license: creativeml-openrail-m
language:
- en
pipeline_tag: text-to-image
MyneFactory Base Model
The foundation of our modelsModel Info
Downloads: MyneFactoryBase V1.0.ckpt
Technical Details
Model Training
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 Training
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.
Block Merge
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: 金Goldkoron, tsmkirby, Juusoz
Prompt Format
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.
Recommended Settings
This model performs best with the following settings:
-
Image Size1024x576 for wide 16:9, 768x768 for square, and 640x1024 for portraitFeel free to experiment with higher resolutions, Juusoz made all the examples at higher than recommended resolutions
-
Vae
-
SamplerDPM++ SDE Karras (preferred)2S KarrasKarras samplers tend to create more dynamic and interesting generationsEuler AResults tends to look smoother and more Airbrushed
-
Steps30 minimum and +70 can give nice results
-
Skip Clip:Clip 1Clip 2 and 4 are valid for experimentation and we recommend trying it for more variation.
-
CFG9-12
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
Examples
1girl, hands, eyes, eyelashes, ponytail, braids, flower hairstick, embroidery, red hair, glasses, solo, plants, sunlight, masterpiece, detailed, depth of field, reflective, caustics, realistic
low quality, worst quality, (bad hands), bad anatomy, watermark, signature, nude, nipples
50
DPM++ SDE Karras
10
2766314147
896x1152
MyneFactoryBase V1.0
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
android woman, masterpiece, caustics, depth of field, neon lights, eyes, steam, city, night
low quality, worst quality, bad hands, bad anatomy, watermark, signature
70
Euler a
10.5
3406131780
1088x960
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
woman, decorated horns, long robes, fog, long curly hair, freckles, solo, masterpiece, reflective, depth of field, caustics, night, forest, leaves, moonlight, eyes, orange hair, green eyes, vines
low quality, worst quality, bad hands, bad anatomy, watermark, signature, kimono
70
Euler a
10.5
1846839782
1088x960
MyneFactoryBase-ep90
woman, business suit, leather vest, pants, glasses, tattoos, hair highlights, office, masterpiece, reflective, caustics, solo, coffee cup, curly hair, lamps, depth of field, pictures, folders, sunlight, window, city
low quality, worst quality, bad hands, bad anatomy, watermark, signature
70
Euler a
10.5
2300296201
1024x1024
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
1girl, wings, feathers, long hair, bloody, angel wings, dress, embroidery, angel, death, feathered wings, braid, sunset, masterpiece, detailed, caustics, depth of field, reflective
low quality, worst quality, bad hands, bad anatomy, watermark, signature
50
DPM++ SDE Karras
8
3530094527
704x1280
MyneFactoryBase-ep90