Image-Text-to-Video
MiniMax H3
Safetensors
English
lora
face-realism
minimax
h3
video
text-to-video
video-generation
portrait
photorealistic
Instructions to use prithivMLmods/MiniMax-H3-Facial-Realism-CloseUp with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Inference
- Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -43,7 +43,7 @@ prompts:
|
|
| 43 |
MiniMax-H3-Facial-Realism-CloseUp is an experimental Human Face Realism LoRA adapter trained on the general-purpose multimodal model MiniMax H3. This LoRA is trained on a high-quality, human-centric face portrait dataset composed of video buckets featuring subtle facial details and micro-expressions.
|
| 44 |
|
| 45 |
> [!NOTE]
|
| 46 |
-
> All checkpoints are available here: https://huggingface.co/buckets/prithivMLmods/minimax-h3-facial-realism-closeup
|
| 47 |
|
| 48 |
## Model Details
|
| 49 |
|
|
|
|
| 43 |
MiniMax-H3-Facial-Realism-CloseUp is an experimental Human Face Realism LoRA adapter trained on the general-purpose multimodal model MiniMax H3. This LoRA is trained on a high-quality, human-centric face portrait dataset composed of video buckets featuring subtle facial details and micro-expressions.
|
| 44 |
|
| 45 |
> [!NOTE]
|
| 46 |
+
> All checkpoints are available here: https://huggingface.co/buckets/prithivMLmods/minimax-h3-facial-realism-closeup. It is recommended to use checkpoint 1800 or 2000.
|
| 47 |
|
| 48 |
## Model Details
|
| 49 |
|