fix: Add vllm-omni backend to video generation model detection (mudler#8659) (mudler#8781)

fix: Add vllm-omni backend to video generation model detection

- Include vllm-omni in the list of backends that support FLAG_VIDEO
- This allows models like vllm-omni-wan2.2-t2v to appear in the video model selector UI
- Fixes issue mudler#8659 where video generation models using vllm-omni backend were not showing in the dropdown

Co-authored-by: team-coding-agent-1 <team-coding-agent-1@localai.dev>

Author: localai-bot

core/config/model_config.go

@@ -641,7 +641,7 @@ func (c *ModelConfig) GuessUsecases(u ModelConfigUsecase) bool {
 
 	}
 	if (u & FLAG_VIDEO) == FLAG_VIDEO {
-		videoBackends := []string{"diffusers", "stablediffusion"}
+		videoBackends := []string{"diffusers", "stablediffusion", "vllm-omni"}
 		if !slices.Contains(videoBackends, c.Backend) {
 			return false
 		}