MossForge model bundle

Everything MossForge (a native macOS studio for MOSS-Image) needs, laid out exactly as its models/ folder. MossForge's first-run setup reads mossforge-manifest.json, downloads the groups you pick into place and checks every file's SHA-256. You can add more weights and LoRAs to models/ later, and MossForge picks them up.

This is a mirror of third-party weights, not new models. Every file keeps its original licence (all Apache-2.0).

Group	Contents	Size	Default
essentials	Essentials	15.5 GB	yes
sft	MOSS-Image SFT (bf16)	10.2 GB	optional
base	MOSS-Image Base (bf16)	10.2 GB	optional
turbo-sft	Turbo LoRA for SFT (lodestones, 8-step)	1.2 GB	optional
turbo-base	Turbo LoRA for Base (lodestones, 8-step)	1.2 GB	optional
turbo-4step	4-step LoRA for SFT (akhaliq)	1.2 GB	optional

Layout

models/
├── diffusion_models/   DiTs (+ .mfmeta.json sidecars, -dataspace files)
├── text_encoders/      qwen3.5_9b_int8_convrot.safetensors, qwen3.5-9b-tokenizer/
├── vae/                flux2-vae.safetensors
└── lora/<author>/      LoRAs with their supporting files and sidecars

Provenance and licences

File(s)	Source	Licence
diffusion_models/moss_image_{sft,base}_bf16	Comfy-Org/MOSS-Image repack of OpenMOSS-Team/MOSS-Image	Apache-2.0
text_encoders/qwen3.5_9b_int8_convrot	Comfy-Org/MOSS-Image (Qwen3.5-9B, int8 ConvRot)	Apache-2.0
text_encoders/qwen3.5-9b-tokenizer/	Qwen/Qwen3.5-9B	Apache-2.0 (LICENSE included)
vae/flux2-vae	FLUX.2 VAE (ae.safetensors)	Apache-2.0
lora/lodestones/*	lodestones/MOSS-Image-SFT-8-steps-dmd, …-Base-8-steps-dmd	Apache-2.0
lora/akhaliq/akhaliq-4step-sft	akhaliq/MOSS-Image-SFT-4-steps v2.0	Apache-2.0
diffusion_models/moss_image_sft_lodestones-8step-sft_int8_convrot*	Made by MossForge: the lodestones SFT 8-step LoRA fused into SFT bf16 in fp32, then int8 ConvRot	Apache-2.0

MOSS-Image is by the OpenMOSS Team. This bundle is unofficial and not affiliated with or endorsed by OpenMOSS.