diff --git a/stable-diffusion.cpp b/stable-diffusion.cpp
index 2cb588213..a0217942c 100644
--- a/stable-diffusion.cpp
+++ b/stable-diffusion.cpp
@@ -1484,6 +1484,17 @@ class StableDiffusionGGML {
         std::vector<int> skip_layers(guidance.slg.layers, guidance.slg.layers + guidance.slg.layer_count);
 
         float cfg_scale     = guidance.txt_cfg;
+        if (cfg_scale < 1.f) {
+            if (cfg_scale == 0.f) {
+                // Diffusers follow the convention from the original paper
+                // (https://arxiv.org/abs/2207.12598v1), so many distilled model docs
+                // recommend 0 as guidance; warn the user that it'll disable prompt folowing
+                LOG_WARN("unconditioned mode, images won't follow the prompt (use cfg-scale=1 for distilled models)");
+            } else {
+                LOG_WARN("cfg value out of expected range may produce unexpected results");
+            }
+        }
+
         float img_cfg_scale = std::isfinite(guidance.img_cfg) ? guidance.img_cfg : guidance.txt_cfg;
         float slg_scale     = guidance.slg.scale;
 
@@ -3875,4 +3886,4 @@ SD_API sd_image_t* generate_video(sd_ctx_t* sd_ctx, const sd_vid_gen_params_t* s
     LOG_INFO("generate_video completed in %.2fs", (t5 - t0) * 1.0f / 1000);
 
     return result_images;
-}
\ No newline at end of file
+}