Document --allow-bigger-models option

README.md

@@ -343,6 +343,12 @@ python3 videogen --clear-cache
 ## VRAM Management
 
 ```bash
+# Allow models larger than VRAM using system RAM (implies sequential offload)
+python3 videogen --auto --prompt "..." --allow-bigger-models
+
+# Specify offload strategy explicitly
+python3 videogen --auto --prompt "..." --offload_strategy sequential --vram_limit 16
+
 # Limit VRAM usage
 python3 videogen --model wan_14b_t2v --prompt "test" --vram_limit 16
 

SKILL.md

@@ -116,6 +116,22 @@ python3 videogen --remove-cached-model <model_id>
 python3 videogen --clear-cache
 ```
 
+#### VRAM Management
+
+```bash
+# Allow models larger than VRAM using system RAM (implies sequential offload)
+python3 videogen --auto --prompt "..." --allow-bigger-models
+
+# Specify offload strategy explicitly
+python3 videogen --auto --prompt "..." --offload_strategy sequential --vram_limit 16
+
+# Limit VRAM usage
+python3 videogen --model wan_14b_t2v --prompt "..." --vram_limit 16
+
+# Low RAM mode
+python3 videogen --model wan_14b_t2v --prompt "..." --low_ram_mode
+```
+
 ### Auto Mode
 
 Auto mode is the easiest way for AI agents to generate content: