Use the standard MOSS-Image CLIP, VAE and scheduler names

README.md

@@ -42,11 +42,11 @@ The LoRA is rank 64 on linear layers and rank 16 on convolutions. It was trained
 
 ## How to use
 
-1. Load **MOSS-Image-SFT**: UNet `moss_image_sft_int8_convrot.safetensors`, text encoder `qwen3.5_9b_int8_convrot.safetensors` with type `moss_image`, VAE `flux2-vae.safetensors`.
+1. Load **MOSS-Image-SFT**: UNet `moss_image_sft_int8_convrot.safetensors`, text encoder `qwen3.5_9b_w4a8_gptq.safetensors` with type `moss_image`, VAE `flux2-vae_small.safetensors`.
 2. Load this LoRA on the UNet at strength **1.0**.
 3. Build the control map and pass it as the single reference image in **Text Encode MOSS-Image Edit**.
 4. Set **edit format** to `ai-toolkit` on both the positive and the negative encode. This LoRA was trained with kv cache on.
-5. Sample with **30 steps**, **CFG 4**, `euler` + `normal`.
+5. Sample with **30 steps**, **CFG 4**, `euler` + `simple`.
 
 No trigger word. The control image sets the structure. The prompt sets identity, materials, clothing and the world.
 
@@ -62,7 +62,7 @@ Also uses the built-in **Text Encode MOSS-Image Edit** node. Set the edit format
 
 Trained on and recommended with **[OpenMOSS-Team/MOSS-Image-SFT](https://huggingface.co/OpenMOSS-Team/MOSS-Image-SFT)**.
 
-Typical settings from the included workflow: **30 steps**, **CFG 4**, `euler` + `normal`, LoRA strength **1.0**.
+Typical settings from the included workflow: **30 steps**, **CFG 4**, `euler` + `simple`, LoRA strength **1.0**.
 
 Negative prompt used in training samples: