Weights' metadata format pt (as PEFT writes it; weights unchanged); card: drawing with diffu's --lora

README.md

@@ -44,7 +44,21 @@ them; diffu's `MossTransformer` does.
 
 ## Use
 
-With PEFT, merged into the DiT, which diffu then draws with like any MOSS-Image model:
+With [diffu](https://github.com/Borg93/diffu2), loaded onto MOSS-Image-Base's own DiT at draw time (no merged model
+needed; diffu's `docs/MOSS.md`, "Hand LoRAs", and `docs/INFERENCE.md`):
+
+```bash
+hf download OpenMOSS-Team/MOSS-Image-Base --revision 85975793d8b3d432f1b6e27f352abaa4c2a4c0d3 --local-dir models/MOSS-Image-Base
+hf download Gabriel/diffu-moss-hand-eight --local-dir models/adapters/eight
+uv run diffu-moss-init --base models/MOSS-Image-Base --out models/moss-base
+uv run diffu-run --jobs run.jsonl --draw-settings draw.json --model models/moss-base \
+    --lora hand=models/adapters/eight --out out/eight --gpus 1
+```
+
+`"fuse_loras": true` in `draw.json` merges the adapter into the DiT's weights at load (needed with MXFP8 or compiled
+blocks).
+
+Or with PEFT alone, merged into the DiT, which diffu then draws with like any MOSS-Image model:
 
 ```python
 from peft import PeftModel

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a9b291e6920fe2e0d2e1be1da99d1e40ed58f21491ada54b35d5f61111d2c767
-size 156254296
+oid sha256:a44d01611e23b697c80ea4c2ae44d36d59568a65f227049da6214d5b0e184469
+size 156254288