Upload 10 files

.gitattributes

@@ -34,3 +34,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 LICENSE.pdf filter=lfs diff=lfs merge=lfs -text
+tokenizer/tokenizer.json filter=lfs diff=lfs merge=lfs -text

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 +1,682 @@
+{
+  "architectures": [
+    "Qwen3VLModel"
+  ],
+  "dtype": "bfloat16",
+  "image_token_id": 151655,
+  "model_type": "qwen3_vl",
+  "quantization_config": {
+    "add_skip_keys": true,
+    "dequantize_fp32": false,
+    "dynamic_loss_threshold": 0.01,
+    "group_size": 0,
+    "hadamard_group_size": 256,
+    "is_integer": true,
+    "is_training": false,
+    "modules_dtype_dict": {
+      "uint4": [
+        "language_model.layers.0.mlp.down_proj.weight",
+        "language_model.layers.0.mlp.gate_proj.weight",
+        "language_model.layers.0.mlp.up_proj.weight",
+        "language_model.layers.0.self_attn.k_proj.weight",
+        "language_model.layers.0.self_attn.o_proj.weight",
+        "language_model.layers.0.self_attn.q_proj.weight",
+        "language_model.layers.0.self_attn.v_proj.weight",
+        "language_model.layers.1.mlp.down_proj.weight",
+        "language_model.layers.1.mlp.gate_proj.weight",
+        "language_model.layers.1.mlp.up_proj.weight",
+        "language_model.layers.1.self_attn.k_proj.weight",
+        "language_model.layers.1.self_attn.o_proj.weight",
+        "language_model.layers.1.self_attn.q_proj.weight",
+        "language_model.layers.1.self_attn.v_proj.weight",
+        "language_model.layers.2.mlp.down_proj.weight",
+        "language_model.layers.2.mlp.gate_proj.weight",
+        "language_model.layers.2.mlp.up_proj.weight",
+        "language_model.layers.2.self_attn.k_proj.weight",
+        "language_model.layers.2.self_attn.o_proj.weight",
+        "language_model.layers.2.self_attn.q_proj.weight",
+        "language_model.layers.2.self_attn.v_proj.weight",
+        "language_model.layers.3.mlp.down_proj.weight",
+        "language_model.layers.3.mlp.gate_proj.weight",
+        "language_model.layers.3.mlp.up_proj.weight",
+        "language_model.layers.3.self_attn.k_proj.weight",
+        "language_model.layers.3.self_attn.o_proj.weight",
+        "language_model.layers.3.self_attn.q_proj.weight",
+        "language_model.layers.3.self_attn.v_proj.weight",
+        "language_model.layers.4.mlp.down_proj.weight",
+        "language_model.layers.4.mlp.gate_proj.weight",
+        "language_model.layers.4.mlp.up_proj.weight",
+        "language_model.layers.4.self_attn.k_proj.weight",
+        "language_model.layers.4.self_attn.o_proj.weight",
+        "language_model.layers.4.self_attn.q_proj.weight",
+        "language_model.layers.4.self_attn.v_proj.weight",
+        "language_model.layers.5.mlp.down_proj.weight",
+        "language_model.layers.5.mlp.gate_proj.weight",
+        "language_model.layers.5.mlp.up_proj.weight",
+        "language_model.layers.5.self_attn.k_proj.weight",
+        "language_model.layers.5.self_attn.o_proj.weight",
+        "language_model.layers.5.self_attn.q_proj.weight",
+        "language_model.layers.5.self_attn.v_proj.weight",
+        "language_model.layers.6.mlp.down_proj.weight",
+        "language_model.layers.6.mlp.gate_proj.weight",
+        "language_model.layers.6.mlp.up_proj.weight",
+        "language_model.layers.6.self_attn.k_proj.weight",
+        "language_model.layers.6.self_attn.o_proj.weight",
+        "language_model.layers.6.self_attn.q_proj.weight",
+        "language_model.layers.6.self_attn.v_proj.weight",
+        "language_model.layers.7.mlp.down_proj.weight",
+        "language_model.layers.7.mlp.gate_proj.weight",
+        "language_model.layers.7.mlp.up_proj.weight",
+        "language_model.layers.7.self_attn.k_proj.weight",
+        "language_model.layers.7.self_attn.o_proj.weight",
+        "language_model.layers.7.self_attn.q_proj.weight",
+        "language_model.layers.7.self_attn.v_proj.weight",
+        "language_model.layers.8.mlp.down_proj.weight",
+        "language_model.layers.8.mlp.gate_proj.weight",
+        "language_model.layers.8.mlp.up_proj.weight",
+        "language_model.layers.8.self_attn.k_proj.weight",
+        "language_model.layers.8.self_attn.o_proj.weight",
+        "language_model.layers.8.self_attn.q_proj.weight",
+        "language_model.layers.8.self_attn.v_proj.weight",
+        "language_model.layers.9.mlp.down_proj.weight",
+        "language_model.layers.9.mlp.gate_proj.weight",
+        "language_model.layers.9.mlp.up_proj.weight",
+        "language_model.layers.9.self_attn.k_proj.weight",
+        "language_model.layers.9.self_attn.o_proj.weight",
+        "language_model.layers.9.self_attn.q_proj.weight",
+        "language_model.layers.9.self_attn.v_proj.weight",
+        "language_model.layers.10.mlp.down_proj.weight",
+        "language_model.layers.10.mlp.gate_proj.weight",
+        "language_model.layers.10.mlp.up_proj.weight",
+        "language_model.layers.10.self_attn.k_proj.weight",
+        "language_model.layers.10.self_attn.o_proj.weight",
+        "language_model.layers.10.self_attn.q_proj.weight",
+        "language_model.layers.10.self_attn.v_proj.weight",
+        "language_model.layers.11.mlp.down_proj.weight",
+        "language_model.layers.11.mlp.gate_proj.weight",
+        "language_model.layers.11.mlp.up_proj.weight",
+        "language_model.layers.11.self_attn.k_proj.weight",
+        "language_model.layers.11.self_attn.o_proj.weight",
+        "language_model.layers.11.self_attn.q_proj.weight",
+        "language_model.layers.11.self_attn.v_proj.weight",
+        "language_model.layers.12.mlp.down_proj.weight",
+        "language_model.layers.12.mlp.gate_proj.weight",
+        "language_model.layers.12.mlp.up_proj.weight",
+        "language_model.layers.12.self_attn.k_proj.weight",
+        "language_model.layers.12.self_attn.o_proj.weight",
+        "language_model.layers.12.self_attn.q_proj.weight",
+        "language_model.layers.12.self_attn.v_proj.weight",
+        "language_model.layers.13.mlp.down_proj.weight",
+        "language_model.layers.13.mlp.gate_proj.weight",
+        "language_model.layers.13.mlp.up_proj.weight",
+        "language_model.layers.13.self_attn.k_proj.weight",
+        "language_model.layers.13.self_attn.o_proj.weight",
