Update README.md

README.md

@@ -14,22 +14,17 @@ tags:
 ---
 
 
-## Contents
+**Contents**
 
 | file | size |
 |---|---|
 | `loras/minimax_h3_fl2v_lightx2v_turbo_8step_merge_0821_bf16.safetensors` | 1.96 GB |
 
-## Recipe
-
-### FLFV 8 Step Merge 0821
+**FLFV 8 Step Merge 0821**
 
 | source | weight |
 |---|---|
 | `minimax_h3_fl2v_turbo_4step_v1.1_768p_comfyui_bf16.safetensors` | 0.5 |
 | `minimax_h3_fl2v_turbo_8step_v1.0_comfyui_bf16.safetensors` | 1.0 |
 
-The 4 step LoRA was trained using shift 6 and the 8 step was trained using shift 12, so 
-theoretically the best setting is 6 steps at 9 shift. Visual quality seems 
-optimal below strength 1.0 with any shift 6-12; at least on T2V, it *should* give more 
-detail than v1.1 LoRA and fixes fingers on the 8 step 1.0 LoRA.
+The 4 step LoRA was trained using shift 6 and the 8 step was trained using shift 12, however the recommended settings are `shift 9`, `8 steps`, and strength `1.0`.