Text-to-Image
Diffusers
Safetensors
jetson
sglang
minimax-h3-image
How to use from the
Use from the
Diffusers library
pip install -U diffusers transformers accelerate
import torch
from diffusers import DiffusionPipeline

# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("manateelazycat/MiniMax-H3-Image-AIPod", 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-Image for AI Pod

Powered by MiniMax-H3-Image. Read the complete upstream license, territorial and use restrictions, and NOTICE before use. This release uses SGLang Diffusion's native MiniMax-H3-Image pipeline, explicitly selecting --backend sglang. It does not use a standalone PyTorch/Diffusers model implementation or automatic backend fallback. The model directory retains the original immutable upstream checkpoint layout and separate H3 BF16 text encoder. Only completed fixed-revision release manifests and their final LPK are installation inputs.

Downloads last month
-
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support