Add files using upload-large-folder tool

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer/tokenizer.json filter=lfs diff=lfs merge=lfs -text

NOTICE

@@ -0,0 +1,14 @@
+This model is a fine-tuned derivative ("Derivative Model") of Krea 2
+(krea/Krea-2-Turbo and krea/Krea-2-Raw by Krea.ai, Inc.), created by fusing the
+community adapter conradlocke/krea2-identity-edit (v1.2, SVD rank-64 variant) into
+the base weights. It is an unofficial community build, not affiliated with or
+endorsed by Krea.ai, Inc. or the adapter's author.
+
+Distributed under the Krea 2 Community License Agreement (see LICENSE.pdf /
+https://krea.ai/krea-2-licensing). By downloading or using it you agree to be bound
+by that Agreement, including its restrictions on prohibited uses, the
+content-filtering requirements for deployments, and the commercial use terms.
+
+Credits: Krea.ai, Inc. (base model) - conradlocke (identity-edit adapter training,
+https://huggingface.co/conradlocke/krea2-identity-edit) - face/head/person-swap
+skill trained on stablellama's MIT-licensed change_eye_face_head_person dataset.

README.md

@@ -0,0 +1,24 @@
+---
+license: other
+license_name: krea-2-community-license
+license_link: https://krea.ai/krea-2-licensing
+base_model: krea/Krea-2-Turbo
+tags:
+- image-editing
+- identity-edit
+- mlx
+- krea-2
+- onyx
+---
+
+# Onyx Krea 2 Edit (Turbo, 4-bit MLX, identity-edit fused)
+
+MLX 4-bit build of Krea 2 with the [krea2-identity-edit](https://huggingface.co/conradlocke/krea2-identity-edit)
+adapter (v1.2 r64) **fused into the weights** - zero runtime LoRA cost, streams like a
+plain checkpoint. Built for the Onyx on-device app: attach a reference photo (plus an
+optional second for swaps/try-on) and describe the change.
+
+Distilled 8-step base: fast, instruction-faithful - the recommended edit build.
+
+See NOTICE for attribution and LICENSE.pdf for the Krea 2 Community License this
+model is distributed under.

model_index.json

@@ -0,0 +1,40 @@
+{
+  "_class_name": "Krea2Pipeline",
+  "_diffusers_version": "0.39.0.dev0",
+  "scheduler": [
+    "diffusers",
+    "FlowMatchEulerDiscreteScheduler"
+  ],
+  "text_encoder": [
+    "transformers",
+    "Qwen3VLModel"
+  ],
+  "text_encoder_select_layers": [
+    2,
+    5,
+    8,
+    11,
+    14,
+    17,
+    20,
+    23,
+    26,
+    29,
+    32,
+    35
+  ],
+  "tokenizer": [
+    "transformers",
+    "Qwen2Tokenizer"
+  ],
+  "transformer": [
+    "diffusers",
+    "Krea2Transformer2DModel"
+  ],
+  "vae": [
+    "diffusers",
+    "AutoencoderKLQwenImage"
+  ],
+  "is_distilled": true,
+  "patch_size": 2
+}

scheduler/scheduler_config.json

@@ -0,0 +1,18 @@
+{
+  "_class_name": "FlowMatchEulerDiscreteScheduler",
+  "_diffusers_version": "0.39.0.dev0",
+  "base_image_seq_len": 256,
+  "base_shift": 0.5,
+  "invert_sigmas": false,
+  "max_image_seq_len": 6400,
+  "max_shift": 1.15,
+  "num_train_timesteps": 1000,
+  "shift": 1.0,
+  "shift_terminal": null,
+  "stochastic_sampling": false,
+  "time_shift_type": "exponential",
+  "use_beta_sigmas": false,
+  "use_dynamic_shifting": true,
+  "use_exponential_sigmas": false,
+  "use_karras_sigmas": false
+}

text_encoder/config.json

@@ -0,0 +1,70 @@
+{
+  "transformers_version" : "5.2.0",
+  "model_type" : "qwen3_vl",
+  "vision_end_token_id" : 151653,
+  "video_token_id" : 151656,
+  "dtype" : "bfloat16",
+  "quantization" : {
+    "bits" : 4,
+    "group_size" : 64
+  },
+  "architectures" : [
+    "Qwen3VLModel"
+  ],
+  "vision_start_token_id" : 151652,
+  "text_config" : {
+    "hidden_size" : 2560,
+    "model_type" : "qwen3_vl_text",
+    "rope_parameters" : {
+      "mrope_section" : [
+        24,
+        20,
+        20
+      ],
+      "rope_theta" : 5000000,
+      "mrope_interleaved" : true,
+      "rope_type" : "default"
+    },
+    "use_cache" : true,
+    "dtype" : "bfloat16",
+    "eos_token_id" : 151645,
+    "bos_token_id" : 151643,
+    "vocab_size" : 151936,
+    "num_hidden_layers" : 36,
+    "num_key_value_heads" : 8,
+    "tie_word_embeddings" : true,
+    "initializer_range" : 0.02,
+    "rms_norm_eps" : 9.9999999999999995e-07,
+    "head_dim" : 128,
+    "attention_dropout" : 0,
+    "max_position_embeddings" : 262144,
+    "num_attention_heads" : 32,
+    "pad_token_id" : null,
+    "intermediate_size" : 9728,
+    "hidden_act" : "silu",
+    "attention_bias" : false
+  },
+  "image_token_id" : 151655,
+  "vision_config" : {
+    "num_heads" : 16,
+    "hidden_size" : 1024,
+    "out_hidden_size" : 2560,
+    "initializer_range" : 0.02,
+    "hidden_act" : "gelu_pytorch_tanh",
+    "deepstack_visual_indexes" : [
+      5,
+      11,
+      17
+    ],
+    "dtype" : "bfloat16",
+    "patch_size" : 16,
+    "intermediate_size" : 4096,
+    "temporal_patch_size" : 2,
+    "num_position_embeddings" : 2304,
+    "depth" : 24,
+    "in_channels" : 3,
+    "spatial_merge_size" : 2,
+    "model_type" : "qwen3_vl"
+  },
+  "tie_word_embeddings" : true
+}

