Update README.md
Browse files
README.md
CHANGED
@@ -1,10 +1,18 @@
|
|
1 |
---
|
2 |
tags:
|
3 |
-
|
4 |
-
|
5 |
-
|
6 |
-
|
7 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
8 |
widget:
|
9 |
- text: >-
|
10 |
photo of two womenn talking and hugging while working at a busy place. flikr
|
@@ -148,7 +156,6 @@ widget:
|
|
148 |
url: images/ComfyUI_02445_.png
|
149 |
base_model: black-forest-labs/FLUX.1-dev
|
150 |
instance_prompt: photo
|
151 |
-
|
152 |
---
|
153 |
# Boreal-Flux-Dev-v2
|
154 |
|
@@ -159,6 +166,10 @@ instance_prompt: photo
|
|
159 |
**Boreal Flux Dev Version 2**
|
160 |
This version of the **Bo**ing **Real**ity flux dev LoRA used a different training approach for its dataset. It should also have the old latent shift dot issue fixed.
|
161 |
|
|
|
|
|
|
|
|
|
162 |
## Trigger words
|
163 |
|
164 |
You should use `photo` to trigger the image generation.
|
@@ -168,4 +179,4 @@ You should use `photo` to trigger the image generation.
|
|
168 |
|
169 |
Weights for this model are available in Safetensors format.
|
170 |
|
171 |
-
[Download](/kudzueye/boreal-flux-dev-v2/tree/main) them in the Files & versions tab.
|
|
|
1 |
---
|
2 |
tags:
|
3 |
+
- text-to-image
|
4 |
+
- stable-diffusion
|
5 |
+
- lora
|
6 |
+
- diffusers
|
7 |
+
- template:sd-lora
|
8 |
+
- flux
|
9 |
+
- photorealism
|
10 |
+
- photo
|
11 |
+
- realism
|
12 |
+
- boring reality
|
13 |
+
- boring
|
14 |
+
- reality
|
15 |
+
- amateur photo
|
16 |
widget:
|
17 |
- text: >-
|
18 |
photo of two womenn talking and hugging while working at a busy place. flikr
|
|
|
156 |
url: images/ComfyUI_02445_.png
|
157 |
base_model: black-forest-labs/FLUX.1-dev
|
158 |
instance_prompt: photo
|
|
|
159 |
---
|
160 |
# Boreal-Flux-Dev-v2
|
161 |
|
|
|
166 |
**Boreal Flux Dev Version 2**
|
167 |
This version of the **Bo**ing **Real**ity flux dev LoRA used a different training approach for its dataset. It should also have the old latent shift dot issue fixed.
|
168 |
|
169 |
+
This LoRA is very overtrained for how it works and the strength may need to be much lower than 1.0. It also works well with dynamic thresholding when you include a very high negative guidance.
|
170 |
+
|
171 |
+
This version lacks some of the creativity of the older version, as I am still trying to switch up how I am approaching the datasets and training parameters.
|
172 |
+
|
173 |
## Trigger words
|
174 |
|
175 |
You should use `photo` to trigger the image generation.
|
|
|
179 |
|
180 |
Weights for this model are available in Safetensors format.
|
181 |
|
182 |
+
[Download](/kudzueye/boreal-flux-dev-v2/tree/main) them in the Files & versions tab.
|