tried to make a pose lora that can show 2 characters instead of 1<h2 id="v1-triggers-gm7ytlety">v1 triggers</h2>sitting on person, full body, crossed legs = works, the rest not so muchfrom sideprofilestraight-onass focus, from behindsolo focus, from below

Sitting on Person

trained on 21 images, girl on top onlythis is the 2nd ver actually. the first had more tags like "sitting on boy" and "sitting on girl". it was too many tags so retrained without but i removed too many tags. i removed "all fours". i should have kept that.Training Params<pre><code>{
 "engine": "kohya",
 "unetLR": 0.0009,
 "clipSkip": 1,
 "loraType": "lora",
 "keepTokens": 1,
 "networkDim": 8,
 "numRepeats": 10,
 "resolution": 1024,
 "lrScheduler": "cosine_with_restarts",
 "minSnrGamma": 5,
 "noiseOffset": 0.3,
 "targetSteps": 1050,
 "enableBucket": true,
 "networkAlpha": 16,
 "optimizerType": "Adafactor",
 "textEncoderLR": 0.00001,
 "maxTrainEpochs": 20,
 "shuffleCaption": true,
 "trainBatchSize": 4,
 "flipAugmentation": true,
 "lrSchedulerNumCycles": 3
}</code></pre>

Files with SHA256: 961b33b61912d149fb5aef8e1a9f63dadaca50d7ae55d1551a444e5ca3911710