---
license: other
license_name: flux-1-dev-non-commercial-license
license_link: https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md
language:
- en
tags:
  - text-to-image
  - stable-diffusion
  - safetensors
  - flux
---
<style>
  .title{
    font-size: 2.5em;
    letter-spacing: 0.01em;
    padding: 0.5em 0;
  }
	.thumbwidth{
	max-width: 180px;
	}
	.font_red{
		color:red
	}
</style>

## Recent Updates
24/12/9 Add [zipang_flux_test02 (not good)](#test02)<br>
24/11/25 Add [zipang_flux_test01](#test01)<br>
<br>

---
<a id="test01"></a> 
<h1 class="title">
<span>zipang flux test01</span>
</h1>
 -Finetune test model.<br/>
 -Various age-group outputs<br/>
 -flux_dev1 base<br/>
 <br/>
 
[Download: zipang_flux_test01](https://huggingface.co/deadman44/Flux_Photoreal_Models/resolve/main/zipang_flux_test01-Q5_K_M.gguf?download=true) (checkpoint)<br/>
<table>
<tr>
<td>
<a href="https://img100.pixhost.to/images/373/536960537_20241125200925_zipang_flux_test01-q5_k_m_2527114569.jpg" target=”_blank”>
      <div>
<img src="https://t100.pixhost.to/thumbs/373/536960537_20241125200925_zipang_flux_test01-q5_k_m_2527114569.jpg" alt="sample1"  class="thumbwidth" >
      </div>
    </td>
<td>
<a href="https://img100.pixhost.to/images/373/536960541_20241125201614_zipang_flux_test01-q5_k_m_3576329090.jpg" target=”_blank”>
      <div>
<img src="https://t100.pixhost.to/thumbs/373/536960541_20241125201614_zipang_flux_test01-q5_k_m_3576329090.jpg" alt="sample1"  class="thumbwidth" >
      </div>
	  </td>
<td>
<a href="https://img100.pixhost.to/images/373/536960545_20241125203241_zipang_flux_test01-q5_k_m_2776563753.jpg" target=”_blank”>
      <div>
<img src="https://t100.pixhost.to/thumbs/373/536960545_20241125203241_zipang_flux_test01-q5_k_m_2776563753.jpg" alt="sample1"  class="thumbwidth" >
      </div>
	  </td>
  </tr>

</table>
-refer to png info
<br />

<br/>

### -VAE / Text Encoder:
ae, clip_l, t5xxl_fp16<br/>
### -Sampling method<br/>
[Forge] Flux Realistic, Euler (Simple)<br/>
### -Sampling steps<br/>
12-30<br/>
### -CFG Scale<br/>
1<br/>
<br/>

## - sample prompt

[<img src=https://t100.pixhost.to/thumbs/373/536960562_20241125204147_zipang_flux_test01-q5_k_m_1888130365.jpg />](https://img100.pixhost.to/images/373/536960562_20241125204147_zipang_flux_test01-q5_k_m_1888130365.jpg)
```bash
17yo, myjk, grin, teeth,
Photograph of a Japanese girl with long dark hair in twintails, wearing a grey school uniform with a white shirt and a red plaid bow tie.
She is sitting at a desk in a classroom with a neutral expression, looking at the camera.
She is holding a pen.
The background shows a typical Japanese classroom with white walls.
The lighting is natural, likely coming from a window on the left side of the frame.
The camera angle is eye-level, capturing her from the front.
The photo has a casual, everyday feel.
Steps: 12, Sampler: Euler, Schedule type: Simple, CFG scale: 1, Distilled CFG Scale: 3.5, Seed: 1888130365, Size: 512x768, Model hash: db4f24fbb9, Model: zipang_flux_test01-Q5_K_M, Version: f2.0.1v1.10.1-previous-535-gb20cb4bf0, Diffusion in Low Bits: Automatic (fp16 LoRA), Module 1: clip_l, Module 2: t5xxl_fp16, Module 3: ae
```
<br />

