Add files using upload-large-folder tool

.gitattributes

@@ -40,3 +40,6 @@ txt_in.mnn.weight filter=lfs diff=lfs merge=lfs -text
 vae_decoder.mnn filter=lfs diff=lfs merge=lfs -text
 text_encoder/llm.mnn.weight filter=lfs diff=lfs merge=lfs -text
 dit.mnn.weight filter=lfs diff=lfs merge=lfs -text
+text_encoder/visual.mnn filter=lfs diff=lfs merge=lfs -text
+vae_encoder.mnn filter=lfs diff=lfs merge=lfs -text
+text_encoder/visual.mnn.weight filter=lfs diff=lfs merge=lfs -text

README.md

@@ -18,7 +18,8 @@ tags:
 # Qwen-Image-2.1 · MNN (int4) for Android
 
 [Qwen/Qwen-Image-2.1](https://huggingface.co/Qwen/Qwen-Image-2.1) converted to [MNN](https://github.com/alibaba/MNN)
-for on-device text-to-image at 512×512 on Android (OpenCL GPU for the DiT).
+for on-device **text-to-image and image editing** on Android at about 512×512 pixels (any aspect ratio with sides that
+are multiples of 32, e.g. 512×512, 576×448, 608×416, 672×384), with the OpenCL GPU running the DiT.
 
 Runtime, Android library and demo app: **[github.com/scsonic/libQwenImage21](https://github.com/scsonic/libQwenImage21)**
 
@@ -31,9 +32,10 @@ Runtime, Android library and demo app: **[github.com/scsonic/libQwenImage21](htt
 | Path | What | Size |
 |---|---|---|
 | `dit.mnn` + `.weight` | 7B single-stream DiT (32 blocks + norm_out/proj_out). Block linears int4 (block 32), small layers int8 | 4.5 GB |
-| `txt_in.mnn`, `img_in.mnn` | text / latent input projections (int8) | 36 MB |
-| `vae_decoder.mnn` | VAE decoder, 64-ch latent → RGBA, fp16 weights | 0.5 GB |
-| `text_encoder/` | Qwen3-VL-8B-Instruct, MNN int4 (from [taobao-mnn/Qwen3-VL-8B-Instruct-MNN](https://huggingface.co/taobao-mnn/Qwen3-VL-8B-Instruct-MNN)); `te_config.json` runs it text-only and returns the last decoder layer before the final norm | 5.1 GB |
+| `txt_in.mnn`, `img_in.mnn` | text (int8) / latent (fp16) input projections | 36 MB |
+| `vae_decoder.mnn` | VAE decoder, 64-ch latent → RGBA, fp16 weights, dynamic size | 0.5 GB |
+| `vae_encoder.mnn` | VAE encoder for image editing, RGBA → normalized 64-ch latent, fp16 | 0.16 GB |
+| `text_encoder/` | Qwen3-VL-8B-Instruct, MNN int4 (from [taobao-mnn/Qwen3-VL-8B-Instruct-MNN](https://huggingface.co/taobao-mnn/Qwen3-VL-8B-Instruct-MNN)). `te_config.json` runs it text-only; `te_vl_config.json` adds the vision tower (`visual.mnn`) for image editing. Both return the last decoder layer before the final norm | 5.4 GB |
 
 Download:
 

img_in.mnn.weight

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:150a49438c182cc5c1307b218eb6d5b30895930a33d3deeed385849ea105e79a
-size 278790
+oid sha256:84ceb8c9ab500f646909606af4ff2a0e8d8deb2f14455f49b2f84e2e50201492
+size 524288

text_encoder/te_vl_config.json

@@ -0,0 +1,18 @@
+{
+  "llm_model": "llm.mnn",
+  "llm_weight": "llm.mnn.weight",
+  "embedding_file": "embeddings_int4.bin",
+  "visual_model": "visual.mnn",
+  "llm_config": "te_vl_llm_config.json",
+  "backend_type": "cpu",
+  "thread_num": 4,
+  "precision": "low",
+  "memory": "low",
+  "use_template": false,
+  "mllm": {
+    "backend_type": "cpu",
+    "thread_num": 4,
+    "precision": "normal",
+    "memory": "low"
+  }
+}