+        "language_model.layers.13.self_attn.q_proj.weight",
+        "language_model.layers.13.self_attn.v_proj.weight",
+        "language_model.layers.14.mlp.down_proj.weight",
+        "language_model.layers.14.mlp.gate_proj.weight",
+        "language_model.layers.14.mlp.up_proj.weight",
+        "language_model.layers.14.self_attn.k_proj.weight",
+        "language_model.layers.14.self_attn.o_proj.weight",
+        "language_model.layers.14.self_attn.q_proj.weight",
+        "language_model.layers.14.self_attn.v_proj.weight",
+        "language_model.layers.15.mlp.down_proj.weight",
+        "language_model.layers.15.mlp.gate_proj.weight",
+        "language_model.layers.15.mlp.up_proj.weight",
+        "language_model.layers.15.self_attn.k_proj.weight",
+        "language_model.layers.15.self_attn.o_proj.weight",
+        "language_model.layers.15.self_attn.q_proj.weight",
+        "language_model.layers.15.self_attn.v_proj.weight",
+        "language_model.layers.16.mlp.down_proj.weight",
+        "language_model.layers.16.mlp.gate_proj.weight",
+        "language_model.layers.16.mlp.up_proj.weight",
+        "language_model.layers.16.self_attn.k_proj.weight",
+        "language_model.layers.16.self_attn.o_proj.weight",
+        "language_model.layers.16.self_attn.q_proj.weight",
+        "language_model.layers.16.self_attn.v_proj.weight",
+        "language_model.layers.17.mlp.down_proj.weight",
+        "language_model.layers.17.mlp.gate_proj.weight",
+        "language_model.layers.17.mlp.up_proj.weight",
+        "language_model.layers.17.self_attn.k_proj.weight",
+        "language_model.layers.17.self_attn.o_proj.weight",
+        "language_model.layers.17.self_attn.q_proj.weight",
+        "language_model.layers.17.self_attn.v_proj.weight",
+        "language_model.layers.18.mlp.down_proj.weight",
+        "language_model.layers.18.mlp.gate_proj.weight",
+        "language_model.layers.18.mlp.up_proj.weight",
+        "language_model.layers.18.self_attn.k_proj.weight",
+        "language_model.layers.18.self_attn.o_proj.weight",
+        "language_model.layers.18.self_attn.q_proj.weight",
+        "language_model.layers.18.self_attn.v_proj.weight",
+        "language_model.layers.19.mlp.down_proj.weight",
+        "language_model.layers.19.mlp.gate_proj.weight",
+        "language_model.layers.19.mlp.up_proj.weight",
+        "language_model.layers.19.self_attn.k_proj.weight",
+        "language_model.layers.19.self_attn.o_proj.weight",
+        "language_model.layers.19.self_attn.q_proj.weight",
+        "language_model.layers.19.self_attn.v_proj.weight",
+        "language_model.layers.20.mlp.down_proj.weight",
+        "language_model.layers.20.mlp.gate_proj.weight",
+        "language_model.layers.20.mlp.up_proj.weight",
+        "language_model.layers.20.self_attn.k_proj.weight",
+        "language_model.layers.20.self_attn.o_proj.weight",
+        "language_model.layers.20.self_attn.q_proj.weight",
+        "language_model.layers.20.self_attn.v_proj.weight",
+        "language_model.layers.21.mlp.down_proj.weight",
+        "language_model.layers.21.mlp.gate_proj.weight",
+        "language_model.layers.21.mlp.up_proj.weight",
+        "language_model.layers.21.self_attn.k_proj.weight",
+        "language_model.layers.21.self_attn.o_proj.weight",
+        "language_model.layers.21.self_attn.q_proj.weight",
+        "language_model.layers.21.self_attn.v_proj.weight",
+        "language_model.layers.22.mlp.down_proj.weight",
+        "language_model.layers.22.mlp.gate_proj.weight",
+        "language_model.layers.22.mlp.up_proj.weight",
+        "language_model.layers.22.self_attn.k_proj.weight",
+        "language_model.layers.22.self_attn.o_proj.weight",
+        "language_model.layers.22.self_attn.q_proj.weight",
+        "language_model.layers.22.self_attn.v_proj.weight",
+        "language_model.layers.23.mlp.down_proj.weight",
+        "language_model.layers.23.mlp.gate_proj.weight",
+        "language_model.layers.23.mlp.up_proj.weight",
+        "language_model.layers.23.self_attn.k_proj.weight",
+        "language_model.layers.23.self_attn.o_proj.weight",
+        "language_model.layers.23.self_attn.q_proj.weight",
+        "language_model.layers.23.self_attn.v_proj.weight",
+        "language_model.layers.24.mlp.down_proj.weight",
+        "language_model.layers.24.mlp.gate_proj.weight",
+        "language_model.layers.24.mlp.up_proj.weight",
+        "language_model.layers.24.self_attn.k_proj.weight",
+        "language_model.layers.24.self_attn.o_proj.weight",
+        "language_model.layers.24.self_attn.q_proj.weight",
+        "language_model.layers.24.self_attn.v_proj.weight",
+        "language_model.layers.25.mlp.down_proj.weight",
+        "language_model.layers.25.mlp.gate_proj.weight",
+        "language_model.layers.25.mlp.up_proj.weight",
+        "language_model.layers.25.self_attn.k_proj.weight",
+        "language_model.layers.25.self_attn.o_proj.weight",
+        "language_model.layers.25.self_attn.q_proj.weight",
+        "language_model.layers.25.self_attn.v_proj.weight",
+        "language_model.layers.26.mlp.down_proj.weight",
+        "language_model.layers.26.mlp.gate_proj.weight",
+        "language_model.layers.26.mlp.up_proj.weight",
+        "language_model.layers.26.self_attn.k_proj.weight",
+        "language_model.layers.26.self_attn.o_proj.weight",
+        "language_model.layers.26.self_attn.q_proj.weight",
+        "language_model.layers.26.self_attn.v_proj.weight",
+        "language_model.layers.27.mlp.down_proj.weight",
+        "language_model.layers.27.mlp.gate_proj.weight",
+        "language_model.layers.27.mlp.up_proj.weight",
+        "language_model.layers.27.self_attn.k_proj.weight",
+        "language_model.layers.27.self_attn.o_proj.weight",
+        "language_model.layers.27.self_attn.q_proj.weight",
+        "language_model.layers.27.self_attn.v_proj.weight",
+        "language_model.layers.28.mlp.down_proj.weight",
+        "language_model.layers.28.mlp.gate_proj.weight",
+        "language_model.layers.28.mlp.up_proj.weight",
+        "language_model.layers.28.self_attn.k_proj.weight",
+        "language_model.layers.28.self_attn.o_proj.weight",
+        "language_model.layers.28.self_attn.q_proj.weight",
