's harmonize. Can't wait for V2!
Details
Files
fusion2250.safetensors
Mirrors
fusion2250.safetensors
F2K_9b-图像融合fusion2250.safetensors
fusion2250-mid_2548669-vid_2864208.safetensors
fusion2250-mid_2548669-vid_2864208.safetensors
Image Blend Fusion - Klein9B - Blend the object into the image seamlessly.safetensors
Image Blend Fusion - Klein9B - Blend the object into the image seamlessly.safetensors
klein9b-rongtu-lora.safetensors
fusion2250-mid_2548669-vid_2864208.safetensors
fusion2250-mid_2548669-vid_2864208.safetensors
50-fusion2250.safetensors








