Image-Text-to-Video
Diffusers
Safetensors
orbitquant
comfyui
w4
w4a4
native-w4a4-transformer-runtime
text-to-video
audio-video-generation
8-bit precision
Instructions to use WaveCut/MiniMax-H3-OrbitQuant-W4A4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use WaveCut/MiniMax-H3-OrbitQuant-W4A4 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("WaveCut/MiniMax-H3-OrbitQuant-W4A4", 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": "MiniMaxH3Transformer3DModel", | |
| "_diffusers_version": "0.40.0.dev0", | |
| "_name_or_path": "MiniMaxAI/MiniMax-H3", | |
| "attention_head_dim": 128, | |
| "audio_in_channels": 32, | |
| "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, | |
| "quantization_config": { | |
| "activation_bits": 4, | |
| "activation_eps": 1e-10, | |
| "activation_kernel_backend": "auto", | |
| "activation_norm_dtype": "float32", | |
| "adaln_group_size": 64, | |
| "adaln_policy": "int4_rtn", | |
| "artifact_format_version": 1, | |
| "block_size": "paper", | |
| "codebook": "lloyd_max", | |
| "codebook_dtype": "float32", | |
| "codebook_version": 2, | |
| "lowbit_boundary_protection": "auto", | |
| "lowbit_interior_protection": "auto", | |
| "lowbit_protected_bits": 4, | |
| "lowbit_protected_blocks": 4, | |
| "modules_dtype_dict": {}, | |
| "modules_to_convert": [], | |
| "modules_to_not_convert": [ | |
| "proj_in", | |
| "audio_proj_in", | |
| "context_embedder", | |
| "time_embedder", | |
| "time_proj", | |
| "token_refiner", | |
| "norm_out", | |
| "proj_out", | |
| "audio_proj_out" | |
| ], | |
| "modules_to_use_adaln": [], | |
| "packed_matmul_block_k": 128, | |
| "packed_matmul_block_m": 64, | |
| "packed_matmul_block_n": 64, | |
| "packed_matmul_num_warps": 4, | |
| "quant_method": "orbitquant", | |
| "rotation": "rpbh", | |
| "rotation_seed": 0, | |
| "row_norm_dtype": "bfloat16", | |
| "runtime_mode": "auto_fused", | |
| "target_policy": "universal", | |
| "w4a4_int8_weight_cache": false, | |
| "weight_bits": 4, | |
| "weight_pack_dtype": "uint8", | |
| "weight_row_tile_size": 256 | |
| }, | |
| "rope_freq_dim": 16, | |
| "rope_theta": 10000.0, | |
| "text_dim": 5120, | |
| "time_embed_dim": 2688, | |
| "time_embed_hidden_dim": 5376 | |
| } | |