TheAwakenOne
commited on
Commit
•
48749a9
1
Parent(s):
cd23996
Update README.md
Browse files
README.md
CHANGED
@@ -1,42 +1,61 @@
|
|
1 |
-
---
|
2 |
-
tags:
|
3 |
-
- text-to-image
|
4 |
-
- flux
|
5 |
-
- lora
|
6 |
-
- diffusers
|
7 |
-
- template:sd-lora
|
8 |
-
- fluxgym
|
9 |
-
widget:
|
10 |
-
- output:
|
11 |
-
url: sample/ldlaughingmemeface_000450_00_20241001223402.png
|
12 |
-
text: LDME Young adult male at a party, mid-laugh with eyebrows raised in mock
|
13 |
-
surprise. He's holding a red solo cup and wearing a graphic t-shirt
|
14 |
-
- output:
|
15 |
-
url: sample/ldlaughingmemeface_000450_01_20241001223612.png
|
16 |
-
text: LDME Close-up of a smirking businessman with arched eyebrows, squinting
|
17 |
-
eyes, and a slightly open mouth. He's holding a coffee mug in an office setting
|
18 |
-
- output:
|
19 |
-
url: sample/ldlaughingmemeface_000450_02_20241001223822.png
|
20 |
-
text: LDME middle-aged woman in a casual shirt, raising his eyebrows skeptically
|
21 |
-
while holding a martini
|
22 |
-
base_model: black-forest-labs/FLUX.1-dev
|
23 |
-
instance_prompt: LDME
|
24 |
-
license: other
|
25 |
-
license_name: flux-1-dev-non-commercial-license
|
26 |
-
license_link: https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md
|
27 |
-
---
|
28 |
-
|
29 |
-
# LDLaughingMemeFace
|
30 |
-
|
31 |
-
A Flux LoRA trained on a local computer with [Fluxgym](https://github.com/cocktailpeanut/fluxgym)
|
32 |
-
|
33 |
-
<Gallery />
|
34 |
-
|
35 |
-
## Trigger words
|
36 |
-
|
37 |
-
You should use `LDME` to trigger the image generation.
|
38 |
-
|
39 |
-
|
40 |
-
|
41 |
-
|
42 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
tags:
|
3 |
+
- text-to-image
|
4 |
+
- flux
|
5 |
+
- lora
|
6 |
+
- diffusers
|
7 |
+
- template:sd-lora
|
8 |
+
- fluxgym
|
9 |
+
widget:
|
10 |
+
- output:
|
11 |
+
url: sample/ldlaughingmemeface_000450_00_20241001223402.png
|
12 |
+
text: LDME Young adult male at a party, mid-laugh with eyebrows raised in mock
|
13 |
+
surprise. He's holding a red solo cup and wearing a graphic t-shirt
|
14 |
+
- output:
|
15 |
+
url: sample/ldlaughingmemeface_000450_01_20241001223612.png
|
16 |
+
text: LDME Close-up of a smirking businessman with arched eyebrows, squinting
|
17 |
+
eyes, and a slightly open mouth. He's holding a coffee mug in an office setting
|
18 |
+
- output:
|
19 |
+
url: sample/ldlaughingmemeface_000450_02_20241001223822.png
|
20 |
+
text: LDME middle-aged woman in a casual shirt, raising his eyebrows skeptically
|
21 |
+
while holding a martini
|
22 |
+
base_model: black-forest-labs/FLUX.1-dev
|
23 |
+
instance_prompt: LDME
|
24 |
+
license: other
|
25 |
+
license_name: flux-1-dev-non-commercial-license
|
26 |
+
license_link: https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md
|
27 |
+
---
|
28 |
+
|
29 |
+
# LDLaughingMemeFace
|
30 |
+
|
31 |
+
A Flux LoRA trained on a local computer with [Fluxgym](https://github.com/cocktailpeanut/fluxgym)
|
32 |
+
|
33 |
+
<Gallery />
|
34 |
+
|
35 |
+
## Trigger words
|
36 |
+
|
37 |
+
You should use `LDME` to trigger the image generation.
|
38 |
+
|
39 |
+
How to Use This LoRA Model
|
40 |
+
|
41 |
+
Describing the Expression
|
42 |
+
|
43 |
+
To get the best results from this LoRA model, use descriptive words that capture the essence of the facial expressions you want to generate. Consider phrases like:
|
44 |
+
|
45 |
+
"exaggerated expression"
|
46 |
+
"raised eyebrows"
|
47 |
+
"as if mocking"
|
48 |
+
"eyebrows lifted and smirking"
|
49 |
+
|
50 |
+
These descriptors will help the model focus on creating the unique, expressive faces you're aiming for.
|
51 |
+
|
52 |
+
Adjusting LoRA Strength
|
53 |
+
|
54 |
+
Strength 1: At full strength, the LoRA model tends to generate images of the same character when you prompt with "a man." This can be useful if you want consistency in character appearance.
|
55 |
+
|
56 |
+
Dialing Down Strength: If you wish to create different characters or add variety, reduce the strength of the LoRA. A strength setting around 0.7 has been effective for me, but I encourage experimenting with different levels to achieve your desired outcome.
|
57 |
+
|
58 |
+
## Download model and use it with ComfyUI, AUTOMATIC1111, SD.Next, Invoke AI, Forge, etc.
|
59 |
+
|
60 |
+
Weights for this model are available in Safetensors format.
|
61 |
+
|