Instructions to use SimpleTuner/minimax-h3-image-LoRA-experiments with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use SimpleTuner/minimax-h3-image-LoRA-experiments with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("MiniMaxAI/MiniMax-H3-Image", dtype=torch.bfloat16, device_map="cuda") pipe.load_lora_weights("SimpleTuner/minimax-h3-image-LoRA-experiments") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
MiniMax H3 Image: A LoRA Experiment Journal
This journal compares unassisted Domokun training at 2048px, 4096px, and mixed 2048px + 4096px while a separate four-H100 run trains a broad-data assistant for 30,000 optimizer updates. Prepared recipes are not completed results.
Contents
- Training setup
- Domokun: three resolution controls
- A real-data-only training assistant
- Photo aesthetics with an assistant
- Progress and runtime notes
- Assistant follow-up controls
The recipes and run manifest follow the layout of the FLUX.3 Klein journal. Measurements and checkpoint links are added only after verification.
Initial campaign
- Downloads last month
- -
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐ Ask for provider support