Add camera LoRAs and Gemma 3 text encoder

.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
 ltx2.3-open.png filter=lfs diff=lfs merge=lfs -text
+text_encoder/tokenizer.json filter=lfs diff=lfs merge=lfs -text

loras/LTX-2-19b-LoRA-Camera-Control-Dolly-In/ltx-2-19b-lora-camera-control-dolly-in.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0da937d528ea619c95859ad0c5cab012c7213fe058b7cb289e2a513ec351f237
+size 327309208

loras/LTX-2-19b-LoRA-Camera-Control-Dolly-Left/ltx-2-19b-lora-camera-control-dolly-left.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fdd28ee1a53e5413d74b90064c7ec0fe98b78457b5da06c0c9c4ea5810d1f5f6
+size 327309208

loras/LTX-2-19b-LoRA-Camera-Control-Dolly-Out/ltx-2-19b-lora-camera-control-dolly-out.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:554c30e64fa57b6c98e059f1b3ccabc50ad85195aab0911aed317b714f8d644d
+size 327309208

loras/LTX-2-19b-LoRA-Camera-Control-Dolly-Right/ltx-2-19b-lora-camera-control-dolly-right.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee1a3a34dc21c6b61a4c5775756dd0fab8700e06dd35658c852c0127202aa5dd
+size 327309208

loras/LTX-2-19b-LoRA-Camera-Control-Jib-Down/ltx-2-19b-lora-camera-control-jib-down.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a2f72b231841f998a46b949271fa0bcec21012d4238a53e7eb4762bc828bee3
+size 2214978664

loras/LTX-2-19b-LoRA-Camera-Control-Jib-Up/ltx-2-19b-lora-camera-control-jib-up.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4e8bd628238caf20079515ba2bce5770fa1108e6ed8c1d403a3179a68dce77f
+size 2214978664

loras/LTX-2-19b-LoRA-Camera-Control-Static/ltx-2-19b-lora-camera-control-static.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b79aad7ecdd60aef07f39177d1ac225a6608806086af94848436fec432e2d0d
+size 2214978664

text_encoder/config.json

@@ -0,0 +1,62 @@
+{
+  "architectures": [
+    "Gemma3ForConditionalGeneration"
+  ],
+  "boi_token_index": 255999,
+  "eoi_token_index": 256000,
+  "eos_token_id": [
+    1,
+    106
+  ],
+  "image_token_index": 262144,
+  "initializer_range": 0.02,
+  "mm_tokens_per_image": 256,
+  "model_type": "gemma3",
+  "text_config": {
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "attn_logit_softcapping": null,
+    "cache_implementation": "hybrid",
+    "final_logit_softcapping": null,
+    "head_dim": 256,
+    "hidden_activation": "gelu_pytorch_tanh",
+    "hidden_size": 3840,
+    "initializer_range": 0.02,
+    "intermediate_size": 15360,
+    "max_position_embeddings": 131072,
+    "model_type": "gemma3_text",
+    "num_attention_heads": 16,
+    "num_hidden_layers": 48,
+    "num_key_value_heads": 8,
+    "query_pre_attn_scalar": 256,
+    "rms_norm_eps": 1e-06,
+    "rope_local_base_freq": 10000,
+    "rope_scaling": {
+      "factor": 8.0,
+      "rope_type": "linear"
+    },
+    "rope_theta": 1000000,
+    "sliding_window": 1024,
+    "sliding_window_pattern": 6,
+    "torch_dtype": "bfloat16",
+    "use_cache": true,
+    "vocab_size": 262208
+  },
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.52.0.dev0",
+  "vision_config": {
+    "attention_dropout": 0.0,
+    "hidden_act": "gelu_pytorch_tanh",
+    "hidden_size": 1152,
+    "image_size": 896,
+    "intermediate_size": 4304,
+    "layer_norm_eps": 1e-06,
+    "model_type": "siglip_vision_model",
+    "num_attention_heads": 16,
+    "num_channels": 3,
+    "num_hidden_layers": 27,
+    "patch_size": 14,
+    "torch_dtype": "bfloat16",
+    "vision_use_head": false
+  }
+}

text_encoder/generation_config.json

@@ -0,0 +1,11 @@
+{
+  "cache_implementation": "hybrid",
+  "do_sample": true,
+  "eos_token_id": [
+    1,
+    106
+  ],
+  "top_k": 64,
+  "top_p": 0.95,
+  "transformers_version": "4.52.0.dev0"
+}

text_encoder/model-00001-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6fb899db428481aafb45a20130457df6e247e7cb03b7d9f01ee4bc2a9a08138
+size 4979902192

text_encoder/model-00002-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d251e7fe9799d529405ddb61705a44cd700bd30a8b66a8d44ae26ddf8365dbc6
+size 4931296592

text_encoder/model-00003-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0684ef801385f0669a0b3e4ab160c50877efdbfa40eb97788595985de2743e78
+size 4931296656

text_encoder/model-00004-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4b964e6526f81ccfa625c900b72ce92d5e0fd2debb75998763038ad06b9c541
+size 4931296656

text_encoder/model-00005-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ef2de8f93e165b4e02425769fc566000b0674256ef0c3a27b23a0d45eb12088
+size 4601000928

text_encoder/preprocessor_config.json

@@ -0,0 +1,29 @@
+{
+  "do_convert_rgb": null,
+  "do_normalize": true,
+  "do_pan_and_scan": null,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_processor_type": "Gemma3ImageProcessor",
+  "image_seq_length": 256,
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "pan_and_scan_max_num_crops": null,
+  "pan_and_scan_min_crop_size": null,
+  "pan_and_scan_min_ratio_to_activate": null,
+  "processor_class": "Gemma3Processor",
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 896,
+    "width": 896
+  }
+}

text_encoder/processor_config.json

@@ -0,0 +1,4 @@
+{
+  "image_seq_length": 256,
+  "processor_class": "Gemma3Processor"
+}

text_encoder/special_tokens_map.json

@@ -0,0 +1,33 @@
+{
+  "boi_token": "<start_of_image>",
+  "bos_token": {
+    "content": "<bos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eoi_token": "<end_of_image>",
+  "eos_token": {
+    "content": "<eos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "image_token": "<image_soft_token>",
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

text_encoder/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d4046bf0505a327dd5a0abbb427ecd4fc82f99c2ceaa170bc61ecde12809b0c
+size 33384570

text_encoder/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1299c11d7cf632ef3b4e11937501358ada021bbdf7c47638d13c0ee982f2e79c
+size 4689074