## - trigger
```bash
japanese, european, 
myjy, myjsl, myjsm, myjsh, myjc, myjk, myjd, 
and 3-30yo, 
and native english(recomended) or danbooru tags
```
<br/>
<br/>

---
<a id="test02"></a> 
<h1 class="title">
<span>zipang flux test02</span>
</h1>

 -license: [apache-2.0](https://choosealicense.com/licenses/apache-2.0/)<br/>
 -Base Model: [Libre Flux](https://huggingface.co/jimmycarter/LibreFLUX)<br/>
 <span class="font_red">-not good...</span><br/>
 <br/>
 
[Download: zipang_flux_test02](https://huggingface.co/deadman44/Flux_Photoreal_Models/resolve/main/zipang_flux_test02-Q5_K_M.gguf?download=true) (checkpoint)<br/>

### -VAE / Text Encoder:
ae, clip_l, t5xxl_fp16<br/>
### -Sampling method<br/>
[Forge] Flux Realistic, Euler (Simple)<br/>
### -Sampling steps<br/>
<span class="font_red">16</span>-30<br/>
### -CFG Scale<br/>
<span class="font_red">3</span><br/>
<br/>

## - sample prompt

[<img src=https://t100.pixhost.to/thumbs/708/540565397_20241209194825_zipang_flux_test02-q5_k_m_2680159760.jpg />](https://img100.pixhost.to/images/708/540565397_20241209194825_zipang_flux_test02-q5_k_m_2680159760.jpg)
```bash
20yo, myjd,
A photo of a Japanese girl standing on a street at night.
She has long black hair with bangs, and is wearing a light pink dress with lace details on the sleeves and has large-sized breasts.
She is looking directly at the camera with a sad expression, and her hands are behind her head.
The background is dark with some indistinct lights, likely from streetlights or a building, and neon light written "not good".
The lighting is artificial, with the photo taken at night.
The camera angle is straight-on, capturing her from the waist up.
The image is sharp with a shallow depth of field, focusing on the girl.
The photo has a high quality, professional feel.
Steps: 16, Sampler: [Forge] Flux Realistic, Schedule type: Simple, CFG scale: 3, Seed: 2680159760, Size: 512x768, Model hash: fab005c9da, Model: zipang_flux_test02-Q5_K_M, Version: f2.0.1v1.10.1-previous-535-gb20cb4bf0, Diffusion in Low Bits: Automatic (fp16 LoRA), Module 1: clip_l, Module 2: ae, Module 3: t5xxl_bf16
```
<br />

## - trigger
```bash
japanese, european, 
myjy, myjsl, myjsm, myjsh, myjc, myjk, myjd, 
and 3-30yo, 
and native english(recomended) or danbooru tags
```
<br/>
<br />

---

## -Train Settings
- [sd-scripts (SD3 branch)](https://github.com/kohya-ss/sd-scripts/tree/sd3)<br>
```bash
base model: flux1-dev.safetensors, LibreFLUX.safetensors
vae/text encoder: clip_l.safetensors, t5xxl_fp16.safetensors, ae.safetensors

caption: JoyCaption Alpha Two
tags: WD EVA02-Large Tagger v3

--network_module "flux_train.py"
--gradient_checkpointing
--cache_latents
--cache_latents_to_disk
--cache_text_encoder_outputs
--cache_text_encoder_outputs_to_disk
--enable_bucket
--bucket_no_upscale
--optimizer_type "adafactor"
--optimizer_args "relative_step=False" "scale_parameter=False" "warmup_init=False"
--learning_rate=5e-7
--train_batch_size 7
--mixed_precision "bf16"
--save_precision "bf16"
--full_bf16
--loss_type "l2"
--huber_schedule "snr"
--timestep_sampling "flux_shift"
--model_prediction_type "raw"
--discrete_flow_shift 3.1582
--max_grad_norm=0
--min_snr_gamma=5
--apply_t5_attn_mask
--fused_backward_pass ^
--blocks_to_swap 35 ^
--skip_cache_check ^
--sdpa
```
<br />