standardize around sd-1.5-ggml since it's smaller

Signed-off-by: mudler <mudler@localai.io>

README.md

@@ -60,7 +60,7 @@ MODEL_NAME=gemma-3-12b-it docker compose up
 # NVIDIA GPU setup with custom multimodal and image models
 MODEL_NAME=gemma-3-12b-it \
 MULTIMODAL_MODEL=minicpm-v-2_6 \
-IMAGE_MODEL=flux.1-dev \
+IMAGE_MODEL=flux.1-dev-ggml \
 docker compose -f docker-compose.nvidia.yaml up
 ```
 
@@ -116,7 +116,7 @@ LocalAGI supports multiple hardware configurations through Docker Compose profil
 - Default models:
   - Text: `arcee-agent`
   - Multimodal: `minicpm-v-2_6`
-  - Image: `flux.1-dev`
+  - Image: `sd-1.5-ggml`
 - Environment variables:
   - `MODEL_NAME`: Text model to use
   - `MULTIMODAL_MODEL`: Multimodal model to use
@@ -150,7 +150,7 @@ MODEL_NAME=gemma-3-12b-it docker compose up
 # NVIDIA GPU with custom models
 MODEL_NAME=gemma-3-12b-it \
 MULTIMODAL_MODEL=minicpm-v-2_6 \
-IMAGE_MODEL=flux.1-dev \
+IMAGE_MODEL=flux.1-dev-ggml \
 docker compose -f docker-compose.nvidia.yaml up
 
 # Intel GPU with custom models
@@ -163,7 +163,7 @@ docker compose -f docker-compose.intel.yaml up
 If no models are specified, it will use the defaults:
 - Text model: `arcee-agent`
 - Multimodal model: `minicpm-v-2_6`
-- Image model: `flux.1-dev` (NVIDIA) or `sd-1.5-ggml` (Intel)
+- Image model: `sd-1.5-ggml`
 
 Good (relatively small) models that have been tested are:
 

docker-compose.intel.yaml

@@ -11,11 +11,6 @@ services:
       # On a system with integrated GPU and an Arc 770, this is the Arc 770
       - /dev/dri/card1
       - /dev/dri/renderD129
-    command: 
-    - ${MODEL_NAME:-arcee-agent}
-    - ${MULTIMODAL_MODEL:-minicpm-v-2_6}
-    - ${IMAGE_MODEL:-sd-1.5-ggml}
-    - granite-embedding-107m-multilingual
 
   localrecall:
     extends:

docker-compose.nvidia.yaml

@@ -6,7 +6,9 @@ services:
     environment:
       - LOCALAI_SINGLE_ACTIVE_BACKEND=true
       - DEBUG=true
-    image: localai/localai:master-sycl-f32-ffmpeg-core
+    image: localai/localai:master-cublas-cuda12-ffmpeg-core
+    # For images with python backends, use:
+    # image: localai/localai:master-cublas-cuda12-ffmpeg
     deploy:
       resources:
         reservations:

docker-compose.yaml

@@ -9,7 +9,7 @@ services:
     command: 
     - ${MODEL_NAME:-arcee-agent}
     - ${MULTIMODAL_MODEL:-minicpm-v-2_6}
-    - ${IMAGE_MODEL:-flux.1-dev}
+    - ${IMAGE_MODEL:-sd-1.5-ggml}
     - granite-embedding-107m-multilingual
     healthcheck:
       test: ["CMD", "curl", "-f", "http://localhost:8080/readyz"]