I present my Illustrious character LoRA for Sheriff Woody from Toy Story.
V2 is my second version where I tried to add variation and the ability to properly generate him as a human (without it looking strange). Removing the toys and animate object tags works well enough but adding/removing the big eyes tag seemed to have more influence on his toy version when I tested.
Recommended LoRA strength: 0.7
Also, I use an adetailer in my generations for this LoRA.
V2 main tags are as follows:
toy version
swoody, 1boy, animate object, toy, brown hair, brown eyes, big eyeshuman version
swoody, 1boy, mature, brown hair, short hair, brown eyesV2 outfit tags are as follows:
cowboy hat, red bandana, yellow shirt, cowhide vest, cowboy bet buckle, belt, jeans, cowboy bootsV2 optional tag:
holsterThe settings I used for my generation testing were 3-4 CFG, 20 steps, DPM++ 2M SDE - Karras on Forge with an adetailer (face_yolov8s).
V1 is my initial version and produces decent results. As far as being a toy the model does that style well. I tried to figure out how to prompt for his shirt (the elbows) to not look so weird if aiming to make him look more like a real person but couldn't figure that one out. He at least looks like a real person while shirtless (or possibly in another outfit entirely).
Recommended LoRA strength: 0.7
Also, I use an adetailer in my generations for this LoRA.
V1 main tags are as follows:
s_woody, 1boy, animate object, brown hair, brown eyesoptional - add "animate object" and "toy story" to negative prompt if you want to try making him look more realistic and less like a toy.
V1 outfit tags are as follows:
cowboy hat, red bandana, yellow shirt, long sleeves, vest, sheriff badge, belt, jeans, cowboy bootsV1 optional tag:
holsterThe settings I used for my generation testing were 3-5 CFG, 20 steps, DPM++ 2M SDE - Karras on Forge with an adetailer (face_yolov8s).
Description
V2 is my second version where I tried to add variation and the ability to properly generate him as a human (without it looking strange). Removing the toys and animate object tags works well enough but adding/removing the big eyes tag seemed to have more influence on his toy version when I tested.
Recommended LoRA strength: 0.7
Also, I use an adetailer in my generations for this LoRA.
FAQ
Details
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.