MOSS-Image Kodachrome
Model description
base_model: OpenMOSS-Team/MOSS-Image-Base tags:
- lokr
- lycoris
- moss-image
- style
- kodachrome
- film
- ai-toolkit license: apache-2.0
Kodachrome LoKr for MOSS-Image
This is a LoKr adapter that gives MOSS-Image the look of Kodachrome slide film. It mimics the color response and the contrast curve of 1940s 4x5 Kodachrome sheet film, but above all the quality and the sharpness. It was trained on MOSS-Image-Base with Ostris AI Toolkit at 1280 batch 4 for 750 steps; the style had transferred by then, but not yet the grain. Treat it as an intermediate checkpoint.
Usage
Load it with the standard LoRA loader in ComfyUI (LoKr support is in core) or with `load_lora_weights` in Diffusers. Trained and tested on MOSS-Image-Base; tested at strength 1.0 with CFG 3, 50 steps, and skip-layer guidance on layer 22. Trigger words: `Kodachrome film, Kodachrome`. Describe the scene in the prompt as you normally would; the film look comes from the adapter.
Why a factor 16 LoKr
A film look is a small amount of information: a palette, a tone curve, grain. A full-rank LoKr at factor 16 has enough capacity for that and produces a file about 5% the size of a rank 32 LoRA. In community Krea 2 and MOSS runs, LoKr also shows less subject bleed than LoRA, which matters for a style trained on photographs of people and places; the adapter should carry the film and not the dataset.
Dataset
551 scans of Kodachrome slides, high resolution, no JPEG compression artifacts. Subjects and settings are deliberately varied: portraits, street scenes, landscapes, interiors, vehicles, daylight and artificial light, several decades of emulsion. Images were trained at native resolution with aspect-ratio buckets, capped at a 1280² pixel area (1.64 MP); scans larger than that were downscaled, smaller ones left as they are. The set bucketed into 130 resolution groups, 66 of them single images. Captions describe the scene content and carry the trigger word; the film look itself is not described in the captions.
Training
Ostris AI Toolkit, architecture `moss_image` (MOSS-Image-Base), text encoder frozen.
- Network: LoKr, full rank, factor 16
- Optimizer: AdamW 8-bit, learning rate 1e-4
- Batch size 4 (within buckets, so 213 steps per epoch; mean effective batch 2.6)
- Steps: 750, about 3.5 epochs
- EMA: on, decay 0.98
- Timestep sampling: flowmatch, shift, balanced
- Resolution: 1280 (area cap), bucketing on, no square crop
- Precision: bf16
- Checkpoints every 250 steps; the 750 step checkpoint is the one published here
Limitations
Grain and halation are learned at 1280² area and weaken at output sizes well below 1 MP. Inherits MOSS-Image's known weak points (small text, hands). Tested on Base only; behavior on MOSS-Image-SFT is unverified.
License
The adapter is released under Apache-2.0, matching the base model. The training images are not included.
Trigger words
You should use Kodachrome film or Kodachrome to trigger the image generation, but rather use something like shot on Kodachrome film or the trigger may bleed into the image (see the front of the diesel engine).
Download model
Download them in the Files & versions tab.