Image-Text-to-Video
Diffusers
Safetensors
text-to-video
image-to-video
video-to-video
text-to-audio-video
image-to-audio-video
image-text-to-audio-video
video-to-audio-video
audio-to-audio-video
audio-video-generation
multimodal
synchronized-audio-video
reference-to-audio-video
Instructions to use Green-eyedDevil/MiniMax-H3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use Green-eyedDevil/MiniMax-H3 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("Green-eyedDevil/MiniMax-H3", 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": "AutoencoderKLMiniMaxH3Audio", | |
| "_diffusers_version": "0.36.0.dev0", | |
| "encoder_dim": 64, | |
| "encoder_rates": [ | |
| 2, | |
| 4, | |
| 4, | |
| 5, | |
| 5 | |
| ], | |
| "latent_dim": 2048, | |
| "latent_channels": 32, | |
| "decoder_dim": 1024, | |
| "decoder_rates": [ | |
| 5, | |
| 5, | |
| 2, | |
| 2, | |
| 2, | |
| 2, | |
| 2 | |
| ], | |
| "decoder_kernel_sizes": [ | |
| 9, | |
| 9, | |
| 4, | |
| 4, | |
| 4, | |
| 4, | |
| 4 | |
| ], | |
| "num_attention_heads": 8, | |
| "resblock_kernel_sizes": [ | |
| 3, | |
| 7, | |
| 11 | |
| ], | |
| "resblock_dilation_sizes": [ | |
| [ | |
| 1, | |
| 3, | |
| 5 | |
| ], | |
| [ | |
| 1, | |
| 3, | |
| 5 | |
| ], | |
| [ | |
| 1, | |
| 3, | |
| 5 | |
| ] | |
| ], | |
| "sampling_rate": 32000, | |
| "latents_mean": [ | |
| -0.020211687488382354, | |
| 0.3876466479950502, | |
| -0.04398279799186767, | |
| -0.28591514936373, | |
| 0.08179686214561671, | |
| -0.35782641352446604, | |
| 0.040623809960919084, | |
| -0.01552534501956604, | |
| -0.223362481667332, | |
| 0.1821006842509091, | |
| 0.2941778783780663, | |
| -0.07901167601970885, | |
| -0.056815072777201, | |
| -0.3699028221860095, | |
| -0.31616315591624855, | |
| 0.5905951377425391, | |
| -0.052139568068853864, | |
| 0.013673160263486295, | |
| -0.03691647864630577, | |
| 0.09732660653298163, | |
| -0.3394662328788498, | |
| -0.30685677538541667, | |
| -0.24504598907458763, | |
| -0.034698524462007344, | |
| 0.02868032184767538, | |
| -0.21217779266454084, | |
| -0.1678263169941987, | |
| 0.3221287889040614, | |
| -0.1223055851554907, | |
| 0.4356604928128464, | |
| -0.0502599202236253, | |
| 0.3979258376211797 | |
| ], | |
| "latents_std": [ | |
| 1.6895524230479284, | |
| 2.76263727217653, | |
| 1.7945344281264435, | |
| 1.6801681847309828, | |
| 1.6390226546605453, | |
| 2.7788298348882177, | |
| 1.7659090095747236, | |
| 1.6199757612137327, | |
| 2.6336525640336896, | |
| 1.8539356672817833, | |
| 2.5056497896915633, | |
| 1.811019237886178, | |
| 1.9579657790720237, | |
| 1.6685498243529284, | |
| 1.4922469314453364, | |
| 3.298670198067373, | |
| 1.9491804496832168, | |
| 1.8720003270431442, | |
| 1.8334080103291832, | |
| 1.6488070416529093, | |
| 1.6176957696319716, | |
| 1.9131449234774398, | |
| 1.5695245398428617, | |
| 1.6943659940415912, | |
| 1.8318420762504692, | |
| 1.5540637421583379, | |
| 1.9344930328968526, | |
| 1.599198216109855, | |
| 1.718045989838149, | |
| 1.6307219190837705, | |
| 1.8661226051202384, | |
| 1.5613768203168363 | |
| ] | |
| } |