---
tags:
- text-to-image
- lora
- diffusers
- template:diffusion-lora
widget:
- text: '-'
  output:
    url: images/Upscaled_00035_.png
- text: '-'
  output:
    url: images/Lora Strength comparision 2 tile.png
- text: '-'
  output:
    url: images/Upscaled_00039_.png
- text: '-'
  output:
    url: images/Upscaled_00038_.png
- text: '-'
  output:
    url: images/8mm Film Lora_01127_.png
- text: '-'
  output:
    url: images/Upscaled_00036_.png
- text: '-'
  output:
    url: images/Upscaled_00034_.png
- text: '-'
  output:
    url: images/Synthwave Lora Strength comparision.png
base_model: black-forest-labs/FLUX.1-dev
instance_prompt: vidsynthsynth, video synth
license: apache-2.0
---
# Synthwave

<Gallery />

## Model description 

Analog video synthesis, synthesized by machine learning.
This Lora was trained on 50 highly stylized images.

Workflow:
https:&#x2F;&#x2F;drive.google.com&#x2F;file&#x2F;d&#x2F;1x2IHDaA-2GydtAAnGoVxZEPx8oeLHbOJ&#x2F;view?usp&#x3D;sharing

Settings:
Lora Strength: 2.5 is the sweet spot. 0.8 is the lowest that the Lora will show effects, 3.0 is the highest before it&#39;s effects generate diminishing returns.

Flux Guidance: 2.5

Scheduler and Sampler Combinations

-Euler &amp; Simple: standard

-Huen &amp; Normal: standard

-Huen &amp; Beta: standard

-dpm_fast &amp; ddim_uniform: more abstraction, color compression that resembles vintage TV texture

Max Shift: 0-1

Base Shift: 0-1

This Lora Pairs nicely with my 8mm Film Lora at a strength of 1.8 and other Loras trained on analog and glitch data.

Please share your results, feedback, and questions.

Happy Synthing!

## Trigger words

You should use `vidsynthsynth` to trigger the image generation.

You should use `video synth` to trigger the image generation.


## Download model

Weights for this model are available in Safetensors format.

[Download](/CalvinHerbst/Synthwave/tree/main) them in the Files & versions tab.