---
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:
- flux
- diffusers
- lora
- replicate
- cgi
- trippy
- 90s
- 3d
base_model: black-forest-labs/FLUX.1-dev
pipeline_tag: text-to-image
instance_prompt: TRP90S
---

# 90S bad trip
<figure>
<img src="https://cdn-uploads.huggingface.co/production/uploads/6354308eb8aa3b0b3ebcc166/CL_wjVkgZ5c2TiKI4FjpT.png" width="200" />
<img src="https://cdn-uploads.huggingface.co/production/uploads/6354308eb8aa3b0b3ebcc166/Z0Z9ci3LnWBkZOfBo2jDN.png" width="200" />
<img src="https://cdn-uploads.huggingface.co/production/uploads/6354308eb8aa3b0b3ebcc166/q9-dIeEg1ZKEDNBjAY96N.png" width="200" />
<img src="https://cdn-uploads.huggingface.co/production/uploads/6354308eb8aa3b0b3ebcc166/sQugdFsEy6lds01QSwKcF.png" width="200" />
<img src="https://cdn-uploads.huggingface.co/production/uploads/6354308eb8aa3b0b3ebcc166/dOIIAQPueSldSEM7dDHAx.png" width="200" />
<img src="https://cdn-uploads.huggingface.co/production/uploads/6354308eb8aa3b0b3ebcc166/bP3FmxbK4y0EMTY52RjTl.png" width="200" />
<img src="https://cdn-uploads.huggingface.co/production/uploads/6354308eb8aa3b0b3ebcc166/qYnhf64D0tk14eAeulEwx.png" width="200" />
<img src="https://cdn-uploads.huggingface.co/production/uploads/6354308eb8aa3b0b3ebcc166/NA64DFTVVF47S73Cb9EAd.png" width="200" />
</figure>

A LoRA for Flux.1 Dev to re-create really bad and trippy CGI from the 90s.

For best results:
- Set `lora_scale` within ranges 1.2 to 1.4 for full effect


## Trigger words
You should use `TRP90S` to trigger the image generation.
("A photo of TRP90S", or, "in the style of TRP90S")


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

```py
from diffusers import AutoPipelineForText2Image
import torch

pipeline = AutoPipelineForText2Image.from_pretrained('black-forest-labs/FLUX.1-dev', torch_dtype=torch.float16).to('cuda')
pipeline.load_lora_weights('markredito/90sbadtrip', weight_name='lora.safetensors')
image = pipeline('your prompt').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)


Trained on Replicate using:

https://replicate.com/ostris/flux-dev-lora-trainer/train