import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("xxnuo/MiniMax-H3-Sol", dtype=torch.bfloat16, device_map="cuda")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]MiniMax H3 Sol checkpoints
Complete pinned checkpoint bundle used by lzc-aipod-minimax-h3-sol: 72 runtime files, 219842086226 bytes. Includes text-to-video, first/last-frame and reference-video components.
Original weights, tokenizer files and configuration files are unchanged. Each component retains its original license; this bundle does not relicense them. Upstream model cards and license notices are preserved under upstream/. See upstream-model-manifest.json for original repositories, revisions, file sizes and SHA-256 checksums.
License texts: MiniMax H3, LTX-2.x. The applicable use restrictions in these licenses apply to recipients of this bundle. See NOTICE.
Paths follow the runtime checkpoint layout, rooted at the repository root.
- Downloads last month
- -
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support