Instructions to use iedavidcastilloX/CandyAI with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use iedavidcastilloX/CandyAI with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("iedavidcastilloX/CandyAI", device_map="auto") - Notebooks
- Google Colab
- Kaggle
| language: en | |
| license: mit | |
| tags: | |
| - candy-ai | |
| - text-to-video | |
| - animation | |
| - stable-diffusion | |
| pipeline_tag: text-to-video | |
| model-index: | |
| - name: CandyCrushAI | |
| results: | |
| - task: | |
| type: text-to-video | |
| name: candy animation generation | |
| metrics: | |
| - type: accuracy | |
| value: 0.92 | |
| - type: fid_score | |
| value: 18.5 | |
| - type: clip_score | |
| value: 0.85 | |
| datasets: | |
| - candy_crush_dataset | |
| base_model: "runwayml/stable-diffusion-v1-5" | |
| library_name: transformers | |
| training_config: | |
| architecture: | |
| base_model: "runwayml/stable-diffusion-v1-5" | |
| lora_r: 32 | |
| lora_alpha: 64 | |
| lora_dropout: 0.1 | |
| num_epochs: 5 | |
| gradient_accumulation_steps: 16 | |
| training_params: | |
| batch_size: 4 | |
| learning_rate: 2e-5 | |
| warmup_steps: 100 | |
| max_grad_norm: 0.3 | |
| generation_params: | |
| num_inference_steps: 50 | |
| guidance_scale: 7.5 | |
| frame_rate: 24 | |
| inference_config: | |
| max_frames: 120 | |
| resolution: 512 | |
| fps: 24 | |
| optimization_level: "premium" | |
| widget: | |
| - text: "Generate candy animation" | |
| example_input: "colorful candy explosion with rainbow sparkles" | |