trained on juggernaut XL, noise offset is 0.018<h3 id="heading-568">I recommend using the word Phoenix.</h3>You should be able to change the color of the bird. I prefer a multicolored bird except for ethereal. In my mind this is a normal awesome creature that is capable of engulfing itself in flames. I tried to train some flaming birds with ashy talons and some with regular talons. Great effort was put on generating quality talons with 3, 4, or 5 claws.V3: Introducing Immolation support! Now, the phoenix boasts a mesmerizing look with parts seemingly crafted from liquid fire. I've fine-tuned the model to eliminate quirks, ensuring the fire no longer looks feathery, and the bird doesn't appear to hold feathers. It's performing exceptionally well with hybrid creatures even with simple prompts. I welcome your feedback on this latest version! Your thoughts and constructive criticism are invaluable to further refine and enhance the model. Thanks for the ongoing support and collaboration!V2 notes: USE ethereal for less bird like more spiritual phoenixusing flaming to increase fire.use fireless to reduce the amount of fire.you can also put 1 or 2 of those 3 words in the negative prompt.I can not promise you fireless will always generate a flame free bird of prey nor can I promise flaming will always have fire but it is better then juggernaut XL defaultFile names is fixed, training reached my intended duration. I've observed an interesting quirk: sometimes the phoenix appears perched on feathers, possibly due to my stupid reluctance to exclude a few long-tailed phoenix that I really liked from the training data. Resolving this, as well as an issue where the fire itself occasionally takes on a feathery texture, proves to be a challenging task. I believe this happens because the model is trained on the feathers and the area around the bird as being on fire. Given the magical nature of the bird, the feathers also glow, leading the model to interpret them as a change to fire. I'm actively working on V3, aiming for a release before Christmas, depending on my progress. Currently, I'm employing LoRA at low strength to generate high-quality images of objects on fire, using them to fine-tune and regularize the model.V1 notes: two training issues. Planned 24 epochs, but a file overwrite with save state enabled caused space shortage, ending training prematurely. Additionally, file renaming occurred due to a side project on NYC trains, affecting only the file name in the code, with no impact on your end unless you deep dive into the file you won't see the train names and stuff none of that is in this lora just the previous file name is hidden inside the code. I DO NOT RECOMMEND DOWNLOADING V1. IT IS NOT BETTER THEN v2 or v3 in anyway.

Phoenix

New: immolation = deep ember burning almost like liquid built into the bird. usually in the upper section of the wings. It really feels like the bird is made of sheol created by Emberus, the god of sun and ash.I did not like this at full strength as much as I preferred it around 0.68 for hybrids and others you may wish to go lower than that.This version has much less control built into it then the last version because I blended all of the best elements. Flameless is much less effective and several times it produced a toy like Phoenix which baffled me and may have been prompt/seed related obviously if that happens put Toy in negative prompts. Ethereal and Etheral both used in the training this was an error caused by a search and replace script I ran I caught it during testing you can prompt with one the other or both either way they aren't going to be as transdimentional as in V2 usually it just makes them glow more. I am please to announce that this one produced even better hybrid creatures then the last which was never my intention when I made this LoRA I got the idea during testing and it has been testing very well.0.0652 = from the final loss of 10 Epochs trained from the original 14 Epoch of the V1 LoRA.This model was actually trained on Juggernaut XL v7 + RunDiffusion where as an earlier version was trained on Juggernaut V1.

Files with SHA256: dab53c9c29260ebc8139ba28cd12b54d129281f4ee246b88f218b21184d79d77