switch image model to FLUX.2-klein-4B (Apache 2.0, 4-step, unified gen+edit)

ansible/roles/openwrt/tasks/network.yml

@@ -75,7 +75,6 @@
         option device 'eth0.1'
         option proto 'static'
         option ipaddr '{{ openwrt_mgmt_ip }}/{{ openwrt_mgmt_prefix }}'
-        option dns '{{ openwrt_dns_servers | join(" ") }}'
 
       # Policy routing for mgmt interface.
       #

apps/llama/configs/config.yaml

@@ -25,7 +25,7 @@ hooks:
 matrix:
   vars:
     q8: "Qwen3.5-0.8B-GGUF-nothink:Q4_K_XL"
-    flux: "flux1-dev:Q4_K_S"
+    flux: "flux2-klein-4b:Q4_K_M"
     coder: "Qwen3-Coder-Next-GGUF:Q4_K_M"
     q35t: "Qwen3.5-35B-A3B-GGUF:Q4_K_M"
     q35nt: "Qwen3.5-35B-A3B-GGUF-nothink:Q4_K_M"
@@ -234,19 +234,20 @@ models:
 
   # Image generation via stable-diffusion.cpp (sd-server)
   # Models must be pre-downloaded to /root/.cache/sd/
-  # FLUX.1-dev: state-of-the-art open-weight text-to-image model by Black Forest Labs
+  # FLUX.2-klein-4B: fast unified text-to-image and image editing model (Apache 2.0)
-  # Download: huggingface-cli download lllyasviel/FLUX.1-dev-gguf flux1-dev-Q4_K_S.gguf --local-dir /root/.cache/sd
+  # Download: uv run --with huggingface_hub hf download unsloth/FLUX.2-klein-4B-GGUF flux-2-klein-4b-Q4_K_M.gguf --local-dir /root/.cache/sd
-  # Download VAE: huggingface-cli download black-forest-labs/FLUX.1-dev ae.safetensors --local-dir /root/.cache/sd
+  # Download VAE: uv run --with huggingface_hub hf download Comfy-Org/flux2-klein-4B split_files/vae/flux2-vae.safetensors --local-dir /root/.cache/sd/flux2-klein && cp /root/.cache/sd/flux2-klein/split_files/vae/flux2-vae.safetensors /root/.cache/sd/
-  # Download text encoders: huggingface-cli download comfyanonymous/flux_text_encoders clip_l.safetensors t5xxl_fp16.safetensors --local-dir /root/.cache/sd
+  # Download LLM: uv run --with huggingface_hub hf download unsloth/Qwen3-4B-GGUF Qwen3-4B-Q4_K_M.gguf --local-dir /root/.cache/sd
-  "flux1-dev:Q4_K_S":
+  "flux2-klein-4b:Q4_K_M":
     checkEndpoint: "/"
     cmd: |
       sd-server
         --listen-port ${PORT}
-        --diffusion-model /root/.cache/sd/flux1-dev-Q4_K_S.gguf
+        --diffusion-model /root/.cache/sd/flux-2-klein-4b-Q4_K_M.gguf
-        --vae /root/.cache/sd/ae.safetensors
+        --vae /root/.cache/sd/flux2-vae.safetensors
-        --clip_l /root/.cache/sd/clip_l.safetensors
+        --llm /root/.cache/sd/Qwen3-4B-Q4_K_M.gguf
-        --t5xxl /root/.cache/sd/t5xxl_fp16.safetensors
         --cfg-scale 1.0
         --sampling-method euler
-        --steps 20
+        --steps 4
+        --diffusion-fa
+        --offload-to-cpu