+        "language_model.layers.28.self_attn.v_proj.weight",
+        "language_model.layers.29.mlp.down_proj.weight",
+        "language_model.layers.29.mlp.gate_proj.weight",
+        "language_model.layers.29.mlp.up_proj.weight",
+        "language_model.layers.29.self_attn.k_proj.weight",
+        "language_model.layers.29.self_attn.o_proj.weight",
+        "language_model.layers.29.self_attn.q_proj.weight",
+        "language_model.layers.29.self_attn.v_proj.weight",
+        "language_model.layers.30.mlp.down_proj.weight",
+        "language_model.layers.30.mlp.gate_proj.weight",
+        "language_model.layers.30.mlp.up_proj.weight",
+        "language_model.layers.30.self_attn.k_proj.weight",
+        "language_model.layers.30.self_attn.o_proj.weight",
+        "language_model.layers.30.self_attn.q_proj.weight",
+        "language_model.layers.30.self_attn.v_proj.weight",
+        "language_model.layers.31.mlp.down_proj.weight",
+        "language_model.layers.31.mlp.gate_proj.weight",
+        "language_model.layers.31.mlp.up_proj.weight",
+        "language_model.layers.31.self_attn.k_proj.weight",
+        "language_model.layers.31.self_attn.o_proj.weight",
+        "language_model.layers.31.self_attn.q_proj.weight",
+        "language_model.layers.31.self_attn.v_proj.weight",
+        "language_model.layers.32.mlp.down_proj.weight",
+        "language_model.layers.32.mlp.gate_proj.weight",
+        "language_model.layers.32.mlp.up_proj.weight",
+        "language_model.layers.32.self_attn.k_proj.weight",
+        "language_model.layers.32.self_attn.o_proj.weight",
+        "language_model.layers.32.self_attn.q_proj.weight",
+        "language_model.layers.32.self_attn.v_proj.weight",
+        "language_model.layers.33.mlp.down_proj.weight",
+        "language_model.layers.33.mlp.gate_proj.weight",
+        "language_model.layers.33.mlp.up_proj.weight",
+        "language_model.layers.33.self_attn.k_proj.weight",
+        "language_model.layers.33.self_attn.o_proj.weight",
+        "language_model.layers.33.self_attn.q_proj.weight",
+        "language_model.layers.33.self_attn.v_proj.weight",
+        "language_model.layers.34.mlp.down_proj.weight",
+        "language_model.layers.34.mlp.gate_proj.weight",
+        "language_model.layers.34.mlp.up_proj.weight",
+        "language_model.layers.34.self_attn.k_proj.weight",
+        "language_model.layers.34.self_attn.o_proj.weight",
+        "language_model.layers.34.self_attn.q_proj.weight",
+        "language_model.layers.34.self_attn.v_proj.weight",
+        "language_model.layers.35.mlp.down_proj.weight",
+        "language_model.layers.35.mlp.gate_proj.weight",
+        "language_model.layers.35.mlp.up_proj.weight",
+        "language_model.layers.35.self_attn.k_proj.weight",
+        "language_model.layers.35.self_attn.o_proj.weight",
+        "language_model.layers.35.self_attn.q_proj.weight",
+        "language_model.layers.35.self_attn.v_proj.weight",
+        "visual.blocks.0.attn.proj.weight",
+        "visual.blocks.0.attn.qkv.weight",
+        "visual.blocks.0.mlp.linear_fc1.weight",
+        "visual.blocks.0.mlp.linear_fc2.weight",
+        "visual.blocks.1.attn.proj.weight",
+        "visual.blocks.1.attn.qkv.weight",
+        "visual.blocks.1.mlp.linear_fc1.weight",
+        "visual.blocks.1.mlp.linear_fc2.weight",
+        "visual.blocks.2.attn.proj.weight",
+        "visual.blocks.2.attn.qkv.weight",
+        "visual.blocks.2.mlp.linear_fc1.weight",
+        "visual.blocks.2.mlp.linear_fc2.weight",
+        "visual.blocks.3.attn.proj.weight",
+        "visual.blocks.3.attn.qkv.weight",
+        "visual.blocks.3.mlp.linear_fc1.weight",
+        "visual.blocks.3.mlp.linear_fc2.weight",
+        "visual.blocks.4.attn.proj.weight",
+        "visual.blocks.4.attn.qkv.weight",
+        "visual.blocks.4.mlp.linear_fc1.weight",
+        "visual.blocks.4.mlp.linear_fc2.weight",
+        "visual.blocks.5.attn.proj.weight",
+        "visual.blocks.5.attn.qkv.weight",
+        "visual.blocks.5.mlp.linear_fc1.weight",
+        "visual.blocks.5.mlp.linear_fc2.weight",
+        "visual.blocks.6.attn.proj.weight",
+        "visual.blocks.6.attn.qkv.weight",
+        "visual.blocks.6.mlp.linear_fc1.weight",
+        "visual.blocks.6.mlp.linear_fc2.weight",
+        "visual.blocks.7.attn.proj.weight",
+        "visual.blocks.7.attn.qkv.weight",
+        "visual.blocks.7.mlp.linear_fc1.weight",
+        "visual.blocks.7.mlp.linear_fc2.weight",
+        "visual.blocks.8.attn.proj.weight",
+        "visual.blocks.8.attn.qkv.weight",
+        "visual.blocks.8.mlp.linear_fc1.weight",
+        "visual.blocks.8.mlp.linear_fc2.weight",
+        "visual.blocks.9.attn.proj.weight",
+        "visual.blocks.9.attn.qkv.weight",
+        "visual.blocks.9.mlp.linear_fc1.weight",
+        "visual.blocks.9.mlp.linear_fc2.weight",
+        "visual.blocks.10.attn.proj.weight",
+        "visual.blocks.10.attn.qkv.weight",
+        "visual.blocks.10.mlp.linear_fc1.weight",
+        "visual.blocks.10.mlp.linear_fc2.weight",
+        "visual.blocks.11.attn.proj.weight",
+        "visual.blocks.11.attn.qkv.weight",
+        "visual.blocks.11.mlp.linear_fc1.weight",
+        "visual.blocks.11.mlp.linear_fc2.weight",
+        "visual.blocks.12.attn.proj.weight",
+        "visual.blocks.12.attn.qkv.weight",
+        "visual.blocks.12.mlp.linear_fc1.weight",
+        "visual.blocks.12.mlp.linear_fc2.weight",
+        "visual.blocks.13.attn.proj.weight",
+        "visual.blocks.13.attn.qkv.weight",
+        "visual.blocks.13.mlp.linear_fc1.weight",
+        "visual.blocks.13.mlp.linear_fc2.weight",
+        "visual.blocks.14.attn.proj.weight",
+        "visual.blocks.14.attn.qkv.weight",
+        "visual.blocks.14.mlp.linear_fc1.weight",
+        "visual.blocks.14.mlp.linear_fc2.weight",
+        "visual.blocks.15.attn.proj.weight",
+        "visual.blocks.15.attn.qkv.weight",
+        "visual.blocks.15.mlp.linear_fc1.weight",
+        "visual.blocks.15.mlp.linear_fc2.weight",
+        "visual.blocks.16.attn.proj.weight",
+        "visual.blocks.16.attn.qkv.weight",
+        "visual.blocks.16.mlp.linear_fc1.weight",
+        "visual.blocks.16.mlp.linear_fc2.weight",
+        "visual.blocks.17.attn.proj.weight",
