fix: reject video models in image generation (#2017)

docs/troubleshooting.md

@@ -1,5 +1,14 @@
 # Troubleshooting
 
+## Video model used in image generation mode
+
+If generation reports that a model cannot be run with `generate_image()`, add
+`--mode vid_gen` to the CLI command. `--video-frames` alone does not select video
+mode. Video models require this mode even when generating a single frame.
+Library callers must use `generate_video()` for these models; use
+`sd_ctx_supports_image_generation()` and `sd_ctx_supports_video_generation()` to
+check the available generation modes.
+
 ## Completely black or white images or videos / NaNs
 
 Some ggml backends can encounter numerical overflow during inference, producing

docs/wan.md

@@ -1,5 +1,7 @@
 # How to Use
 
+Wan models require `-M vid_gen`, including single-frame generation. `--video-frames` alone does not select video mode. Library callers must use `generate_video()` instead of `generate_image()`.
+
 ## Download weights
 
 - Download Wan

src/model.h

@@ -252,6 +252,14 @@ static inline bool sd_version_is_sensenova_u1(SDVersion version) {
     return version == VERSION_SENSENOVA_U1_5;
 }
 
+static inline bool sd_version_supports_video_generation(SDVersion version) {
+    return version == VERSION_SVD || sd_version_is_wan(version) || sd_version_is_hunyuan_video(version) || sd_version_is_lingbot_video(version) || sd_version_is_ltxav(version) || sd_version_is_minimax_h3(version);
+}
+
+static inline bool sd_version_supports_image_generation(SDVersion version) {
+    return !sd_version_supports_video_generation(version);
+}
+
 static inline bool sd_version_uses_flux_vae(SDVersion version) {
     if (sd_version_is_flux(version) || sd_version_is_z_image(version) || sd_version_is_boogu_image(version) || sd_version_is_longcat(version)) {
         return true;

src/pipeline/image.cpp

@@ -789,15 +789,9 @@ namespace sd::pipeline {
             return false;
         }
 
-        // MiniMax-H3 is video-only. Its denoiser always splits the packed latent into a video and an
+        if (!sd_version_supports_image_generation(sd->version)) {
-        // audio half, and only generate_video ever computes the audio length, so reaching this
+            LOG_ERROR("%s cannot be run with generate_image(); use generate_video() or --mode vid_gen in the CLI",
-        // function with an H3 checkpoint is guaranteed to die on
+                      model_version_to_str[sd->version]);
-        // GGML_ASSERT(!audio_input_cache.empty()) with a core dump, after the several minutes it
-        // takes to load the weights, and with nothing in the output pointing at the missing --mode.
-        // (The AnimateDiff path below routes vid_gen back through here, but that is SD1.5 plus a
-        // motion module, never H3.)
-        if (sd_version_is_minimax_h3(sd->version)) {
-            LOG_ERROR("MiniMax-H3 is a video model and cannot be run in img_gen mode; use --mode vid_gen");
             return false;
         }
 

src/stable-diffusion.cpp

@@ -630,14 +630,6 @@ struct sd_ctx_t {
     StableDiffusionGGML* sd = nullptr;
 };
 
-static bool sd_version_supports_video_generation(SDVersion version) {
-    return version == VERSION_SVD || sd_version_is_wan(version) || sd_version_is_hunyuan_video(version) || sd_version_is_lingbot_video(version) || sd_version_is_ltxav(version) || sd_version_is_minimax_h3(version);
-}
-
-static bool sd_version_supports_image_generation(SDVersion version) {
-    return !sd_version_supports_video_generation(version);
-}
-
 sd_ctx_t* new_sd_ctx(const sd_ctx_params_t* sd_ctx_params) {
     sd_ctx_t* sd_ctx = (sd_ctx_t*)malloc(sizeof(sd_ctx_t));
     if (sd_ctx == nullptr) {