Note that Base + rank-512 LoRA bands like SFT

README.md

@@ -33,7 +33,7 @@ Don't stack it with [Kijai's blocks 21–49 LoRA](https://huggingface.co/Kijai/M
 [Kijai/MOSS-image_experimental](https://huggingface.co/Kijai/MOSS-image_experimental) has the SFT-difference LoRAs this work builds on, and his README has the original −0.5 banding recipe:
 
 - [`moss_image_sft_lora_blocks_21_to_49_rank_512_bf16`](https://huggingface.co/Kijai/MOSS-image_experimental/blob/main/loras/moss_image_sft_lora_blocks_21_to_49_rank_512_bf16.safetensors): his banding fix, applied to SFT at −0.5. It's the "Kijai" column below.
-- [`moss_image_sft_lora_rank_256_bf16`](https://huggingface.co/Kijai/MOSS-image_experimental/blob/main/loras/moss_image_sft_lora_rank_256_bf16.safetensors) and [`moss_image_sft_lora_rank_512_bf16`](https://huggingface.co/Kijai/MOSS-image_experimental/blob/main/loras/moss_image_sft_lora_rank_512_bf16.safetensors): the full SFT difference as a LoRA, for applying the SFT look to the Base model at whatever strength you want.
+- [`moss_image_sft_lora_rank_256_bf16`](https://huggingface.co/Kijai/MOSS-image_experimental/blob/main/loras/moss_image_sft_lora_rank_256_bf16.safetensors) and [`moss_image_sft_lora_rank_512_bf16`](https://huggingface.co/Kijai/MOSS-image_experimental/blob/main/loras/moss_image_sft_lora_rank_512_bf16.safetensors): the full SFT difference as a LoRA, for applying the SFT look to the Base model at whatever strength you want. At +1 the rank-512 version reproduces SFT's banding as well (41.5 vs 41.0 on the goose bench).
 
 His fix and this one take different routes. His subtracts half of the SFT change across layers 3, 4 and 21–41; this one fully reverts only layers 37–41. Pick by eye: the grids below show both on every test image.