models

Ponypang_XL_giveup (Pony Base): fix5:2024-07-03
Zipang XL test03.1 (Animagine Base): 3.1b:2024-07-22

Zipang XL test3.1

-4000+ twitter images trained & 10000+ images merged model

-Animagine XL 3.1 Base
-Good Lighting
-photoreal like tag: shadow, flash lighting, backlighting, silhouette, sunset, night, day, bokeh, etc.

Download:test3.1 (Recommended)
Download:test3.1b (Newer isn't always better)

These images are test3.1.

-refer to pnginfo

- base model

-Animagine XL 3.1 -great XL model!

- trigger

japanese
european
yo tag and myjs, myjc, myjk (e.g.:18yo, myjk)

- quality tags

masterpiece, best quality, very aesthetic, absurdres,

- negative tags

lowres, (bad), error, fewer, extra, missing, worst quality, low quality, extra digits

- sampler

DPM++ 2M SDE Heun Karras :24-28 steps
(Lightning)DPM++ 2M SGMUniform :8-14 steps
(Hyper-SD XL 8steps)DPM++ 2s a,DPM++ 2M SGM Uniform ;8-16 steps (Bad)

- cfg scale

3-5
(Lightning):1-3
(Hyper-SD XL):1

- Resolution

768 x1024, 1024 x 768
1024 x 1024
896 x 1152, 1152 x 896
512 x 768, 768 x 512 (hires.fix required)

Sample prompt

-SDXL Lightning (too fast: recommended)

masterpiece, best quality, very aesthetic, absurdres,
16yo, japanese, myjk, 1girl, solo, backlighting, silhouette, horizon, sunset, wind, water, outdoors, wading, scenery, white dress, photo background, skirt hold, realistic, long hair, standing, barefoot, from behind, facing away, close-up
Negative prompt: lowres, (bad), error, fewer, extra, missing, worst quality, low quality, extra digits

Steps: 24, Sampler: DPM++ 2M SDE Heun Karras, CFG scale: 3, Seed: 2770074115, Size: 896x1152, Model hash: 90bbe169ac, Model: zipang_XL_test3.1.fp16, Denoising strength: 0.3, Hires upscale: 2, Hires upscaler: 4x-UltraSharp, Version: f0.0.17v1.8.0rc-latest-276-g29be1da7

-train

base1:trained 4000+images:manual tagging (Prodigy:70epoch)
model:trained 10000+images:wd14 tagger(swinv2 tagger v3) (base model:base1)(Nadam:lr:1e-04:27epoch)

Ponypang XL giveup

This is an incomplete model.

Mixed LoRA due to problems with training not being able to continue.
e621 tag might be better than danbooru tag.

-4000+ twitter images trained & 10000+ images merged model

-experimental
-Might look like Zipang.
-Hand is not good.
-ADetailer and HiresFix Recommendation.

Download: fix5
Download: fix4

These images are fix4.

-refer to pnginfo

- base model

-Pony Diffusion V6 XL -great XL model!
-ebara pony 2.1 -great XL model! too

- trigger

japanese
european
yo tag and myjs, myjc, myjk (e.g.:18yo, myjk)

- quality tags

score_9, score_8_up, score_7_up, masterpiece, best quality, realistic, photorealistic,

- negative tags

worst quality, low quality, normal quality, messy drawing, amateur drawing, lowres, bad anatomy, bad hands, source furry, source pony, source cartoon, comic, source filmmaker, 3d, \(bad\), error, fewer, missing, extra digits

- sampler

DPM++ 2M SDE Heun Karras :24-28 steps
DPM++ SGM Uniform, DPM++ 2s a :8-16 steps (HyperSDXL)

Hyper-SDXL-8steps-lora

- cfg scale

3-7
1-1.5 (HyperSDXL)

- Resolution

768 x1024, 1024 x 768
1024 x 1024
896 x 1152, 1152 x 896
512 x 768, 768 x 512 (hires.fix required)

sample prompt

score_9, score_8_up, score_7_up, masterpiece, best quality,
18yo, myjk, japanese, realistic, photorealistic,
1girl, solo, black hair, long hair, bangs, brown eyes, animal ears,school uniform,
stuffed toy, stuffed animal, teddy bear,
looking at viewer, grin, holding stuffed toy, upper body, sitting, hairband
Negative prompt: worst quality, low quality, normal quality, messy drawing, amateur drawing, lowres, bad anatomy, bad hands, source furry, source pony, source cartoon, comic, source filmmaker, 3d, \(bad\), error, fewer, missing, extra digits
Steps: 28, Sampler: DPM++ 2M SDE Heun Karras, CFG scale: 4, Seed: 2317472872, Size: 896x1152, Model hash: 58cd1b19e0, Model: ponypang_XL_giveup_fix4.fp16, Version: f0.0.17v1.8.0rc-latest-287-g77bdb9208

-merge & train

base1:ebara pony 2.1 base Trained.
base2:base1 x ebara base LoRA (1,1,1,1,0.3,0.3,0.3,0.3,0.5,0.75,0,0,0,0.75,1,0.9,0.5,0.3,0.3,0.3,1,1,0,0,0,0)
base3:Merge Zipang test3.1 (0,0,0,0,0,0,0,0,0,0.5,0,0.3,0,0.1,0,0,0,0,0,0)
base4:base3 x pony base LoRA (0,0,0,0,0,0.1,0.25,0,0,0.7,0,0,0,0.5,0.25,1,0,0.1,0.75,0.65,0,0,0,0,0,0)
fix: base4 base trained (Lion 1e-07)