---
license: other
license_name: bespoke-lora-trained-license
license_link: https://multimodal.art/civitai-licenses?allowNoCredit=True&allowCommercialUse=RentCivit&allowDerivatives=False&allowDifferentLicense=False
tags:
- text-to-image
- stable-diffusion
- lora
- diffusers
- template:sd-lora
- migrated
- realism
- style
- epic
- diamond
- crystal
- glamor

base_model: black-forest-labs/FLUX.1-dev
instance_prompt: crystalz
widget:
- text: 'greek 30yrs old woman full body shot, blue crystalz eyes, wearing a overgrown glowing crystalz dress, in a mythical forest, masterpiece, perfect face, intricate details, horror theme '
  
  output:
    url: >-
      25946713.jpeg
- text: 'cat, crystalz '
  
  output:
    url: >-
      25946701.jpeg
- text: 'food photography photo of a crystal fish , maximum detail, foreground focus, crystalz '
  
  output:
    url: >-
      25946702.jpeg
- text: 'crystal superhero, sprad wings, american flag background, god rays from above, full body shot, crystalz '
  
  output:
    url: >-
      25946700.jpeg
- text: 'A cute colorful crystalz cthulhu, wildlife photography, in a ral-decoznow swamp, 4K UHD, 8K UHD, High-definition, capturing highest detailed, 4k, uhd, hdr '
  
  output:
    url: >-
      25946699.jpeg
- text: 'rick from rick and morty made out of crystalz '
  
  output:
    url: >-
      25946708.jpeg
- text: 'apple, infinity mirror, infinity reflection, ziprealism, crystalz '
  
  output:
    url: >-
      25946710.jpeg
- text: 'glittering night, ice sculpture, vivid, cuteness overload, sci-fi ice horror styled . anatomical, unmaterial, bones, forest background, contoured, surrealism, close up photography by Shaddy of a close up cute transparent ghostly vivid happy dreamy owl ice monster sitting on a tree branch inside fully transparent body, detailed transparent feathers, bioluminescence, leaves, ethereal, ice, looking in camera, sky, sleek, modern., fairytale, fantasy, by Andy Kehoe, soft sepia, artistic water drops, dynamic pose, tender, soft pastel colors, octane render, soft natural volumetric light, atmospheric, sharp focus, centered composition, professional photography, complex background, soft haze, masterpiece. animalistic, beautiful, tiny detailed, crystalz '
  
  output:
    url: >-
      25946711.jpeg
- text: '(Very Intricate), (UHD), (Unreal Details), (Exquisite intricacies), sharp focus, skull, cave, crystalz '
  
  output:
    url: >-
      25946712.jpeg
- text: 'style by Gustav Klimt, intricate background, smouldering coals, (crystalz, crystals of future worlds:1.2), (stardust piercing time, space and gravity, music of eternity:1.1) , space shipyards, stunning detail, dynamic atmosphere, (portrait lost wanderer1.3),, crystalz '
  
  output:
    url: >-
      25946714.jpeg
- text: 'a crystalz palace '
  
  output:
    url: >-
      26240329.jpeg
- text: 'a crystalz fantasy forest, mythical forest, purple orange and black '
  
  output:
    url: >-
      26240342.jpeg

---

# Crystals [FLUX+SDXL+PONY+1.5] 

<Gallery />





## Model description

<p><span style="color:rgb(193, 194, 197)">Trigger word (PONY): </span><strong><span style="color:rgb(193, 194, 197)">ral-</span>crystalz</strong></p><p><span style="color:rgb(193, 194, 197)">Trigger word (FLUX+SDXL+1.5): </span><strong>crystalz</strong><br /><br /><span style="color:rgb(193, 194, 197)">☕ Buy me a coffee: </span><a target="_blank" rel="ugc" href="https://ko-fi.com/ralfingerai">https://ko-fi.com/ralfingerai</a><br /><span style="color:rgb(193, 194, 197)">🍺 Join my discord: </span><a target="_blank" rel="ugc" href="https://discord.gg/g5Pb8qNUuP">https://discord.gg/g5Pb8qNUuP</a></p>

## Trigger words
You should use `crystalz` to trigger the image generation.
    

## Download model

Weights for this model are available in Safetensors format.

[Download](/Keltezaa/crystals-flux-sdxl-pony-1-5/tree/main) them in the Files & versions tab.

## Use it with the [🧨 diffusers library](https://github.com/huggingface/diffusers)

```py
from diffusers import AutoPipelineForText2Image
import torch

device = "cuda" if torch.cuda.is_available() else "cpu"

pipeline = AutoPipelineForText2Image.from_pretrained('black-forest-labs/FLUX.1-dev', torch_dtype=torch.bfloat16).to(device)
pipeline.load_lora_weights('Keltezaa/crystals-flux-sdxl-pony-1-5', weight_name='ral-crystalz_flux.safetensors')
image = pipeline('a crystalz fantasy forest, mythical forest, purple orange and black ').images[0]
```

For more details, including weighting, merging and fusing LoRAs, check the [documentation on loading LoRAs in diffusers](https://huggingface.co/docs/diffusers/main/en/using-diffusers/loading_adapters)