---
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
  - stable-diffusion-xl
---
<style>
  .title{
    font-size: 2.5em;
    letter-spacing: 0.01em;
    padding: 0.5em 0;
  }
	.thumbwidth{
	max-width: 180px;
	}
	.font_red{
		color:red
	}
</style>

<a id="test02"></a> 
<h1 class="title">
<span>myjsm_flux_test02</span>
</h1>
  -It is a test lora of poor quality with only a few images learned.<br/>
 -trained 273 images.<br/>
  <br/>
Found a slightly better training setting.
But still hard to find things that don't show up in flux.
 <br/>
 <br/>
 
[Download:test02](https://huggingface.co/deadman44/Flux_Photoreal_LoRA/resolve/main/myjsm_flux_test02.safetensors?download=true) <br/>
<br/>
The model used for the test is [Flux Fusion DS v0 GGUF Q4_0 (UNET)](https://civitai.com/models/630820?modelVersionId=736086) and [v0 GGUF Q5_K_M](https://civitai.com/models/630820?modelVersionId=765575).
<table>
  <tr>
    <td colspan="3">
      <div>
GGUF Q4_0 + t5xxl_fp8_e4m3fn : 4step
      </div>
	  </td>
	</tr>
<tr>
<td>
<a href="https://img99.pixhost.to/images/126/507626249_20240827094724_fusionds_v0_q4_456078958.jpg" target=”_blank”>
      <div>
<img src="https://t99.pixhost.to/thumbs/126/507626249_20240827094724_fusionds_v0_q4_456078958.jpg" alt="sample1"  class="thumbwidth" >
      </div>
    </td>
<td>
<a href="https://img99.pixhost.to/images/126/507626251_20240827103511_fusionds_v0_q4_482040669.jpg" target=”_blank”>
      <div>
<img src="https://t99.pixhost.to/thumbs/126/507626251_20240827103511_fusionds_v0_q4_482040669.jpg" alt="sample1"  class="thumbwidth" >
      </div>
	  </td>
<td>
<a href="https://img99.pixhost.to/images/126/507626253_20240827112528_fusionds_v0_q4_1816421730.jpg" target=”_blank”>
      <div>
<img src="https://t99.pixhost.to/thumbs/126/507626253_20240827112528_fusionds_v0_q4_1816421730.jpg" alt="sample1"  class="thumbwidth" >
      </div>
	  </td>
  </tr>
  <tr>
    <td colspan="3">
      <div>
GGUF Q5_K_M. + t5-v1_1-xxl-encoder-Q5_K_M : 12step
      </div>
	  </td>
	</tr>
<tr>
<td>
<a href="https://img99.pixhost.to/images/126/507626250_20240827102458_fluxfusionds_v0_q5_k_m_2418428235.jpg" target=”_blank”>
      <div>
<img src="https://t99.pixhost.to/thumbs/126/507626250_20240827102458_fluxfusionds_v0_q5_k_m_2418428235.jpg" alt="sample1"  class="thumbwidth" >
      </div>
    </td>
<td>
<a href="https://img99.pixhost.to/images/126/507626252_20240827110802_fluxfusionds_v0_q5_k_m_3216545735.jpg" target=”_blank”>
      <div>
<img src="https://t99.pixhost.to/thumbs/126/507626252_20240827110802_fluxfusionds_v0_q5_k_m_3216545735.jpg" alt="sample1"  class="thumbwidth" >
      </div>
	  </td>
<td>
<a href="https://img99.pixhost.to/images/126/507626256_20240827121409_fluxfusionds_v0_q5_k_m_2982180625.jpg" target=”_blank”>
      <div>
<img src="https://t99.pixhost.to/thumbs/126/507626256_20240827121409_fluxfusionds_v0_q5_k_m_2982180625.jpg" alt="sample1"  class="thumbwidth" >
      </div>
	  </td>
  </tr>
</table>
-refer to png info
<br />

## - sample prompt
[<img src=https://t99.pixhost.to/thumbs/126/507626257_20240827124249_fusionds_v0_q4_642879771.jpg />](https://img99.pixhost.to/images/126/507626257_20240827124249_fusionds_v0_q4_642879771.jpg)
```bash
9yo, myjsm, japanese,
photograph of a girl sitting on a brick pavement with a pink umbrella in front of her. She is wearing a white camisole and a blue skirt with a anime print. She has shoulder-length dark hair and is smiling at the camera.
bangs, black eyes, skirt, rain
<lora:myjsm_flux_test02:1>
Steps: 4, Sampler: Euler, Schedule type: Simple, CFG scale: 1, Seed: 642879771, Size: 792x1056, Model hash: 5e21feb505, Model: FusionDS_v0_Q4, Lora hashes: "myjsm_flux_test02: 3fdff20b7d65", Version: f2.0.1v1.10.1-previous-419-gf82029c5c, Module 1: ae, Module 2: clip_l, Module 3: t5xxl_fp8_e4m3fn
```
<br />

