---
license: other
license_name: faipl-1.0-sd
license_link: https://freedevproject.org/faipl-1.0-sd/
language:
- en
tags:
- text-to-image
- stable-diffusion
- safetensors
- stable-diffusion-xl
---
# models
- [Zipang XL test03.1](#test031) (recommended: good lighting)
- [Ponypang_XL_giveup](#potest2) (bad quality)
---
Zipang XL test3.1
-4000+ twitter images trained & 10000+ images merged model
Animagine XL 3.1 Base
photoreal like tag: shadow, flash lighting, backlighting, silhouette, sunset, night, day, bokeh, etc.
[Download:test3.1](https://huggingface.co/deadman44/SDXL_Photoreal_Merged_Models/resolve/main/zipang_XL_test3.1.fp16.safetensors?download=true)
-refer to pnginfo
---
# - base model
-Animagine XL 3.1
-great XL model!
## - trigger
```bash
japanese
european
yo tag and myjs, myjc, myjk (e.g.:18yo, myjk)
```
## - quality tags
```bash
masterpiece, best quality, very aesthetic, absurdres,
```
## - negative tags
```bash
lowres, (bad), error, fewer, extra, missing, worst quality, low quality, extra digits
```
## - sampler
```bash
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
```bash
3-5
(Lightning):1-3
(Hyper-SD XL):1
```
## - Resolution
```bash
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](https://huggingface.co/ByteDance/SDXL-Lightning) (too fast: recommended)
[](https://img95.pixhost.to/images/1092/472679384_20240528182902_zipang_xl_test3-1-fp16_2770074115.jpg)
```bash
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
```bash
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 (bad quality)
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
-not good. (bad quality, worst quality:2.0)
-I don't know how this happened.
-ADetailer and HiresFix Recommendation.
[Download: fix2](https://huggingface.co/deadman44/SDXL_Photoreal_Merged_Models/resolve/main/ponypang_XL_giveup_fix2.fp16.safetensors?download=true)
-refer to pnginfo
---
# - base model
-Pony Diffusion V6 XL
-great XL model!
-ebara pony 2.1
-great XL model! too
## - trigger
```bash
japanese
european
```
## - quality tags
```bash
score_9, score_8_up, score_7_up, masterpiece, best quality,
```
## - negative tags
```bash
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
```
^Tested only with Hyper-SDXL-8steps-lora
## - sampler
```bash
DPM++ SGM Uniform, DPM++ 2s a :8-16 steps
```
## - cfg scale
```bash
1-1.5
```
## - Resolution
```bash
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
[](https://pixhost.to/show/170/475287804_20240606090249_ponypang_xl_giveup_fix2-fp16_650805228.jpg)
```bash
score_9, score_8_up, score_7_up, masterpiece, best quality,
15yo, myjc, japanese, 1girl, solo, realistic, long hair, black hair, plaid skirt, school uniform, smile, looking at viewer, street, road, school bag, collared white shirt, red bowtie, blue skirt
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: 8, Sampler: DPM++ 2M SGMUniform, CFG scale: 1, Seed: 650805228, Size: 896x1152, Model hash: 3a2ec4d842, Model: ponypang_XL_giveup_fix2.fp16, Lora hashes: "Hyper-SDXL-8steps-lora: 4f494295edb1", Version: f0.0.17v1.8.0rc-latest-276-g29be1da7
```
-merge & train
```bash
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)
```
---