stable diffusion framework desktop notes

active/device_framework_desktop/framework_desktop.md

@@ -32,7 +32,7 @@ git clone https://github.com/ggml-org/llama.cpp.git
 export BUILD_TAG=$(date +"%Y-%m-%d-%H-%M-%S")
 docker build -t llama-cpp-vulkan:${BUILD_TAG} -f .devops/vulkan.Dockerfile .
 
-# Run llama server
+# Run llama server with gpt-oss-120b
 docker run \
 -d \
 --restart always \
@@ -45,6 +45,20 @@ llama-cpp-vulkan:${BUILD_TAG} \
 -hf ggml-org/gpt-oss-120b-GGUF  --ctx-size 0 --jinja -ub 2048 -b 2048 \
 --port 8000 --host 0.0.0.0 -n -1 --n-gpu-layers 999
 
+# Run llama server with devstral-small-2 24b
+docker run \
+-d \
+--restart always \
+--name=llama-server-devstral \
+--network=host \
+--device=/dev/kfd \
+--device=/dev/dri \
+-v llama-server-cache:/root/.cache \
+llama-cpp-vulkan:${BUILD_TAG} \
+-hf bartowski/mistralai_Devstral-Small-2-24B-Instruct-2512-GGUF \
+--ctx-size 0 --jinja -ub 2048 -b 2048 \
+--port 8001 --host 0.0.0.0 -n -1 --n-gpu-layers 999
+
 # Firewall
 firewall-cmd --add-port=8000/tcp --permanent
 firewall-cmd --reload
@@ -83,6 +97,14 @@ Per [the docs](https://docs.anythingllm.com/installation-docker/cloud-docker):
 > use sandboxed Chromium across all runtimes for best security practices
 
 ```bash
+mkdir /etc/anything-llm
+touch /etc/anything-llm/.env
+chown 1000:1000 /etc/anything-llm/.env
+chmod 600 /etc/anything-llm/.env
+
+# Add JWT_SECRET=<random string> to this file
+vim /etc/anything-llm/.env
+
 # Server will be accessible on port 3001
 # Connect llama.cpp as a generic OpenAI LLM provider and use host
 # http://172.17.0.1:8000/v1
@@ -94,6 +116,7 @@ docker run \
 --name anythingllm \
 --cap-add SYS_ADMIN \
 -v anythingllm:/app/server/storage \
+-v /etc/anything-llm/.env:/app/server/.env \
 -e STORAGE_DIR="/app/server/storage" \
 docker.io/mintplexlabs/anythingllm
 
@@ -101,3 +124,43 @@ docker.io/mintplexlabs/anythingllm
 firewall-cmd --add-port=3001/tcp --permanent
 firewall-cmd --reload
 ```
+
+## Stable Diffusion CPP
+
+```bash
+# z-turbo
+docker run --rm \
+-v ./models:/models \
+-v ./build:/output \
+--device /dev/kfd \
+--device /dev/dri \
+ghcr.io/leejet/stable-diffusion.cpp:master-vulkan \
+--diffusion-model /models/z_turbo/z_image_turbo_bf16.safetensors \
+--vae /models/z_turbo/ae.safetensors  \
+--llm /models/z_turbo/qwen_3_4b.safetensors \
+--cfg-scale 1.0 \
+-v \
+--diffusion-fa \
+-H 1024 \
+-W 512 \
+-o /output/output.png \
+--seed -1 \
+-p "Framework Laptop 13"
+
+# Flux2
+docker run --rm \
+-v ./models:/models \
+-v ./build:/output \
+--device /dev/kfd \
+--device /dev/dri \
+ghcr.io/leejet/stable-diffusion.cpp:master-vulkan \
+--diffusion-model  /models/flux2/flux2-dev-Q8_0.gguf \
+--vae /models/flux2/ae.safetensors \
+--llm /models/flux2/Mistral-Small-3.2-24B-Instruct-2506-Q8_0.gguf \
+--cfg-scale 1.0 \
+--sampling-method euler \
+-v \
+--diffusion-fa \
+-o /output/output.png \
+-p "A picture of sign that says 'framework'"
+```