Update README.md
Browse files
README.md
CHANGED
|
@@ -9,20 +9,36 @@ tags:
|
|
| 9 |
- diffusers
|
| 10 |
- lora
|
| 11 |
- replicate
|
| 12 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
| 13 |
pipeline_tag: text-to-image
|
| 14 |
instance_prompt: TRP90S
|
| 15 |
---
|
| 16 |
|
| 17 |
-
#
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 18 |
|
| 19 |
-
|
| 20 |
|
| 21 |
-
|
|
|
|
| 22 |
|
| 23 |
|
| 24 |
## Trigger words
|
| 25 |
You should use `TRP90S` to trigger the image generation.
|
|
|
|
| 26 |
|
| 27 |
|
| 28 |
## Use it with the [🧨 diffusers library](https://github.com/huggingface/diffusers)
|
|
@@ -37,3 +53,8 @@ image = pipeline('your prompt').images[0]
|
|
| 37 |
```
|
| 38 |
|
| 39 |
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)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 9 |
- diffusers
|
| 10 |
- lora
|
| 11 |
- replicate
|
| 12 |
+
- cgi
|
| 13 |
+
- trippy
|
| 14 |
+
- 90s
|
| 15 |
+
- 3d
|
| 16 |
+
base_model: black-forest-labs/FLUX.1-dev
|
| 17 |
pipeline_tag: text-to-image
|
| 18 |
instance_prompt: TRP90S
|
| 19 |
---
|
| 20 |
|
| 21 |
+
# 90S bad trip
|
| 22 |
+
<figure>
|
| 23 |
+
<img src="https://cdn-uploads.huggingface.co/production/uploads/6354308eb8aa3b0b3ebcc166/CL_wjVkgZ5c2TiKI4FjpT.png" width="200" />
|
| 24 |
+
<img src="https://cdn-uploads.huggingface.co/production/uploads/6354308eb8aa3b0b3ebcc166/Z0Z9ci3LnWBkZOfBo2jDN.png" width="200" />
|
| 25 |
+
<img src="https://cdn-uploads.huggingface.co/production/uploads/6354308eb8aa3b0b3ebcc166/q9-dIeEg1ZKEDNBjAY96N.png" width="200" />
|
| 26 |
+
<img src="https://cdn-uploads.huggingface.co/production/uploads/6354308eb8aa3b0b3ebcc166/sQugdFsEy6lds01QSwKcF.png" width="200" />
|
| 27 |
+
<img src="https://cdn-uploads.huggingface.co/production/uploads/6354308eb8aa3b0b3ebcc166/dOIIAQPueSldSEM7dDHAx.png" width="200" />
|
| 28 |
+
<img src="https://cdn-uploads.huggingface.co/production/uploads/6354308eb8aa3b0b3ebcc166/bP3FmxbK4y0EMTY52RjTl.png" width="200" />
|
| 29 |
+
<img src="https://cdn-uploads.huggingface.co/production/uploads/6354308eb8aa3b0b3ebcc166/qYnhf64D0tk14eAeulEwx.png" width="200" />
|
| 30 |
+
<img src="https://cdn-uploads.huggingface.co/production/uploads/6354308eb8aa3b0b3ebcc166/NA64DFTVVF47S73Cb9EAd.png" width="200" />
|
| 31 |
+
</figure>
|
| 32 |
|
| 33 |
+
A LoRA for Flux.1 Dev to re-create really bad and trippy CGI from the 90s.
|
| 34 |
|
| 35 |
+
For best results:
|
| 36 |
+
- Set `lora_scale` within ranges 1.2 to 1.4 for full effect
|
| 37 |
|
| 38 |
|
| 39 |
## Trigger words
|
| 40 |
You should use `TRP90S` to trigger the image generation.
|
| 41 |
+
("A photo of TRP90S", or, "in the style of TRP90S")
|
| 42 |
|
| 43 |
|
| 44 |
## Use it with the [🧨 diffusers library](https://github.com/huggingface/diffusers)
|
|
|
|
| 53 |
```
|
| 54 |
|
| 55 |
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)
|
| 56 |
+
|
| 57 |
+
|
| 58 |
+
Trained on Replicate using:
|
| 59 |
+
|
| 60 |
+
https://replicate.com/ostris/flux-dev-lora-trainer/train
|