+        "visual.blocks.17.attn.qkv.weight",
+        "visual.blocks.17.mlp.linear_fc1.weight",
+        "visual.blocks.17.mlp.linear_fc2.weight",
+        "visual.blocks.18.attn.proj.weight",
+        "visual.blocks.18.attn.qkv.weight",
+        "visual.blocks.18.mlp.linear_fc1.weight",
+        "visual.blocks.18.mlp.linear_fc2.weight",
+        "visual.blocks.19.attn.proj.weight",
+        "visual.blocks.19.attn.qkv.weight",
+        "visual.blocks.19.mlp.linear_fc1.weight",
+        "visual.blocks.19.mlp.linear_fc2.weight",
+        "visual.blocks.20.attn.proj.weight",
+        "visual.blocks.20.attn.qkv.weight",
+        "visual.blocks.20.mlp.linear_fc1.weight",
+        "visual.blocks.20.mlp.linear_fc2.weight",
+        "visual.blocks.21.attn.proj.weight",
+        "visual.blocks.21.attn.qkv.weight",
+        "visual.blocks.21.mlp.linear_fc1.weight",
+        "visual.blocks.21.mlp.linear_fc2.weight",
+        "visual.blocks.22.attn.proj.weight",
+        "visual.blocks.22.attn.qkv.weight",
+        "visual.blocks.22.mlp.linear_fc1.weight",
+        "visual.blocks.22.mlp.linear_fc2.weight",
+        "visual.blocks.23.attn.proj.weight",
+        "visual.blocks.23.attn.qkv.weight",
+        "visual.blocks.23.mlp.linear_fc1.weight",
+        "visual.blocks.23.mlp.linear_fc2.weight",
+        "visual.deepstack_merger_list.0.linear_fc1.weight",
+        "visual.deepstack_merger_list.0.linear_fc2.weight",
+        "visual.deepstack_merger_list.1.linear_fc1.weight",
+        "visual.deepstack_merger_list.1.linear_fc2.weight",
+        "visual.deepstack_merger_list.2.linear_fc1.weight",
+        "visual.deepstack_merger_list.2.linear_fc2.weight",
+        "visual.merger.linear_fc1.weight",
+        "visual.merger.linear_fc2.weight"
+      ]
+    },
+    "modules_quant_config": {},
+    "modules_to_not_convert": [
+      ".condition_embedder",
+      "patch_embed",
+      ".emb_in",
+      ".txt_out",
+      ".context_embedder",
+      ".vid_out",
+      "lm_head",
+      ".time_embed",
+      ".img_out",
+      ".final_layer",
+      "patch_emb",
+      ".norm_out",
+      ".txt_in",
+      "multi_modal_projector",
+      "language_model.norm",
+      ".proj_out",
+      "patch_embedding",
+      ".vid_in",
+      ".t_embedder",
+      ".x_embedder",
+      "time_text_embed",
+      ".emb_out",
+      ".img_in",
+      "wte",
+      ".y_embedder",
+      "language_model.embed_tokens.weight",
+      "language_model.layers.0.input_layernorm.weight",
+      "language_model.layers.0.post_attention_layernorm.weight",
+      "language_model.layers.0.self_attn.k_norm.weight",
+      "language_model.layers.0.self_attn.q_norm.weight",
+      "language_model.layers.1.input_layernorm.weight",
+      "language_model.layers.1.post_attention_layernorm.weight",
+      "language_model.layers.1.self_attn.k_norm.weight",
+      "language_model.layers.1.self_attn.q_norm.weight",
+      "language_model.layers.2.input_layernorm.weight",
+      "language_model.layers.2.post_attention_layernorm.weight",
+      "language_model.layers.2.self_attn.k_norm.weight",
+      "language_model.layers.2.self_attn.q_norm.weight",
+      "language_model.layers.3.input_layernorm.weight",
+      "language_model.layers.3.post_attention_layernorm.weight",
+      "language_model.layers.3.self_attn.k_norm.weight",
+      "language_model.layers.3.self_attn.q_norm.weight",
+      "language_model.layers.4.input_layernorm.weight",
+      "language_model.layers.4.post_attention_layernorm.weight",
+      "language_model.layers.4.self_attn.k_norm.weight",
+      "language_model.layers.4.self_attn.q_norm.weight",
+      "language_model.layers.5.input_layernorm.weight",
+      "language_model.layers.5.post_attention_layernorm.weight",
+      "language_model.layers.5.self_attn.k_norm.weight",
+      "language_model.layers.5.self_attn.q_norm.weight",
+      "language_model.layers.6.input_layernorm.weight",
+      "language_model.layers.6.post_attention_layernorm.weight",
+      "language_model.layers.6.self_attn.k_norm.weight",
+      "language_model.layers.6.self_attn.q_norm.weight",
+      "language_model.layers.7.input_layernorm.weight",
+      "language_model.layers.7.post_attention_layernorm.weight",
+      "language_model.layers.7.self_attn.k_norm.weight",
+      "language_model.layers.7.self_attn.q_norm.weight",
+      "language_model.layers.8.input_layernorm.weight",
+      "language_model.layers.8.post_attention_layernorm.weight",
+      "language_model.layers.8.self_attn.k_norm.weight",
+      "language_model.layers.8.self_attn.q_norm.weight",
+      "language_model.layers.9.input_layernorm.weight",
+      "language_model.layers.9.post_attention_layernorm.weight",
+      "language_model.layers.9.self_attn.k_norm.weight",
+      "language_model.layers.9.self_attn.q_norm.weight",
+      "language_model.layers.10.input_layernorm.weight",
+      "language_model.layers.10.post_attention_layernorm.weight",
+      "language_model.layers.10.self_attn.k_norm.weight",
+      "language_model.layers.10.self_attn.q_norm.weight",
+      "language_model.layers.11.input_layernorm.weight",
+      "language_model.layers.11.post_attention_layernorm.weight",
+      "language_model.layers.11.self_attn.k_norm.weight",
+      "language_model.layers.11.self_attn.q_norm.weight",
+      "language_model.layers.12.input_layernorm.weight",
+      "language_model.layers.12.post_attention_layernorm.weight",
+      "language_model.layers.12.self_attn.k_norm.weight",
+      "language_model.layers.12.self_attn.q_norm.weight",
+      "language_model.layers.13.input_layernorm.weight",
+      "language_model.layers.13.post_attention_layernorm.weight",
+      "language_model.layers.13.self_attn.k_norm.weight",
+      "language_model.layers.13.self_attn.q_norm.weight",
+      "language_model.layers.14.input_layernorm.weight",
+      "language_model.layers.14.post_attention_layernorm.weight",
+      "language_model.layers.14.self_attn.k_norm.weight",
+      "language_model.layers.14.self_attn.q_norm.weight",
+      "language_model.layers.15.input_layernorm.weight",
+      "language_model.layers.15.post_attention_layernorm.weight",
+      "language_model.layers.15.self_attn.k_norm.weight",
+      "language_model.layers.15.self_attn.q_norm.weight",
+      "language_model.layers.16.input_layernorm.weight",
