Update README.md
Browse files
README.md
CHANGED
|
@@ -1,9 +1,26 @@
|
|
| 1 |
---
|
| 2 |
license: mit
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
---
|
| 4 |
|
| 5 |
# **Hunyuan Video Lora - AnimeShots**
|
| 6 |
|
|
|
|
| 7 |
|
| 8 |
|
| 9 |
[v0.1 - testing version]
|
|
@@ -42,4 +59,4 @@ Use prompts in the format of `anime <subject> <description>` to get the best res
|
|
| 42 |
|
| 43 |
## Limitations
|
| 44 |
|
| 45 |
-
It's trained as a test model so sometimes when body movements are large it gets disconnected. Also some concepts are less anime-like compared to others. I do plan to update the model later with more training time and dataset.
|
|
|
|
| 1 |
---
|
| 2 |
license: mit
|
| 3 |
+
datasets:
|
| 4 |
+
- trojblue/test-HunyuanVideo-anime-stills
|
| 5 |
+
base_model:
|
| 6 |
+
- tencent/HunyuanVideo
|
| 7 |
+
pipeline_tag: text-to-video
|
| 8 |
+
tags:
|
| 9 |
+
- hunyuan-video
|
| 10 |
+
- text-to-video
|
| 11 |
+
- lora
|
| 12 |
+
- diffusers
|
| 13 |
+
- template:diffusion-lora
|
| 14 |
+
instance_prompt: anime
|
| 15 |
+
widget:
|
| 16 |
+
- text: 'anime girl 1girl, alcohol carton, blush, braid, bridge, crosswalk, dress, green dress, holding carton, long hair, long sleeves, multiple girls, night, open mouth, outdoors, pedestrian bridge, purple eyes, red hair, single braid, solo focus, spaghetti strap'
|
| 17 |
+
output:
|
| 18 |
+
url: samples/ComfyUI_00017_.webp
|
| 19 |
---
|
| 20 |
|
| 21 |
# **Hunyuan Video Lora - AnimeShots**
|
| 22 |
|
| 23 |
+
<Gallery />
|
| 24 |
|
| 25 |
|
| 26 |
[v0.1 - testing version]
|
|
|
|
| 59 |
|
| 60 |
## Limitations
|
| 61 |
|
| 62 |
+
It's trained as a test model so sometimes when body movements are large it gets disconnected. Also some concepts are less anime-like compared to others. I do plan to update the model later with more training time and dataset.
|