fix: make PhotoMakerV2 more robust by image count check (#970)

Author: akleine

stable-diffusion.cpp

@@ -2660,18 +2660,24 @@ sd_image_t* generate_image_internal(sd_ctx_t* sd_ctx,
                 LOG_WARN("Turn off PhotoMaker");
                 sd_ctx->sd->stacked_id = false;
             } else {
-                id_cond.c_crossattn = sd_ctx->sd->id_encoder(work_ctx, init_img, id_cond.c_crossattn, id_embeds, class_tokens_mask);
-                int64_t t1          = ggml_time_ms();
-                LOG_INFO("Photomaker ID Stacking, taking %" PRId64 " ms", t1 - t0);
-                if (sd_ctx->sd->free_params_immediately) {
-                    sd_ctx->sd->pmid_model->free_params_buffer();
-                }
-                // Encode input prompt without the trigger word for delayed conditioning
-                prompt_text_only = sd_ctx->sd->cond_stage_model->remove_trigger_from_prompt(work_ctx, prompt);
-                // printf("%s || %s \n", prompt.c_str(), prompt_text_only.c_str());
-                prompt = prompt_text_only;  //
-                if (sample_steps < 50) {
-                    LOG_WARN("It's recommended to use >= 50 steps for photo maker!");
+                if (pm_params.id_images_count != id_embeds->ne[1]) {
+                    LOG_WARN("PhotoMaker image count (%d) does NOT match ID embeds (%d). You should run face_detect.py again.", pm_params.id_images_count, id_embeds->ne[1]);
+                    LOG_WARN("Turn off PhotoMaker");
+                    sd_ctx->sd->stacked_id = false;
+                } else {
+                    id_cond.c_crossattn = sd_ctx->sd->id_encoder(work_ctx, init_img, id_cond.c_crossattn, id_embeds, class_tokens_mask);
+                    int64_t t1          = ggml_time_ms();
+                    LOG_INFO("Photomaker ID Stacking, taking %" PRId64 " ms", t1 - t0);
+                    if (sd_ctx->sd->free_params_immediately) {
+                        sd_ctx->sd->pmid_model->free_params_buffer();
+                    }
+                    // Encode input prompt without the trigger word for delayed conditioning
+                    prompt_text_only = sd_ctx->sd->cond_stage_model->remove_trigger_from_prompt(work_ctx, prompt);
+                    // printf("%s || %s \n", prompt.c_str(), prompt_text_only.c_str());
+                    prompt = prompt_text_only;  //
+                    if (sample_steps < 50) {
+                        LOG_WARN("It's recommended to use >= 50 steps for photo maker!");
+                    }
                 }
             }
         } else {