+      "language_model.layers.16.post_attention_layernorm.weight",
+      "language_model.layers.16.self_attn.k_norm.weight",
+      "language_model.layers.16.self_attn.q_norm.weight",
+      "language_model.layers.17.input_layernorm.weight",
+      "language_model.layers.17.post_attention_layernorm.weight",
+      "language_model.layers.17.self_attn.k_norm.weight",
+      "language_model.layers.17.self_attn.q_norm.weight",
+      "language_model.layers.18.input_layernorm.weight",
+      "language_model.layers.18.post_attention_layernorm.weight",
+      "language_model.layers.18.self_attn.k_norm.weight",
+      "language_model.layers.18.self_attn.q_norm.weight",
+      "language_model.layers.19.input_layernorm.weight",
+      "language_model.layers.19.post_attention_layernorm.weight",
+      "language_model.layers.19.self_attn.k_norm.weight",
+      "language_model.layers.19.self_attn.q_norm.weight",
+      "language_model.layers.20.input_layernorm.weight",
+      "language_model.layers.20.post_attention_layernorm.weight",
+      "language_model.layers.20.self_attn.k_norm.weight",
+      "language_model.layers.20.self_attn.q_norm.weight",
+      "language_model.layers.21.input_layernorm.weight",
+      "language_model.layers.21.post_attention_layernorm.weight",
+      "language_model.layers.21.self_attn.k_norm.weight",
+      "language_model.layers.21.self_attn.q_norm.weight",
+      "language_model.layers.22.input_layernorm.weight",
+      "language_model.layers.22.post_attention_layernorm.weight",
+      "language_model.layers.22.self_attn.k_norm.weight",
+      "language_model.layers.22.self_attn.q_norm.weight",
+      "language_model.layers.23.input_layernorm.weight",
+      "language_model.layers.23.post_attention_layernorm.weight",
+      "language_model.layers.23.self_attn.k_norm.weight",
+      "language_model.layers.23.self_attn.q_norm.weight",
+      "language_model.layers.24.input_layernorm.weight",
+      "language_model.layers.24.post_attention_layernorm.weight",
+      "language_model.layers.24.self_attn.k_norm.weight",
+      "language_model.layers.24.self_attn.q_norm.weight",
+      "language_model.layers.25.input_layernorm.weight",
+      "language_model.layers.25.post_attention_layernorm.weight",
+      "language_model.layers.25.self_attn.k_norm.weight",
+      "language_model.layers.25.self_attn.q_norm.weight",
+      "language_model.layers.26.input_layernorm.weight",
+      "language_model.layers.26.post_attention_layernorm.weight",
+      "language_model.layers.26.self_attn.k_norm.weight",
+      "language_model.layers.26.self_attn.q_norm.weight",
+      "language_model.layers.27.input_layernorm.weight",
+      "language_model.layers.27.post_attention_layernorm.weight",
+      "language_model.layers.27.self_attn.k_norm.weight",
+      "language_model.layers.27.self_attn.q_norm.weight",
+      "language_model.layers.28.input_layernorm.weight",
+      "language_model.layers.28.post_attention_layernorm.weight",
+      "language_model.layers.28.self_attn.k_norm.weight",
+      "language_model.layers.28.self_attn.q_norm.weight",
+      "language_model.layers.29.input_layernorm.weight",
+      "language_model.layers.29.post_attention_layernorm.weight",
+      "language_model.layers.29.self_attn.k_norm.weight",
+      "language_model.layers.29.self_attn.q_norm.weight",
+      "language_model.layers.30.input_layernorm.weight",
+      "language_model.layers.30.post_attention_layernorm.weight",
+      "language_model.layers.30.self_attn.k_norm.weight",
+      "language_model.layers.30.self_attn.q_norm.weight",
+      "language_model.layers.31.input_layernorm.weight",
+      "language_model.layers.31.post_attention_layernorm.weight",
+      "language_model.layers.31.self_attn.k_norm.weight",
+      "language_model.layers.31.self_attn.q_norm.weight",
+      "language_model.layers.32.input_layernorm.weight",
+      "language_model.layers.32.post_attention_layernorm.weight",
+      "language_model.layers.32.self_attn.k_norm.weight",
+      "language_model.layers.32.self_attn.q_norm.weight",
+      "language_model.layers.33.input_layernorm.weight",
+      "language_model.layers.33.post_attention_layernorm.weight",
+      "language_model.layers.33.self_attn.k_norm.weight",
+      "language_model.layers.33.self_attn.q_norm.weight",
+      "language_model.layers.34.input_layernorm.weight",
+      "language_model.layers.34.post_attention_layernorm.weight",
+      "language_model.layers.34.self_attn.k_norm.weight",
+      "language_model.layers.34.self_attn.q_norm.weight",
+      "language_model.layers.35.input_layernorm.weight",
+      "language_model.layers.35.post_attention_layernorm.weight",
+      "language_model.layers.35.self_attn.k_norm.weight",
+      "language_model.layers.35.self_attn.q_norm.weight",
+      "language_model.norm.weight",
+      "visual.blocks.0.norm1.weight",
+      "visual.blocks.0.norm2.weight",
+      "visual.blocks.1.norm1.weight",
+      "visual.blocks.1.norm2.weight",
+      "visual.blocks.2.norm1.weight",
+      "visual.blocks.2.norm2.weight",
+      "visual.blocks.3.norm1.weight",
+      "visual.blocks.3.norm2.weight",
+      "visual.blocks.4.norm1.weight",
+      "visual.blocks.4.norm2.weight",
+      "visual.blocks.5.norm1.weight",
+      "visual.blocks.5.norm2.weight",
+      "visual.blocks.6.norm1.weight",
+      "visual.blocks.6.norm2.weight",
+      "visual.blocks.7.norm1.weight",
+      "visual.blocks.7.norm2.weight",
+      "visual.blocks.8.norm1.weight",
+      "visual.blocks.8.norm2.weight",
+      "visual.blocks.9.norm1.weight",
+      "visual.blocks.9.norm2.weight",
+      "visual.blocks.10.norm1.weight",
+      "visual.blocks.10.norm2.weight",
+      "visual.blocks.11.norm1.weight",
+      "visual.blocks.11.norm2.weight",
+      "visual.blocks.12.norm1.weight",
+      "visual.blocks.12.norm2.weight",
+      "visual.blocks.13.norm1.weight",
+      "visual.blocks.13.norm2.weight",
+      "visual.blocks.14.norm1.weight",
+      "visual.blocks.14.norm2.weight",
+      "visual.blocks.15.norm1.weight",
+      "visual.blocks.15.norm2.weight",
+      "visual.blocks.16.norm1.weight",
+      "visual.blocks.16.norm2.weight",
+      "visual.blocks.17.norm1.weight",
+      "visual.blocks.17.norm2.weight",
