



















Signal Flare.. One of the things that lack on the actual SD 1.5 base model or any other trained models.
There are also very few photos on the internet with this fancy colorful fire stick.
As the resources are very few and low in quality, with 40 trained images in total (half of them for the smoke flare) the LORA doesn't always give you the perfect result. But still it's possible to get good results as you will see in my example images.
For the next version, i will additionally use my images to make the LORA more stable.
Use SignalFlare as the main trigger. For the smoke instead of fire, use "color smokeflare" (for example: green smokeflare)
Also you can check the prompt data of examples, to see how i use the trigger words.
Hope you like it!
And please share your thoughts and images if you come up with any good results.
1. Modèle partagé uniquement à l'apprentissage et au partage. Droits d'auteur et interprétation finale réservés à l'auteur original.
2. Auteur souhaitant revendiquer le modèle : Contactez officiellement SeaArt AI pour l'authentification. Nous protégeons les droits de chaque auteur. Cliquer pour revendiquer
