Commit
·
32d4fcc
1
Parent(s):
bb51b37
Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,33 @@
|
|
| 1 |
---
|
|
|
|
|
|
|
|
|
|
| 2 |
license: creativeml-openrail-m
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
+
language:
|
| 3 |
+
- en
|
| 4 |
+
thumbnail: "https://huggingface.co/wavymulder/CollageXL/resolve/main/imgs/grid2.jpg"
|
| 5 |
license: creativeml-openrail-m
|
| 6 |
+
tags:
|
| 7 |
+
- stable-diffusion
|
| 8 |
+
- text-to-image
|
| 9 |
+
- safetensors
|
| 10 |
+
inference: false
|
| 11 |
---
|
| 12 |
+
|
| 13 |
+
|
| 14 |
+
|
| 15 |
+
**CollageXL**
|
| 16 |
+
|
| 17 |
+
[*SAFETENSOR DOWNLOAD LINK*]( ADD LINK ) - This is an SDXL LoRA trained on collage images.
|
| 18 |
+
|
| 19 |
+
Use **collage style**, I recommend at the start of the prompt.
|
| 20 |
+
|
| 21 |
+
SDXL is much better at making collages than 1.5 was. This LoRA helps push SDXL towards making them a bit more analog.
|
| 22 |
+
|
| 23 |
+
Compared the Collage Diffusion for 1.5, this LoRA is much more responsive to prompting. One drawback is that sometimes the LoRA will just give an image, without much "collage style". I find best results when my prompt includes two distinct visual elements. In general, the more creative/weird your prompt, the better the result.
|
| 24 |
+
|
| 25 |
+
Can increase the "hand-made" effect with terms like "arts and craft", "cut and paste", "scrapbook". Can use these terms in negative for opposite effect, though this can also break the collage style.
|
| 26 |
+
|
| 27 |
+
"sepia" in negative helps brighten up the colors and remove the vintage look.
|
| 28 |
+
|
| 29 |
+
Please see [this document where I share the parameters (prompt, sampler, seed, etc.) used for all example images.]( ADD LINK )
|
| 30 |
+
|
| 31 |
+
|
| 32 |
+
|
| 33 |
+
|