+      "visual.blocks.18.norm1.weight",
+      "visual.blocks.18.norm2.weight",
+      "visual.blocks.19.norm1.weight",
+      "visual.blocks.19.norm2.weight",
+      "visual.blocks.20.norm1.weight",
+      "visual.blocks.20.norm2.weight",
+      "visual.blocks.21.norm1.weight",
+      "visual.blocks.21.norm2.weight",
+      "visual.blocks.22.norm1.weight",
+      "visual.blocks.22.norm2.weight",
+      "visual.blocks.23.norm1.weight",
+      "visual.blocks.23.norm2.weight",
+      "visual.deepstack_merger_list.0.norm.weight",
+      "visual.deepstack_merger_list.1.norm.weight",
+      "visual.deepstack_merger_list.2.norm.weight",
+      "visual.merger.norm.weight",
+      "visual.pos_embed.weight"
+    ],
+    "modules_to_not_use_matmul": [],
+    "non_blocking": false,
+    "quant_conv": false,
+    "quant_embedding": false,
+    "quant_method": "sdnq",
+    "quantization_device": null,
+    "quantized_matmul_dtype": null,
+    "return_device": null,
+    "sdnq_version": "0.2.0",
+    "svd_rank": 32,
+    "svd_steps": 8,
+    "use_dynamic_quantization": true,
+    "use_grad_ckpt": true,
+    "use_hadamard": true,
+    "use_quantized_matmul": false,
+    "use_quantized_matmul_conv": false,
+    "use_static_quantization": true,
+    "use_stochastic_rounding": false,
+    "use_svd": false,
+    "weights_dtype": "uint4"
+  },
+  "text_config": {
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "bos_token_id": 151643,
+    "dtype": "bfloat16",
+    "eos_token_id": 151645,
+    "head_dim": 128,
+    "hidden_act": "silu",
+    "hidden_size": 2560,
+    "initializer_range": 0.02,
+    "intermediate_size": 9728,
+    "max_position_embeddings": 262144,
+    "model_type": "qwen3_vl_text",
+    "num_attention_heads": 32,
+    "num_hidden_layers": 36,
+    "num_key_value_heads": 8,
+    "pad_token_id": null,
+    "rms_norm_eps": 1e-06,
+    "rope_parameters": {
+      "mrope_interleaved": true,
+      "mrope_section": [
+        24,
+        20,
+        20
+      ],
+      "rope_theta": 5000000,
+      "rope_type": "default"
+    },
+    "tie_word_embeddings": true,
+    "use_cache": true,
+    "vocab_size": 151936
+  },
+  "tie_word_embeddings": true,
+  "transformers_version": "5.3.0",
+  "video_token_id": 151656,
+  "vision_config": {
+    "deepstack_visual_indexes": [
+      5,
+      11,
+      17
+    ],
+    "depth": 24,
+    "dtype": "bfloat16",
+    "hidden_act": "gelu_pytorch_tanh",
+    "hidden_size": 1024,
+    "in_channels": 3,
+    "initializer_range": 0.02,
+    "intermediate_size": 4096,
+    "model_type": "qwen3_vl",
+    "num_heads": 16,
+    "num_position_embeddings": 2304,
+    "out_hidden_size": 2560,
+    "patch_size": 16,
+    "spatial_merge_size": 2,
+    "temporal_patch_size": 2
+  },
+  "vision_end_token_id": 151653,
+  "vision_start_token_id": 151652
+}

text_encoder/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:afbf7bf5538760a82714c5f15e3d17aee1ed7fd6443a0d6be6419dd7cec68a51
+size 3062036496

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 +1,350 @@
+{
+  "_class_name": "Krea2Transformer2DModel",
+  "_diffusers_version": "0.39.0.dev0",
+  "_name_or_path": "/home/ozzy/Documents/models/Krea-2-Turbo/transformer",
+  "attention_head_dim": 128,
+  "axes_dims_rope": [
+    32,
+    48,
+    48
+  ],
+  "in_channels": 64,
+  "intermediate_size": 16384,
+  "norm_eps": 1e-05,
+  "num_attention_heads": 48,
+  "num_key_value_heads": 12,
+  "num_layers": 28,
+  "num_layerwise_text_blocks": 2,
+  "num_refiner_text_blocks": 2,
+  "num_text_layers": 12,
+  "quantization_config": {
+    "add_skip_keys": true,
+    "dequantize_fp32": false,
+    "dynamic_loss_threshold": 0.01,
+    "group_size": 0,
+    "hadamard_group_size": 256,
+    "is_integer": true,
+    "is_training": false,
+    "modules_dtype_dict": {
+      "uint4": [
+        "text_fusion.projector.weight",
+        "time_mod_proj.weight",
+        "text_fusion.layerwise_blocks.0.attn.to_gate.weight",
+        "text_fusion.layerwise_blocks.0.attn.to_k.weight",
+        "text_fusion.layerwise_blocks.0.attn.to_out.0.weight",
+        "text_fusion.layerwise_blocks.0.attn.to_q.weight",
+        "text_fusion.layerwise_blocks.0.attn.to_v.weight",
+        "text_fusion.layerwise_blocks.0.ff.down.weight",
+        "text_fusion.layerwise_blocks.0.ff.gate.weight",
+        "text_fusion.layerwise_blocks.0.ff.up.weight",
+        "text_fusion.layerwise_blocks.1.attn.to_gate.weight",
+        "text_fusion.layerwise_blocks.1.attn.to_k.weight",
+        "text_fusion.layerwise_blocks.1.attn.to_out.0.weight",
+        "text_fusion.layerwise_blocks.1.attn.to_q.weight",
+        "text_fusion.layerwise_blocks.1.attn.to_v.weight",
+        "text_fusion.layerwise_blocks.1.ff.down.weight",
+        "text_fusion.layerwise_blocks.1.ff.gate.weight",
+        "text_fusion.layerwise_blocks.1.ff.up.weight",
+        "text_fusion.refiner_blocks.0.attn.to_gate.weight",
+        "text_fusion.refiner_blocks.0.attn.to_k.weight",
+        "text_fusion.refiner_blocks.0.attn.to_out.0.weight",
+        "text_fusion.refiner_blocks.0.attn.to_q.weight",
+        "text_fusion.refiner_blocks.0.attn.to_v.weight",
+        "text_fusion.refiner_blocks.0.ff.down.weight",
+        "text_fusion.refiner_blocks.0.ff.gate.weight",
+        "text_fusion.refiner_blocks.0.ff.up.weight",
+        "text_fusion.refiner_blocks.1.attn.to_gate.weight",
+        "text_fusion.refiner_blocks.1.attn.to_k.weight",
+        "text_fusion.refiner_blocks.1.attn.to_out.0.weight",
+        "text_fusion.refiner_blocks.1.attn.to_q.weight",
+        "text_fusion.refiner_blocks.1.attn.to_v.weight",
+        "text_fusion.refiner_blocks.1.ff.down.weight",
+        "text_fusion.refiner_blocks.1.ff.gate.weight",
+        "text_fusion.refiner_blocks.1.ff.up.weight",
+        "transformer_blocks.0.attn.to_gate.weight",
+        "transformer_blocks.0.attn.to_k.weight",
+        "transformer_blocks.0.attn.to_out.0.weight",
+        "transformer_blocks.0.attn.to_q.weight",
+        "transformer_blocks.0.attn.to_v.weight",
+        "transformer_blocks.0.ff.down.weight",
+        "transformer_blocks.0.ff.gate.weight",
+        "transformer_blocks.0.ff.up.weight",
+        "transformer_blocks.1.attn.to_gate.weight",
+        "transformer_blocks.1.attn.to_k.weight",
+        "transformer_blocks.1.attn.to_out.0.weight",