apps/llama/configs/qwen_nothink_chat_template.jinja

@@ -1,101 +0,0 @@
-{%- if not add_generation_prompt is defined %}
-    {%- set add_generation_prompt = false %}
-{%- endif %}
-{%- set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='', is_first_sp=true, is_last_user=false) %}
-{%- for message in messages %}
-    {%- if message['role'] == 'system' %}
-        {%- if ns.is_first_sp %}
-            {%- set ns.system_prompt = ns.system_prompt + message['content'] %}
-            {%- set ns.is_first_sp = false %}
-        {%- else %}
-            {%- set ns.system_prompt = ns.system_prompt + '\n\n' + message['content'] %}
-        {%- endif %}
-    {%- endif %}
-{%- endfor %}
-
-{#- Adapted from https://github.com/sgl-project/sglang/blob/main/examples/chat_template/tool_chat_template_deepseekr1.jinja #}
-{%- if tools is defined and tools is not none %}
-    {%- set tool_ns = namespace(text='You are a helpful assistant with tool calling capabilities. ' + 'When a tool call is needed, you MUST use the following format to issue the call:\n' + '<｜tool▁calls▁begin｜><｜tool▁call▁begin｜>function<｜tool▁sep｜>FUNCTION_NAME\n' + '```json\n{"param1": "value1", "param2": "value2"}\n```<｜tool▁call▁end｜><｜tool▁calls▁end｜>\n\n' + 'Make sure the JSON is valid.' + '## Tools\n\n### Function\n\nYou have the following functions available:\n\n') %}
-    {%- for tool in tools %}
-        {%- set tool_ns.text = tool_ns.text + '\n```json\n' + (tool | tojson) + '\n```\n' %}
-    {%- endfor %}
-    {%- if ns.system_prompt|length != 0 %}
-        {%- set ns.system_prompt = ns.system_prompt + '\n\n' + tool_ns.text %}
-    {%- else %}
-        {%- set ns.system_prompt = tool_ns.text %}
-    {%- endif %}
-{%- endif %}
-{{- bos_token }}
-{{- '/no_think' + ns.system_prompt }}
-{%- set last_index = (messages|length - 1) %}
-{%- for message in messages %}
-    {%- set content = message['content'] %}
-    {%- if message['role'] == 'user' %}
-        {%- set ns.is_tool = false -%}
-        {%- set ns.is_first = false -%}
-        {%- set ns.is_last_user = true -%}
-        {%- if loop.index0 == last_index %}
-            {{- '<｜User｜>' + content }}
-        {%- else %}
-            {{- '<｜User｜>' + content + '<｜Assistant｜>'}}
-        {%- endif %}
-    {%- endif %}
-    {%- if message['role'] == 'assistant' %}
-        {%- if '</think>' in content %}
-            {%- set content = (content.split('</think>')|last) %}
-        {%- endif %}
-    {%- endif %}
-    {%- if message['role'] == 'assistant' and message['tool_calls'] is defined and message['tool_calls'] is not none %}
-        {%- set ns.is_last_user = false -%}
-        {%- if ns.is_tool %}
-            {{- '<｜tool▁outputs▁end｜>'}}
-        {%- endif %}
-        {%- set ns.is_first = false %}
-        {%- set ns.is_tool = false -%}
-        {%- set ns.is_output_first = true %}
-        {%- for tool in message['tool_calls'] %}
-            {%- set arguments = tool['function']['arguments'] %}
-            {%- if arguments is not string %}
-                {%- set arguments = arguments|tojson %}
-            {%- endif %}
-            {%- if not ns.is_first %}
-                {%- if content is none %}
-                    {{- '<｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\n' + '```json' + '\n' + arguments + '\n' + '```' + '<｜tool▁call▁end｜>'}}
-                }
-                {%- else %}
-                    {{- content + '<｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\n' + '```json' + '\n' + arguments + '\n' + '```' + '<｜tool▁call▁end｜>'}}
-                {%- endif %}
-                {%- set ns.is_first = true -%}
-            {%- else %}
-                {{- '\n' + '<｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\n' + '```json' + '\n' + arguments + '\n' + '```' + '<｜tool▁call▁end｜>'}}
-            {%- endif %}
-        {%- endfor %}
-        {{- '<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}
-    {%- endif %}
-    {%- if message['role'] == 'assistant' and (message['tool_calls'] is not defined or message['tool_calls'] is none) %}
-        {%- set ns.is_last_user = false -%}
-        {%- if ns.is_tool %}
-            {{- '<｜tool▁outputs▁end｜>' + content + '<｜end▁of▁sentence｜>'}}
-            {%- set ns.is_tool = false -%}
-        {%- else %}
-            {{- content + '<｜end▁of▁sentence｜>'}}
-        {%- endif %}
-    {%- endif %}
-    {%- if message['role'] == 'tool' %}
-        {%- set ns.is_last_user = false -%}
-        {%- set ns.is_tool = true -%}
-        {%- if ns.is_output_first %}
-            {{- '<｜tool▁outputs▁begin｜><｜tool▁output▁begin｜>' + content + '<｜tool▁output▁end｜>'}}
-            {%- set ns.is_output_first = false %}
-        {%- else %}
-            {{- '\n<｜tool▁output▁begin｜>' + content + '<｜tool▁output▁end｜>'}}
-        {%- endif %}
-    {%- endif %}
-{%- endfor -%}
-{%- if ns.is_tool %}
-    {{- '<｜tool▁outputs▁end｜>'}}
-{%- endif %}
-{#- if add_generation_prompt and not ns.is_last_user and not ns.is_tool #}
-{%- if add_generation_prompt and not ns.is_tool %}
-    {{- '<｜Assistant｜>'}}
-{%- endif %}

apps/llama/kustomization.yaml

@@ -12,4 +12,3 @@ configMapGenerator:
     namespace: llama
     files:
       - config.yaml=configs/config.yaml
-      - qwen_nothink_chat_template.jinja=configs/qwen_nothink_chat_template.jinja

apps/openwebui/release.yaml

@@ -84,7 +84,7 @@ spec:
       - name: IMAGES_OPENAI_API_KEY
         value: "ignored"
       - name: IMAGE_GENERATION_MODEL
-        value: "flux1-dev:Q4_K_S"
+        value: "flux2-klein-4b:Q4_K_M"
       - name: IMAGE_SIZE
         value: "512x512"
       # Image editing via llama-swap sd-server (/v1/images/edits)
@@ -97,6 +97,6 @@ spec:
       - name: IMAGES_EDIT_OPENAI_API_KEY
         value: "ignored"
       - name: IMAGE_EDIT_MODEL
-        value: "flux1-dev:Q4_K_S"
+        value: "flux2-klein-4b:Q4_K_M"
       - name: IMAGE_EDIT_SIZE
         value: "512x512"