Instructions to use SimpleTuner/moss-image-LoRA-experiments with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use SimpleTuner/moss-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("OpenMOSS-Team/MOSS-Image-Base", dtype=torch.bfloat16, device_map="cuda") pipe.load_lora_weights("SimpleTuner/moss-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
Download README.md from SimpleTuner/moss-image-LoRA-experiments: direct link, hf CLI and curl.
- Browser
- Download file 3.64 kB
-
https://huggingface.co/SimpleTuner/moss-image-LoRA-experiments/resolve/main/README.md
- Command line
-
hf download hf://SimpleTuner/moss-image-LoRA-experiments/README.md
-
curl -L -o README.md https://huggingface.co/SimpleTuner/moss-image-LoRA-experiments/resolve/main/README.md
license: apache-2.0
base_model:
- OpenMOSS-Team/MOSS-Image-Base
- OpenMOSS-Team/MOSS-Image-SFT
library_name: diffusers
tags:
- simpletuner
- moss-image
- lora
- experiments
MOSS-Image: A LoRA Experiment Journal
This experiment compares learning Domokun with MOSS-Image Base and SFT at 512px and 1024px, then repeats the 512px comparison with vision-grounded native JSON captions.
Protocol
The initial four runs use the original filename captions for all 29 images in
RareConcepts/Domokun, pinned to
2e4831a72f2a701c080e0046c8f8ec41cb1ccbcf. Each run starts from its released checkpoint:
Base 1ceede80badddd6a7812069619edaa5633587192, SFT fc5de0d56fc910cbca6f6625a70f5f582b26deb1.
Resolution is equivalent image area with original aspect ratios preserved.
Every run targets 10,000 optimizer updates on one H100 80 GB, with rank-32 BF16 LoRA,
batch 4, gradient accumulation 1, learning rate 0.0001, 25 warmup updates, seed 42, and REPA.
Validation uses four prompts, 50 sampling steps, CFG 3, seed 42, at startup and every 500 updates.
All 20 saved adapter checkpoints and their validation previews are published per completed run.
Baseline images are available in each run repository's baseline folder.
The two JSON-caption runs are queued after all initial runs finish and start fresh from Base/SFT.
They share one set of captions generated using Qwen/Qwen3.5-27B, revision
fc05daec18b0a78c049392ed2e771dde82bdf654, grounded in training images and actual 512px bucket dimensions.
Captions must pass native schema, bounding-box, concept-token, and tokenizer-length checks before training.
These runs use the same 10,000-update protocol; no 1024px JSON runs or assistant-LoRA runs are scheduled.
Adapters and previews are collected without interrupting training. Full training state and logs are archived separately.
The public recipes retain the in-process publishing flags used during training; an external collector uploads results.
The original-caption runs use SimpleTuner revision e30354dffd02c80f52f39912cea271f12be5ac4e;
the JSON runs use the shared schema implementation from PR #3273.
Progress
| Run | Observed updates | Latest published checkpoint | Status |
|---|---|---|---|
| base-512 | 10,000 / 10,000 | 10,000 | completed |
| base-1024 | 10,000 / 10,000 | 10,000 | completed |
| sft-512 | 10,000 / 10,000 | 10,000 | completed |
| sft-1024 | 10,000 / 10,000 | 10,000 | completed |
| json-base-512 | 10,000 / 10,000 | 10,000 | completed |
| json-sft-512 | 10,000 / 10,000 | 10,000 | completed |