Downloads: MyneFactoryBase V1.0.ckpt
MyneFactoryBase was trained using 23,088 samples from Yande.re. File captions were generated using 3 iterations of WD1.4 tagger to ensure maximum identification of objects within the training data. A second captioning run was done using one tagger with a reduced threshold to produce shorter captions for later use. The model was trained using the NAI model as the base, and the Adam optimizer was used with a manually set maximum learning rate and cosine decay. Training was done on an RTX 4090 with a batch size of 4, utilizing DDIM sample scheduler and DDPM noise scheduler with mix precision.
Text Encoder was trained for 50% of the training durations, freezing and unfreezing every 10ep. During the final 20ep of finetuning, the TE was frozen.
At the ep20 milestone, a block merge was done with BasilMix. However, it was evident that the merged weights were being trained out quickly, and the weights had entirely shifted back to the training data by the end of the training. Ultimately, the decision was made to not use a block merge for the final release.
For more detailed technical information on the training process and model architecture, please refer to this document.
Authors: Juusoz, 金Goldkoron, tsmkirby
It is recommended to use booru styled tags to for the prompts.
woman, decorated horns, long robes, fog, long curly hair, freckles, solo, masterpiece, reflective, depth of field, caustics, detailed night, forest, leaves, moonlight, eyes, orange hair, green eyes, vines
1girl, solo, skirt, book, glasses, long hair, looking at viewer, bookshelf, jacket, plaid skirt, school uniform, long sleeves, parted lips, semi-rimless eyewear, bangs, blush, holding, blazer, indoors, sweater, under-rim eyewear, red-framed eyewear, holding book, brown eyes, library, sitting
The tags were generated with WD14 tagger for the dataset.
The model has also been fine tuned to be better at handling shorter prompts.
This model performs best with the following settings:
Not required, but these tags improve the quality of the image:
best quality, masterpiece
lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry
damaged robot woman in a junkyard, cyberpunk, masterpiece, face
low quality, worst quality, bad hands, bad anatomy, watermark, signature
60
Euler a
11
620829716
1024x1024
MyneFactoryBase-ep70
girl, eyes, face, steampunk, wings, halo, embroidery, ruins, bridge, mist, sunlight, masterpiece, detailed, depth of field, reflective, caustics
low quality, worst quality, bad hands, bad anatomy, watermark, signature, nude
50
DPM++ SDE Karras
8
1923352681
1280x704
MyneFactoryBase-ep90
Bearded old man, glasses, sitting at table, vest, solo, masterpiece, clocks, wooden shack
low quality, worst quality, bad hands, bad anatomy, watermark, signature, breasts
60
Euler a
10
1550904897
1024x1024
MyneFactoryBase-ep90
floating islands, caustics, depth of field, masterpiece, detailed, waterfall, reflective, fog, foggy, sunset, autumn, lens flare, windy, scenery, leaves, town, buildings
low quality, worst quality, bad hands, bad anatomy, watermark, signature, sitting
70
Euler a
10.5
1057239513
1216x832
MyneFactoryBase-ep90
floating islands, caustics, depth of field, masterpiece, detailed, waterfall, reflective, fog, foggy, scenery, town, buildings, waterfall, moon, night, street, lights, cherry blossoms, stars
low quality, worst quality, bad hands, bad anatomy, watermark, signature
70
Euler a
10.5
2568996689
1216x832
MyneFactoryBase-ep90
fantasy, caustics, depth of field, masterpiece, detailed, waterfall, reflective, fog, foggy, scenery, city, buildings, waterfall, moon, night, street, lights, cherry blossoms, stars, neon, cyberpunk, statue, people, airship
low quality, worst quality, bad hands, bad anatomy, watermark, signature
70
Euler a
10.5
2494833890
1216x832
MyneFactoryBase-ep90
caustics, depth of field, masterpiece, detailed, waterfall, reflective, fog, foggy, scenery, town, buildings, waterfall, moon, night, street, lights, cherry blossoms, stars, statue
low quality, worst quality, bad hands, bad anatomy, watermark, signature
70
Euler a
10.5
4020336312
1216x832
MyneFactoryBase-ep90