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
| from __future__ import annotations | |
| def inventory_failure( | |
| component_mode: str, *, orbit_count: int, adaln_count: int, cache_count: int | |
| ) -> str | None: | |
| if cache_count: | |
| return "full dequantized caches present after clean load" | |
| low_bit_count = orbit_count + adaln_count | |
| if component_mode == "w4a4" and low_bit_count == 0: | |
| return "no low-bit modules restored" | |
| if component_mode == "source_copy" and low_bit_count: | |
| return "unexpected low-bit modules in source component copy" | |
| if component_mode not in {"w4a4", "source_copy"}: | |
| return f"unknown component mode: {component_mode}" | |
| return None | |