Update README.md
Browse files
README.md
CHANGED
@@ -8,10 +8,15 @@ tags:
|
|
8 |
|
9 |
# Arcane CogVideoX LoRA v1
|
10 |
|
11 |
-
|
|
|
|
|
|
|
12 |
|
13 |
## Important Notes:
|
14 |
|
|
|
|
|
15 |
- Despite the LoRA started to learn the appearance of the main characters it still doesn't able to reproduce them accurately. So don't expect to see your beloved characters.
|
16 |
- For the best quality do not use quantization (like fp8) or sage attention
|
17 |
|
@@ -20,11 +25,11 @@ This CogVideoX LoRA is created as part of a <b>fan project</b> for <b>research p
|
|
20 |
|
21 |
## ID Token / Trigger word(s):
|
22 |
|
23 |
-
Use these in your prompt helps providing the style. See example prompt
|
24 |
- csetiarcane
|
25 |
|
26 |
## Character Tokens:
|
27 |
-
I used tokens to tag characters. Unfortunately, it didn't properly learn their appearances, so don't expect to see your favorite characters. However, since it associates certain character features with the tokens, it might help with character consistency. See example prompt
|
28 |
|
29 |
| Token | Character |
|
30 |
|--------|-----------|
|
@@ -73,15 +78,6 @@ export_to_video(video, "output.mp4", fps=8)
|
|
73 |
- Thanks to [Kijai](https://github.com/kijai) for his great [ComfyUI integration](https://github.com/kijai/ComfyUI-CogVideoXWrapper)
|
74 |
- Thanks to [POM](https://huggingface.co/peteromallet) for providing the computing resources. Without this, these LoRAs could not have been created.
|
75 |
|
76 |
-
## Examples:
|
77 |
-
|
78 |
-
<b>Prompt:</b> "walgro1. Gromit sits quietly in a cozy living room, the soft glow of a nearby lamp casting warm light across the room. The camera starts with a close-up of his thoughtful expression, his eyes darting toward the side, observing the subtle movement of something off-screen. A clock ticks rhythmically on the wall behind him, creating a steady backdrop to the otherwise silent room.
|
79 |
-
The camera slowly pulls back to reveal the setting: a tidy space with bookshelves filled with old volumes, a comfortable armchair in the corner, and a small coffee table in the center, where a half-finished jigsaw puzzle lies scattered. The atmosphere is calm, almost serene, as Gromit glances toward the puzzle, his curiosity piqued."
|
80 |
-
<video width="720" height="480" controls>
|
81 |
-
<source src="https://huggingface.co/Cseti/CogVideoX-LoRA-Wallace_and_Gromit/resolve/main/WalGro_withLoRA_0000.mp4" type="video/mp4">
|
82 |
-
Your browser does not support the video tag.
|
83 |
-
</video>
|
84 |
-
|
85 |
## Citation
|
86 |
```
|
87 |
@article{yang2024cogvideox,
|
|
|
8 |
|
9 |
# Arcane CogVideoX LoRA v1
|
10 |
|
11 |
+
<video width="100%" height="auto" controls>
|
12 |
+
<source src="https://huggingface.co/Cseti/CogVideoX1.0-LoRA-Arcane-v1/resolve/main/csetiarcane_comparison_00017.mp4" type="video/mp4">
|
13 |
+
</video>
|
14 |
+
<b>Prompt:</b> "CSETIARCANE. The video is focusing on girl with blue hair. Her expression transitions subtly across the frames, starting from a somber or contemplative look and progressing to one that appears more engaged or possibly surprised. The lighting is dim and moody, emphasizing shadows and creating a dramatic effect around the character's features. The background remains consistently dark throughout the sequence, ensuring the focus stays solely on the character's changing expressions."
|
15 |
|
16 |
## Important Notes:
|
17 |
|
18 |
+
This CogVideoX LoRA is created as part of a <b>fan project</b> for <b>research purposes</b> only and is <b>not</b> intended for commercial use. It is based on the TV series called Arcane which are protected by copyright. Users utilize the model at their own risk. Users are obligated to comply with copyright laws and applicable regulations. The model has been developed for non-commercial purposes, and it is not my intention to infringe on any copyright. I assume no responsibility for any damages or legal consequences arising from the use of the model.
|
19 |
+
|
20 |
- Despite the LoRA started to learn the appearance of the main characters it still doesn't able to reproduce them accurately. So don't expect to see your beloved characters.
|
21 |
- For the best quality do not use quantization (like fp8) or sage attention
|
22 |
|
|
|
25 |
|
26 |
## ID Token / Trigger word(s):
|
27 |
|
28 |
+
Use these in your prompt helps providing the style. See example prompt above.
|
29 |
- csetiarcane
|
30 |
|
31 |
## Character Tokens:
|
32 |
+
I used tokens to tag characters. Unfortunately, it didn't properly learn their appearances, so don't expect to see your favorite characters. However, since it associates certain character features with the tokens, it might help with character consistency. See example prompt above.
|
33 |
|
34 |
| Token | Character |
|
35 |
|--------|-----------|
|
|
|
78 |
- Thanks to [Kijai](https://github.com/kijai) for his great [ComfyUI integration](https://github.com/kijai/ComfyUI-CogVideoXWrapper)
|
79 |
- Thanks to [POM](https://huggingface.co/peteromallet) for providing the computing resources. Without this, these LoRAs could not have been created.
|
80 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
81 |
## Citation
|
82 |
```
|
83 |
@article{yang2024cogvideox,
|