❌💲 Commercial use of this model is not allowed

I like this bird species, but AI simply can't generate it, the closest you can get is an ambiguous corvid. So I made this LoRA to see if I can make it work.

🏷 DATASET TAGS (doesn't apply to Flux and ZIT, those use natural captions)

Tagging is a mix of autotagging and manual.

The whole dataset is tagged with "jackdaw, western jackdaw, eurasian jackdaw, coloeus monedula, corvus monedula, corvid, bird, feral, animal, animal focus, realistic, no humans".

Some pictures focus on the bird's head, most of the others use "fullbody".

Most images in the dataset show solo birds (tagged "solo, 1 jackdaw, 1 bird"), a few images show two ("duo, 2 jackdaws, 2 birds").

🖼 DATASET

122 images which are photos only (doesn't apply to the Flux version). I don't own anything.

Images don't contain signatures/watermarks.

Resolution is all over the place, flying pictures are lower quality overall, though some images were large enough to be automatically sized down.

Images don't show any humans or other distinct creatures.

Only adult birds with normal colouration. No eggs, hatchlings or fledglings, no colouration anomalies.

⚠ ISSUES

The bird's colouration most likely will be lost in cartoony results.

BONUS: I tried SD3.5L, but it doesn't work and I don't know why.

I deleted the LoRA for SD3.5L since it couldn't produce the jackdaw. You don't need a LoRA for generic corvids. I thought I could make a proper LoRA if I used all the 122 images and maybe increased the number of Epochs. But seeing the sample images, I knew that nothing helped... I'm not putting these useless LoRAs on here, but if you can use SD3.5L locally, you can see for yourself. I took time to correct the captions on 14 pages of images so there wouldn't be any incorrect bird names, so it wouldn't be called "large" or its eyes "yellow", and it was all pointless... How come Flux works with about 30 images, but SD3.5 doesn't with 100+? And I wondered why SD3.5 LoRAs were so scarce. Ain't gonna bother with it again anytime soon.

Description

Before making the decision to make this LoRA I did one test generation to confirm that Flux can't make a jackdaw either.

I took the dataset previously used for all the SD models, and by process of elimination discarded most of it, trying to prioritise resolution and quality, until I had 30 images. I ended up with a dataset where only solo birds were shown and, unfortunately, only 3 pictures showed flight and only 2 showed open beak.

I got rid of the Booru style tags and for the first time entrusted AI to make natural language captions. Just as I predicted, AI doesn't know what a jackdaw is, calling it by names of other birds (usually crow or raven) so I had to fix the captions to name the bird correctly, along a few other mistakes. For this model I stuck with just one name - "jackdaw". A couple of image descriptions mention the crow family.