## - trigger
```bash
myjsm, japanese, 9yo, 
and native english
```
<br />

## -Train Settings
```bash
base model: flux1-dev.safetensors
vae/text encoder: clip_l.safetensors, t5xxl_fp8_e4m3fn.safetensors, ae.safetensors
tag: caption (native eng) + tags (danbooru)

--network_module "networks.lora_flux"
--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 "AdamW8bit"
--optimizer_args "weight_decay=0.01" "betas=0.9,0.999"
--learning_rate=0.0002
--network_dim=32
--network_alpha=4
--network_train_unet_only
--mixed_precision "bf16"
--save_precision "bf16"
--full_bf16
--loss_type "l2"
--huber_schedule "snr"
--model_prediction_type "raw"
--discrete_flow_shift 3
--timestep_sampling "sigma"
--max_grad_norm=1
--max_timestep=1000
--min_snr_gamma=5
--min_timestep=100
--noise_offset=0.0375
--adaptive_noise_scale=0.00375
--apply_t5_attn_mask
--split_mode
--network_args "loraplus_unet_lr_ratio=16" "train_blocks=single"
```
<br />

<a id="test01"></a> 
<h1 class="title">
<span>myjsm_flux_test01</span>
</h1>
  -It is a test lora of poor quality with only a few images learned.<br/>
 -trained 167 images.<br/>
  <br/>
I don't know why the image turns white.
 <br/>
 <br/>
 
[Download:test01](https://huggingface.co/deadman44/Flux_Photoreal_LoRA/resolve/main/myjsm_flux_test01.safetensors?download=true) <br/>
<br/>
The model used for the test is [Flux Fusion DS v0 GGUF Q4_0 (UNET)](https://civitai.com/models/630820?modelVersionId=736086)
<table>
  <tr>
    <td>
      <div>
test01
      </div>
	  </td>
<td>
      <div>
original
      </div>
	  </td>
	</tr>
<tr>
<td>
<a href="https://img99.pixhost.to/images/33/506653593_20240823152822_fusionds_v0_q4_1439912753.jpg" target=”_blank”>
      <div>
<img src="https://t99.pixhost.to/thumbs/33/506653593_20240823152822_fusionds_v0_q4_1439912753.jpg" alt="sample1"  class="thumbwidth" >
      </div>
    </td>
<td>
<a href="https://img99.pixhost.to/images/33/506653594_20240823153500_fusionds_v0_q4_1439912753.jpg" target=”_blank”>
      <div>
<img src="https://t99.pixhost.to/thumbs/33/506653594_20240823153500_fusionds_v0_q4_1439912753.jpg" alt="sample1"  class="thumbwidth" >
      </div>
	  </td>
  </tr>
</table>
<br />

```bash
myjsm, japanese, photograph of a portrait of a young girl sitting on a white couch in girly room. She is wearing a pink and white checkered dress with a pink bow on her head. black hair, twintails, bangs, black eyes, smile, upper body
```
<br />

## - trigger
```bash
myjsm, japanese, 9yo
```
<br />

## -Train Settings
```bash
base model: flux1-dev.safetensors
vae/text encoder: clip_l.safetensors, t5xxl_fp8_e4m3fn.safetensors, ae.safetensors
tag: caption (native eng) + tags (danbooru)

--network_module "networks.lora_flux"
--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 "AdamW8bit"
--optimizer_args "weight_decay=0.01" "betas=0.9,0.999"
--learning_rate=0.0002
--network_dim=32
--network_alpha=16
--network_train_unet_only
--mixed_precision "bf16"
--save_precision "bf16"
--full_bf16
--loss_type "l2"
--huber_schedule "snr"
--model_prediction_type "raw"
--discrete_flow_shift 3
--timestep_sampling "sigma"
--max_grad_norm=1
--max_timestep=1000
--min_snr_gamma=5
--min_timestep=100
--noise_offset=0.0375
--adaptive_noise_scale=0.00375
--apply_t5_attn_mask
--split_mode
--network_args "loraplus_unet_lr_ratio=16" "train_blocks=single"
```
<br />