Warning - Don't take this as definitive and oficial, i'ts just a experimental lora.
Im posting it because i think that is funny to experiment.
Prompt: Remix
This is the same as remix from @NO8D , but i just trained with few data for testing ( 6 images ), is very basic, can do face/object insertion, can transform anime scene into realistic, etc, its very basic so the composition is not a masterpiece like the original remix.
Needs https://github.com/ostris/ComfyUI-MOSS-Image-Ostris-Edit
kv cache: on
☕ Support me on Ko-fi
Any contribution is appreciated and helps me keep working on open-source projects.
https://ko-fi.com/luisacaotica
☁️ Support through RunPod
You can also use my referral link when signing up for RunPod:
https://runpod.io?ref=kpjo0xmj
f you purchase RunPod credits through the referral, you get the computing resources you need, and I receive referral support as well. It's a win-win! It would also help me get access to more GPU resources so I can experiment with and train LoRAs alongside my other projects.
Description
FAQ
Comments (7)
Nice
<3 thank you
A good attempt and it looks promising. How is its ability to maintain consistency?
so i trained with synthetic data, asked to nano banana to "reverse the image into mixed-media/collage ".
also is just 50 steps of training, so everything is kinda cheap.
workflow?
you can use the same one on the ai toolkit git, i only added a 8 step lora.
Great start. Keep going!