+        "transformer_blocks.1.attn.to_q.weight",
+        "transformer_blocks.1.attn.to_v.weight",
+        "transformer_blocks.1.ff.down.weight",
+        "transformer_blocks.1.ff.gate.weight",
+        "transformer_blocks.1.ff.up.weight",
+        "transformer_blocks.2.attn.to_gate.weight",
+        "transformer_blocks.2.attn.to_k.weight",
+        "transformer_blocks.2.attn.to_out.0.weight",
+        "transformer_blocks.2.attn.to_q.weight",
+        "transformer_blocks.2.attn.to_v.weight",
+        "transformer_blocks.2.ff.down.weight",
+        "transformer_blocks.2.ff.gate.weight",
+        "transformer_blocks.2.ff.up.weight",
+        "transformer_blocks.3.attn.to_gate.weight",
+        "transformer_blocks.3.attn.to_k.weight",
+        "transformer_blocks.3.attn.to_out.0.weight",
+        "transformer_blocks.3.attn.to_q.weight",
+        "transformer_blocks.3.attn.to_v.weight",
+        "transformer_blocks.3.ff.down.weight",
+        "transformer_blocks.3.ff.gate.weight",
+        "transformer_blocks.3.ff.up.weight",
+        "transformer_blocks.4.attn.to_gate.weight",
+        "transformer_blocks.4.attn.to_k.weight",
+        "transformer_blocks.4.attn.to_out.0.weight",
+        "transformer_blocks.4.attn.to_q.weight",
+        "transformer_blocks.4.attn.to_v.weight",
+        "transformer_blocks.4.ff.down.weight",
+        "transformer_blocks.4.ff.gate.weight",
+        "transformer_blocks.4.ff.up.weight",
+        "transformer_blocks.5.attn.to_gate.weight",
+        "transformer_blocks.5.attn.to_k.weight",
+        "transformer_blocks.5.attn.to_out.0.weight",
+        "transformer_blocks.5.attn.to_q.weight",
+        "transformer_blocks.5.attn.to_v.weight",
+        "transformer_blocks.5.ff.down.weight",
+        "transformer_blocks.5.ff.gate.weight",
+        "transformer_blocks.5.ff.up.weight",
+        "transformer_blocks.6.attn.to_gate.weight",
+        "transformer_blocks.6.attn.to_k.weight",
+        "transformer_blocks.6.attn.to_out.0.weight",
+        "transformer_blocks.6.attn.to_q.weight",
+        "transformer_blocks.6.attn.to_v.weight",
+        "transformer_blocks.6.ff.down.weight",
+        "transformer_blocks.6.ff.gate.weight",
+        "transformer_blocks.6.ff.up.weight",
+        "transformer_blocks.7.attn.to_gate.weight",
+        "transformer_blocks.7.attn.to_k.weight",
+        "transformer_blocks.7.attn.to_out.0.weight",
+        "transformer_blocks.7.attn.to_q.weight",
+        "transformer_blocks.7.attn.to_v.weight",
+        "transformer_blocks.7.ff.down.weight",
+        "transformer_blocks.7.ff.gate.weight",
+        "transformer_blocks.7.ff.up.weight",
+        "transformer_blocks.8.attn.to_gate.weight",
+        "transformer_blocks.8.attn.to_k.weight",
+        "transformer_blocks.8.attn.to_out.0.weight",
+        "transformer_blocks.8.attn.to_q.weight",
+        "transformer_blocks.8.attn.to_v.weight",
+        "transformer_blocks.8.ff.down.weight",
+        "transformer_blocks.8.ff.gate.weight",
+        "transformer_blocks.8.ff.up.weight",
+        "transformer_blocks.9.attn.to_gate.weight",
+        "transformer_blocks.9.attn.to_k.weight",
+        "transformer_blocks.9.attn.to_q.weight",
+        "transformer_blocks.9.attn.to_v.weight",
+        "transformer_blocks.10.attn.to_gate.weight",
+        "transformer_blocks.10.attn.to_k.weight",
+        "transformer_blocks.10.attn.to_out.0.weight",
+        "transformer_blocks.10.attn.to_q.weight",
+        "transformer_blocks.10.attn.to_v.weight",
+        "transformer_blocks.10.ff.down.weight",
+        "transformer_blocks.10.ff.gate.weight",
+        "transformer_blocks.10.ff.up.weight",
+        "transformer_blocks.11.attn.to_gate.weight",
+        "transformer_blocks.11.attn.to_k.weight",
+        "transformer_blocks.11.attn.to_out.0.weight",
+        "transformer_blocks.11.attn.to_q.weight",
+        "transformer_blocks.11.attn.to_v.weight",
+        "transformer_blocks.11.ff.down.weight",
+        "transformer_blocks.11.ff.gate.weight",
+        "transformer_blocks.11.ff.up.weight",
+        "transformer_blocks.12.attn.to_gate.weight",
+        "transformer_blocks.12.attn.to_k.weight",
+        "transformer_blocks.12.attn.to_out.0.weight",
+        "transformer_blocks.12.attn.to_q.weight",
+        "transformer_blocks.12.attn.to_v.weight",
+        "transformer_blocks.12.ff.down.weight",
+        "transformer_blocks.12.ff.gate.weight",
+        "transformer_blocks.12.ff.up.weight",
+        "transformer_blocks.13.attn.to_gate.weight",
+        "transformer_blocks.13.attn.to_k.weight",
+        "transformer_blocks.13.attn.to_out.0.weight",
+        "transformer_blocks.13.attn.to_q.weight",
+        "transformer_blocks.13.attn.to_v.weight",
+        "transformer_blocks.13.ff.down.weight",
+        "transformer_blocks.13.ff.gate.weight",
+        "transformer_blocks.13.ff.up.weight",
+        "transformer_blocks.14.attn.to_gate.weight",
+        "transformer_blocks.14.attn.to_k.weight",
+        "transformer_blocks.14.attn.to_out.0.weight",
+        "transformer_blocks.14.attn.to_q.weight",
+        "transformer_blocks.14.attn.to_v.weight",
+        "transformer_blocks.14.ff.down.weight",
+        "transformer_blocks.14.ff.gate.weight",
+        "transformer_blocks.14.ff.up.weight",
+        "transformer_blocks.15.attn.to_gate.weight",
+        "transformer_blocks.15.attn.to_k.weight",
+        "transformer_blocks.15.attn.to_out.0.weight",
+        "transformer_blocks.15.attn.to_q.weight",
+        "transformer_blocks.15.attn.to_v.weight",
+        "transformer_blocks.15.ff.down.weight",
+        "transformer_blocks.15.ff.gate.weight",
+        "transformer_blocks.15.ff.up.weight",
+        "transformer_blocks.16.attn.to_gate.weight",
+        "transformer_blocks.16.attn.to_k.weight",
+        "transformer_blocks.16.attn.to_out.0.weight",
+        "transformer_blocks.16.attn.to_q.weight",
+        "transformer_blocks.16.attn.to_v.weight",
+        "transformer_blocks.16.ff.down.weight",
+        "transformer_blocks.16.ff.gate.weight",
+        "transformer_blocks.16.ff.up.weight",
+        "transformer_blocks.17.attn.to_gate.weight",
+        "transformer_blocks.17.attn.to_k.weight",
+        "transformer_blocks.17.attn.to_out.0.weight",
