Image-Text-to-Video
Diffusers
Safetensors
MiniMax H3
modular-diffusers
ref2va
fl2va
Merge
synchronized-audio-video
experimental
Instructions to use diffusers-modular/MiniMax-H3-Pruned-Ref-Delta-Fused-r1024 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use diffusers-modular/MiniMax-H3-Pruned-Ref-Delta-Fused-r1024 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("diffusers-modular/MiniMax-H3-Pruned-Ref-Delta-Fused-r1024", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
| { | |
| "_class_name": "MiniMaxH3PrunedTransformer3DModel", | |
| "_diffusers_version": "0.40.0.dev0", | |
| "_name_or_path": "multimodalart/MiniMax-H3-Pruned", | |
| "adaln_rank": 8, | |
| "attention_head_dim": 128, | |
| "audio_in_channels": 32, | |
| "auto_map": { | |
| "AutoModel": "modeling_minimax_h3_pruned.MiniMaxH3PrunedTransformer3DModel" | |
| }, | |
| "ffn_dim": 14336, | |
| "final_norm_eps": 1e-05, | |
| "freq_dim": 256, | |
| "hidden_size": 5376, | |
| "in_channels": 24, | |
| "norm_eps": 1e-05, | |
| "num_attention_heads": 56, | |
| "num_layers": 50, | |
| "num_refiner_layers": 2, | |
| "patch_size": [ | |
| 1, | |
| 2, | |
| 2 | |
| ], | |
| "qk_norm_eps": 1e-05, | |
| "rope_freq_dim": 16, | |
| "rope_theta": 10000.0, | |
| "text_dim": 5120, | |
| "time_embed_dim": 2688, | |
| "time_embed_hidden_dim": 5376, | |
| "time_table_size": 1025 | |
| } | |