<h3 id="heading-450">STOPMO - Stop-motion Style for SDXL</h3>Even though I already trained a LoRa that sorta do stop-motion style I decided to train another model from scratch since I wasn't satisfied with the results. This should work better and have a more distinct styleUse stopmotion as first tokentilt-shift adds a nice shallow depth of field effect that reinforces the styleput painting and drawing in the negative prompt to obtain cleaner resultsuse weight 1, lower it if it's too crowdedThe best results requires a low CFG (7) and high steps number (I used 60), I know, this sucksHope you like it, let me knowif you like my LoRas just publish some image made with them to help me gain buzzTraining LoRa necessitate a lot of coffee. If you think that what I do is useful and want to help me keep doing this you can buy me a coffe here: <a target="_blank" rel="ugc" href="https://ko-fi.com/clumsy_trainer">https://ko-fi.com/clumsy_trainer</a>

STOPMO - Stop-motion Style for SDXL

STOPMO_2.0_RC.safetensors

v2.0

v1.0

<h3 id="heading-450">STOPMO - Stop-motion Style for SDXL</h3>Even tho I already trained a LoRa that sorta do stop-motion style I decided to train another model from scratch since I wasn't satisfied with the results. This should work better and have a more distinct styleUse stopmotion as first tokenuse weight 0.9 or even 1I suggest DPM++ 2M SDE Exponential as sampler but it should work with any other sample you preferCFG scale is up to youHope you like it, let me knowif you like my LoRas just publish some image made with them to help me gain buzzTraining LoRa necessitate a lot of coffee. If you think that what I do is useful and want to help me keep doing this you can buy me a coffe here: <a target="_blank" rel="ugc" href="https://ko-fi.com/clumsy_trainer">https://ko-fi.com/clumsy_trainer</a>

Files with SHA256: 036ef209e4b86f618adcb599235211a2656ca3e1796d81c4a110c580e9e65995