README.md

metadata

license: creativeml-openrail-m

Model Info | Troubleshooting | Recommmended Settings | Prompt Format | Examples | Socials

MyneFactory Base Model

The foundation of our models

All example images

Model 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 technical information, please see this document.

Authors: Juusoz, 金Goldkoron, tsmkirby

Prompt Format

It is recommended to use booru styled tags to for the prompts.

Example: 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

Example: 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 Size
  1024x576 for wide 16:9, 768x768 for square, and 640x1024 for portrait
  Feel free to experiment with higher resolutions, Juusoz made all the examples at higher than recommended resolutions
• Vae
  vae-ft-mse-840000-ema-pruned.ckpt
• Sampler
  DPM++ SDE Karras (preferred)

  2S Karras

  Karras samplers tend to create more dynamic and interesting generations
  Euler A

  Results tends to look smoother and more Airbrushed
• Steps
  30 minimum and +70 can give nice results
• Skip Clip:
  Clip 1
  Clip 2 and 4 are valid for experimentation and we recommend trying it for more variation.
• CFG
  9-12

Not required, but these tags improve the quality of the image:

Prompt: best quality, masterpiece
Negative Prompt: 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

Prompt: damaged robot woman in a junkyard, cyberpunk, masterpiece, face

Negative Prompt: low quality, worst quality, bad hands, bad anatomy, watermark, signature

Steps: 60

Sampler: Euler a

CFG Scale: 11

Seed: 620829716

Size: 1024x1024

Model: MyneFactoryBase-ep70

Prompt: girl, eyes, face, steampunk, wings, halo, embroidery, ruins, bridge, mist, sunlight, masterpiece, detailed, depth of field, reflective, caustics

Negative Prompt: low quality, worst quality, bad hands, bad anatomy, watermark, signature, nude

Steps: 50

Sampler: DPM++ SDE Karras

CFG Scale: 8

Seed: 1923352681

Size: 1280x704

Model: MyneFactoryBase-ep90

Prompt: Bearded old man, glasses, sitting at table, vest, solo, masterpiece, clocks, wooden shack

Negative Prompt: low quality, worst quality, bad hands, bad anatomy, watermark, signature, breasts

Steps: 60

Sampler: Euler a

CFG Scale: 10

Seed: 1550904897

Size: 1024x1024

Model: MyneFactoryBase-ep90

Prompt: floating islands, caustics, depth of field, masterpiece, detailed, waterfall, reflective, fog, foggy, sunset, autumn, lens flare, windy, scenery, leaves, town, buildings

Negative Prompt: low quality, worst quality, bad hands, bad anatomy, watermark, signature, sitting

Steps: 70

Sampler: Euler a

CFG Scale: 10.5

Seed: 1057239513

Size: 1216x832

Model: MyneFactoryBase-ep90

Prompt: floating islands, caustics, depth of field, masterpiece, detailed, waterfall, reflective, fog, foggy, scenery, town, buildings, waterfall, moon, night, street, lights, cherry blossoms, stars

Negative Prompt: low quality, worst quality, bad hands, bad anatomy, watermark, signature

Steps: 70

Sampler: Euler a

CFG Scale: 10.5

Seed: 2568996689

Size: 1216x832

Model: MyneFactoryBase-ep90

Prompt: 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

Negative Prompt: low quality, worst quality, bad hands, bad anatomy, watermark, signature

Steps: 70

Sampler: Euler a

CFG Scale: 10.5

Seed: 2494833890

Size: 1216x832

Model: MyneFactoryBase-ep90

Prompt: caustics, depth of field, masterpiece, detailed, waterfall, reflective, fog, foggy, scenery, town, buildings, waterfall, moon, night, street, lights, cherry blossoms, stars, statue

Negative Prompt: low quality, worst quality, bad hands, bad anatomy, watermark, signature

Steps: 70

Sampler: Euler a

CFG Scale: 10.5

Seed: 4020336312

Size: 1216x832

Model: MyneFactoryBase-ep90

Socials

Website | Discord | Patreon