+        "transformer_blocks.17.attn.to_q.weight",
+        "transformer_blocks.17.attn.to_v.weight",
+        "transformer_blocks.17.ff.down.weight",
+        "transformer_blocks.17.ff.gate.weight",
+        "transformer_blocks.17.ff.up.weight",
+        "transformer_blocks.18.attn.to_gate.weight",
+        "transformer_blocks.18.attn.to_k.weight",
+        "transformer_blocks.18.attn.to_out.0.weight",
+        "transformer_blocks.18.attn.to_q.weight",
+        "transformer_blocks.18.attn.to_v.weight",
+        "transformer_blocks.18.ff.down.weight",
+        "transformer_blocks.18.ff.gate.weight",
+        "transformer_blocks.18.ff.up.weight",
+        "transformer_blocks.19.attn.to_gate.weight",
+        "transformer_blocks.19.attn.to_k.weight",
+        "transformer_blocks.19.attn.to_out.0.weight",
+        "transformer_blocks.19.attn.to_q.weight",
+        "transformer_blocks.19.attn.to_v.weight",
+        "transformer_blocks.19.ff.down.weight",
+        "transformer_blocks.19.ff.gate.weight",
+        "transformer_blocks.19.ff.up.weight",
+        "transformer_blocks.20.attn.to_gate.weight",
+        "transformer_blocks.20.attn.to_k.weight",
+        "transformer_blocks.20.attn.to_out.0.weight",
+        "transformer_blocks.20.attn.to_q.weight",
+        "transformer_blocks.20.attn.to_v.weight",
+        "transformer_blocks.20.ff.gate.weight",
+        "transformer_blocks.9.attn.to_out.0.weight",
+        "transformer_blocks.9.ff.down.weight",
+        "transformer_blocks.9.ff.gate.weight",
+        "transformer_blocks.9.ff.up.weight",
+        "transformer_blocks.20.ff.down.weight",
+        "transformer_blocks.20.ff.up.weight",
+        "transformer_blocks.21.attn.to_gate.weight",
+        "transformer_blocks.21.attn.to_k.weight",
+        "transformer_blocks.21.attn.to_out.0.weight",
+        "transformer_blocks.21.attn.to_q.weight",
+        "transformer_blocks.21.attn.to_v.weight",
+        "transformer_blocks.21.ff.down.weight",
+        "transformer_blocks.21.ff.gate.weight",
+        "transformer_blocks.21.ff.up.weight",
+        "transformer_blocks.22.attn.to_gate.weight",
+        "transformer_blocks.22.attn.to_k.weight",
+        "transformer_blocks.22.attn.to_out.0.weight",
+        "transformer_blocks.22.attn.to_q.weight",
+        "transformer_blocks.22.attn.to_v.weight",
+        "transformer_blocks.22.ff.down.weight",
+        "transformer_blocks.22.ff.gate.weight",
+        "transformer_blocks.22.ff.up.weight",
+        "transformer_blocks.23.attn.to_gate.weight",
+        "transformer_blocks.23.attn.to_k.weight",
+        "transformer_blocks.23.attn.to_out.0.weight",
+        "transformer_blocks.23.attn.to_q.weight",
+        "transformer_blocks.23.attn.to_v.weight",
+        "transformer_blocks.23.ff.down.weight",
+        "transformer_blocks.23.ff.gate.weight",
+        "transformer_blocks.23.ff.up.weight",
+        "transformer_blocks.24.attn.to_gate.weight",
+        "transformer_blocks.24.attn.to_k.weight",
+        "transformer_blocks.24.attn.to_out.0.weight",
+        "transformer_blocks.24.attn.to_q.weight",
+        "transformer_blocks.24.attn.to_v.weight",
+        "transformer_blocks.24.ff.down.weight",
+        "transformer_blocks.24.ff.gate.weight",
+        "transformer_blocks.24.ff.up.weight",
+        "transformer_blocks.25.attn.to_gate.weight",
+        "transformer_blocks.25.attn.to_k.weight",
+        "transformer_blocks.25.attn.to_out.0.weight",
+        "transformer_blocks.25.attn.to_q.weight",
+        "transformer_blocks.25.attn.to_v.weight",
+        "transformer_blocks.25.ff.down.weight",
+        "transformer_blocks.25.ff.gate.weight",
+        "transformer_blocks.25.ff.up.weight",
+        "transformer_blocks.26.attn.to_gate.weight",
+        "transformer_blocks.26.attn.to_k.weight",
+        "transformer_blocks.26.attn.to_out.0.weight",
+        "transformer_blocks.26.attn.to_q.weight",
+        "transformer_blocks.26.attn.to_v.weight",
+        "transformer_blocks.26.ff.down.weight",
+        "transformer_blocks.26.ff.gate.weight",
+        "transformer_blocks.26.ff.up.weight",
+        "transformer_blocks.27.attn.to_gate.weight",
+        "transformer_blocks.27.attn.to_k.weight",
+        "transformer_blocks.27.attn.to_out.0.weight",
+        "transformer_blocks.27.attn.to_q.weight",
+        "transformer_blocks.27.attn.to_v.weight",
+        "transformer_blocks.27.ff.down.weight",
+        "transformer_blocks.27.ff.gate.weight",
+        "transformer_blocks.27.ff.up.weight"
+      ]
+    },
+    "modules_quant_config": {},
+    "modules_to_not_convert": [
+      "norm",
+      "norm_k",
+      "time_embed",
+      ".condition_embedder",
+      "patch_embed",
+      ".emb_in",
+      ".txt_out",
+      ".context_embedder",
+      ".vid_out",
+      "lm_head",
+      ".time_embed",
+      "norm1",
+      ".img_out",
+      "norm_q",
+      ".final_layer",
+      "patch_emb",
+      ".norm_out",
+      ".txt_in",
+      "multi_modal_projector",
+      ".proj_out",
+      "patch_embedding",
+      ".vid_in",
+      ".t_embedder",
+      ".x_embedder",
+      "time_text_embed",
+      ".emb_out",
+      "norm2",
+      ".img_in",
+      "wte",
+      ".y_embedder"
+    ],
+    "modules_to_not_use_matmul": [],
+    "non_blocking": false,
+    "quant_conv": false,
+    "quant_embedding": false,
+    "quant_method": "sdnq",
+    "quantization_device": null,
+    "quantized_matmul_dtype": null,
+    "return_device": null,
+    "sdnq_version": "0.2.0",
+    "svd_rank": 32,
+    "svd_steps": 8,
+    "use_dynamic_quantization": true,
+    "use_grad_ckpt": true,
+    "use_hadamard": true,
+    "use_quantized_matmul": false,
+    "use_quantized_matmul_conv": false,
+    "use_static_quantization": true,
+    "use_stochastic_rounding": false,
+    "use_svd": false,
+    "weights_dtype": "uint4"
+  },
+  "rope_theta": 1000.0,
+  "text_hidden_dim": 2560,
+  "text_intermediate_size": 6912,
+  "text_num_attention_heads": 20,
+  "text_num_key_value_heads": 20,
+  "timestep_embed_dim": 256
+}

transformer/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b42987209cbbc14daebe46b65053a16336a376bc644e194f07fd1955488d6c3e
+size 7348837562

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:ab1b61103959913d6c7e628cf793dbb2ca4726a40a3b3ae206c52b8e75bf6f08
+size 507591892