text_encoder/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9febb58bef0d8417926daff88996ee43fd5124d555365f711e3601c3f7116c0a
+size 2822141221

tokenizer/chat_template.jinja

@@ -0,0 +1,120 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {%- if messages[0].content is string %}
+            {{- messages[0].content }}
+        {%- else %}
+            {%- for content in messages[0].content %}
+                {%- if 'text' in content %}
+                    {{- content.text }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        {{- '\n\n' }}
+    {%- endif %}
+    {{- "# 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>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\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" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' }}
+        {%- if messages[0].content is string %}
+            {{- messages[0].content }}
+        {%- else %}
+            {%- for content in messages[0].content %}
+                {%- if 'text' in content %}
+                    {{- content.text }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set image_count = namespace(value=0) %}
+{%- set video_count = namespace(value=0) %}
+{%- for message in messages %}
+    {%- if message.role == "user" %}
+        {{- '<|im_start|>' + message.role + '\n' }}
+        {%- if message.content is string %}
+            {{- message.content }}
+        {%- else %}
+            {%- for content in message.content %}
+                {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}
+                    {%- set image_count.value = image_count.value + 1 %}
+                    {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
+                    <|vision_start|><|image_pad|><|vision_end|>
+                {%- elif content.type == 'video' or 'video' in content %}
+                    {%- set video_count.value = video_count.value + 1 %}
+                    {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
+                    <|vision_start|><|video_pad|><|vision_end|>
+                {%- elif 'text' in content %}
+                    {{- content.text }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role + '\n' }}
+        {%- if message.content is string %}
+            {{- message.content }}
+        {%- else %}
+            {%- for content_item in message.content %}
+                {%- if 'text' in content_item %}
+                    {{- content_item.text }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and message.content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {%- if message.content is string %}
+            {{- message.content }}
+        {%- else %}
+            {%- for content in message.content %}
+                {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}
+                    {%- set image_count.value = image_count.value + 1 %}
+                    {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
+                    <|vision_start|><|image_pad|><|vision_end|>
+                {%- elif content.type == 'video' or 'video' in content %}
+                    {%- set video_count.value = video_count.value + 1 %}
+                    {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
+                    <|vision_start|><|video_pad|><|vision_end|>
+                {%- elif 'text' in content %}
+                    {{- content.text }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+{%- endif %}

tokenizer/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be75606093db2094d7cd20f3c2f385c212750648bd6ea4fb2bf507a6a4c55506
+size 11422650

tokenizer/tokenizer_config.json

@@ -0,0 +1,29 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "is_local": true,
+  "model_max_length": 262144,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

transformer/config.json

@@ -0,0 +1,29 @@
+{
+  "num_refiner_text_blocks" : 2,
+  "text_num_attention_heads" : 20,
+  "num_layers" : 28,
+  "text_intermediate_size" : 6912,
+  "timestep_embed_dim" : 256,
+  "_diffusers_version" : "0.39.0.dev0",
+  "norm_eps" : 1.0000000000000001e-05,
+  "quantization" : {
+    "bits" : 4,
+    "group_size" : 64
+  },
+  "num_text_layers" : 12,
+  "in_channels" : 64,
+  "attention_head_dim" : 128,
+  "rope_theta" : 1000,
+  "text_num_key_value_heads" : 20,
+  "num_layerwise_text_blocks" : 2,
+  "num_attention_heads" : 48,
+  "_class_name" : "Krea2Transformer2DModel",
+  "num_key_value_heads" : 12,
+  "intermediate_size" : 16384,
+  "axes_dims_rope" : [
+    32,
+    48,
+    48
+  ],
+  "text_hidden_dim" : 2560
+}

transformer/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b881269d519affa958adb934d7ef52b1a4abfef59d2745ac36f953c82be00884
+size 7213547199

vae/config.json

@@ -0,0 +1,58 @@
+{
+  "_class_name": "AutoencoderKLQwenImage",
+  "_diffusers_version": "0.39.0.dev0",
+  "_name_or_path": "Qwen/Qwen-Image",
+  "attn_scales": [],
+  "base_dim": 96,
+  "dim_mult": [
+    1,
+    2,
+    4,
+    4
+  ],
+  "dropout": 0.0,
+  "input_channels": 3,
+  "latents_mean": [
+    -0.7571,
+    -0.7089,
+    -0.9113,
+    0.1075,
+    -0.1745,
+    0.9653,
+    -0.1517,
+    1.5508,
+    0.4134,
+    -0.0715,
+    0.5517,
+    -0.3632,
+    -0.1922,
+    -0.9497,
+    0.2503,
+    -0.2921
+  ],
+  "latents_std": [
+    2.8184,
+    1.4541,
+    2.3275,
+    2.6558,
+    1.2196,
+    1.7708,
+    2.6052,
+    2.0743,
+    3.2687,
+    2.1526,
+    2.8652,
+    1.5579,
+    1.6382,
+    1.1253,
+    2.8251,
+    1.916
+  ],
+  "num_res_blocks": 2,
+  "temperal_downsample": [
+    false,
+    true,
+    true
+  ],
+  "z_dim": 16
+}

vae/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e87baefc88a80d8b02a9a89f6a02b857da1a5a9f1cc284d237fe5fded8c3b2d
+size 253806728