text_encoder/te_vl_llm_config.json

@@ -0,0 +1,47 @@
+{
+  "hidden_size": 4096,
+  "layer_nums": 36,
+  "attention_mask": "float",
+  "key_value_shape": [
+    2,
+    1,
+    0,
+    8,
+    128
+  ],
+  "bos": "",
+  "system_prompt_template": "<|im_start|>system\n%s<|im_end|>\n",
+  "user_prompt_template": "<|im_start|>user\n%s<|im_end|>\n",
+  "assistant_prompt_template": "<|im_start|>assistant\n%s<|im_end|>\n",
+  "is_visual": true,
+  "attention_type": "full",
+  "jinja": {
+    "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0].role == 'system' %}\n        {%- if messages[0].content is string %}\n            {{- messages[0].content }}\n        {%- else %}\n            {%- for content in messages[0].content %}\n                {%- if 'text' in content %}\n                    {{- content.text }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {{- '\\n\\n' }}\n    {%- endif %}\n    {{- \"# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0].role == 'system' %}\n        {{- '<|im_start|>system\\n' }}\n        {%- if messages[0].content is string %}\n            {{- messages[0].content }}\n        {%- else %}\n            {%- for content in messages[0].content %}\n                {%- if 'text' in content %}\n                    {{- content.text }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- set image_count = namespace(value=0) %}\n{%- set video_count = namespace(value=0) %}\n{%- for message in messages %}\n    {%- if message.role == \"user\" %}\n        {{- '<|im_start|>' + message.role + '\\n' }}\n        {%- if message.content is string %}\n            {{- message.content }}\n        {%- else %}\n            {%- for content in message.content %}\n                {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}\n                    {%- set image_count.value = image_count.value + 1 %}\n                    {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}\n                    <|vision_start|><|image_pad|><|vision_end|>\n                {%- elif content.type == 'video' or 'video' in content %}\n                    {%- set video_count.value = video_count.value + 1 %}\n                    {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}\n                    <|vision_start|><|video_pad|><|vision_end|>\n                {%- elif 'text' in content %}\n                    {{- content.text }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role + '\\n' }}\n        {%- if message.content is string %}\n            {{- message.content }}\n        {%- else %}\n            {%- for content_item in message.content %}\n                {%- if 'text' in content_item %}\n                    {{- content_item.text }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {%- if message.tool_calls %}\n            {%- for tool_call in message.tool_calls %}\n                {%- if (loop.first and message.content) or (not loop.first) %}\n                    {{- '\\n' }}\n                {%- endif %}\n                {%- if tool_call.function %}\n                    {%- set tool_call = tool_call.function %}\n                {%- endif %}\n                {{- '<tool_call>\\n{\"name\": \"' }}\n                {{- tool_call.name }}\n                {{- '\", \"arguments\": ' }}\n                {%- if tool_call.arguments is string %}\n                    {{- tool_call.arguments }}\n                {%- else %}\n                    {{- tool_call.arguments | tojson }}\n                {%- endif %}\n                {{- '}\\n</tool_call>' }}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {%- if message.content is string %}\n            {{- message.content }}\n        {%- else %}\n            {%- for content in message.content %}\n                {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}\n                    {%- set image_count.value = image_count.value + 1 %}\n                    {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}\n                    <|vision_start|><|image_pad|><|vision_end|>\n                {%- elif content.type == 'video' or 'video' in content %}\n                    {%- set video_count.value = video_count.value + 1 %}\n                    {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}\n                    <|vision_start|><|video_pad|><|vision_end|>\n                {%- elif 'text' in content %}\n                    {{- content.text }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+    "eos": "<|im_end|>"
+  },
+  "image_mean": [
+    127.5,
+    127.5,
+    127.5
+  ],
+  "image_norm": [
+    0.00784313725490196,
+    0.00784313725490196,
+    0.00784313725490196
+  ],
+  "image_size": 420,
+  "vision_start": 151652,
+  "vision_end": 151653,
+  "image_pad": 151655,
+  "num_grid_per_side": 48,
+  "has_deepstack": true,
+  "tie_embeddings": [
+    0,
+    311164928,
+    77791232,
+    4,
+    64
+  ],
+  "hidden_states": true,
+  "hidden_states_output": "/Add_182_output_0"
+}

text_encoder/visual.mnn

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f1653348a94c29e56d47529dd461215c80d5380263136adee7945809f407bf7
+size 562048

text_encoder/visual.mnn.weight

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d8b1a4886cca9ab8b8c86979f4e5291e126ac930124e9a2361833e7b11301e6
+size 326728744

vae_decoder.mnn

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b98440baff5ffa77c0c3e59b1337f92f6c818d6a57fc9f765636705d33b08a4
+oid sha256:2525485bba44d4d8176d05522fa7e8b4b1080c9e7b7df18dfde7d58e667ff055
 size 506595396

vae_encoder.mnn

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a131ea3a9c822a62842c17ddf0526685d5d8cd842ed13d5500112121df770248
+size 156215404