Diffusers
simpletuner
minimax-h3-image
lora
experiments

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

  1. Training setup
  2. Domokun: three resolution controls
  3. A real-data-only training assistant
  4. Photo aesthetics with an assistant
  5. Progress and runtime notes
  6. 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

Run Target updates Hardware Progress
Domokun 2048 10,000 1 H100 Status
Domokun 4096 10,000 1 H100 Status
Domokun mixed 2048 + 4096 10,000 1 H100 Status
Broad-data assistant 30,000 4 H100 Status
Downloads last month
-
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Model tree for SimpleTuner/minimax-h3-image-LoRA-experiments

Adapter
(7)
this model