Update README.md

README.md

@@ -48,25 +48,13 @@ docker run --rm --gpus all -p 8080:80 \
   your-image:tag
 ```
 
-**Conservative `COMFY_FLAGS` presets by GPU**
+**Recommended `COMFY_FLAGS`**
 
 These presets prioritize stability. They’re meant as safe defaults; you should still **set `COMFY_FLAGS` explicitly** for your deployment when you know your workload.
 
-**Tesla T4 / L4**
-- Recommended COMFY_FLAGS: `--lowvram --disable-xformers --disable-smart-memory --use-pytorch-cross-attention --cache-lru 1 --reserve-vram 3.5`
-  
-**G10 | A10G | A10 | A40 | L40S| L40**
-- Recommended COMFY_FLAGS: `--normalvram --disable-xformers --use-pytorch-cross-attention --cache-lru 64 --reserve-vram 1.5`
-                     
-**A100 80GB | H100 | H200**
-- Recommended COMFY_FLAGS: `--normalvram --disable-xformers --use-pytorch-cross-attention --cache-lru 128 --reserve-vram 1.0`
-                             
-**By VRAM:**
-
-* `≥ 70 GB` → `--normalvram --disable-xformers --use-pytorch-cross-attention --cache-lru 256 --reserve-vram 1.0`
-* `≥ 22 GB` → `--normalvram --disable-xformers --use-pytorch-cross-attention --cache-lru 64  --reserve-vram 1.5`
-* `< 22 GB` → `--lowvram  --disable-xformers --disable-smart-memory --use-pytorch-cross-attention --cache-lru 1 --reserve-vram 3.5`
-
-> Keep `--disable-xformers --use-pytorch-cross-attention` in all presets.
-> Use `--disable-smart-memory` for low VRAM profiles.
+`--disable-xformers --use-pytorch-cross-attention --cache-lru 2 --reserve-vram 2.0`
+
+**Minimal recommended `hardware`**
+
+- Nvidia L4: 8 vCPU, 32 GiB RAM, disk 40 GiB