Upload 10 files

ip_adapter/image_encoders/ViT-H-VISIONONLY/ViT-H.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ca9667da1ca9e0b0f75e46bb030f7e011f44f86cbfb8d5a36590fcd7507b030
+size 2528373448

ip_adapter/image_encoders/ViT-H-VISIONONLY/config.json

@@ -0,0 +1,23 @@
+{
+  "_name_or_path": "./image_encoder",
+  "architectures": [
+    "CLIPVisionModelWithProjection"
+  ],
+  "attention_dropout": 0.0,
+  "dropout": 0.0,
+  "hidden_act": "gelu",
+  "hidden_size": 1280,
+  "image_size": 224,
+  "initializer_factor": 1.0,
+  "initializer_range": 0.02,
+  "intermediate_size": 5120,
+  "layer_norm_eps": 1e-05,
+  "model_type": "clip_vision_model",
+  "num_attention_heads": 16,
+  "num_channels": 3,
+  "num_hidden_layers": 32,
+  "patch_size": 14,
+  "projection_dim": 1024,
+  "torch_dtype": "float16",
+  "transformers_version": "4.28.0.dev0"
+}

ip_adapter/image_encoders/ViT-H-VISIONONLY/huggingface_repo.json

@@ -0,0 +1,46 @@
+{
+  "schema_version": 1,
+  "purpose": "Upstream Hugging Face provenance for a locally repacked VISIONONLY CLIP image encoder folder.",
+  "created_by": "stable-diffusion-webui-codex",
+  "created_at_utc": "2026-03-28T00:00:00Z",
+  "recommended_local_folder_name": "ViT-H-VISIONONLY",
+  "upstream": {
+    "provider": "huggingface",
+    "repo_type": "model",
+    "repo_id": "laion/CLIP-ViT-H-14-laion2B-s32B-b79K",
+    "repo_url": "https://huggingface.co/laion/CLIP-ViT-H-14-laion2B-s32B-b79K",
+    "tree_url": "https://huggingface.co/laion/CLIP-ViT-H-14-laion2B-s32B-b79K/tree/main",
+    "api_url": "https://huggingface.co/api/models/laion/CLIP-ViT-H-14-laion2B-s32B-b79K",
+    "revision": "main",
+    "sha": "1c2b8495b28150b8a4922ee1c8edee224c284c0c",
+    "last_modified": "2025-01-22T04:38:44.000Z",
+    "license": "mit",
+    "library_name": "open_clip",
+    "pipeline_tag": "zero-shot-image-classification"
+  },
+  "local_repack": {
+    "folder_name": "ViT-H-VISIONONLY",
+    "intended_contents": [
+      "config.json",
+      "model.safetensors"
+    ],
+    "preferred_runtime_weight_file": "model.safetensors",
+    "note": "Provenance sidecar only. Current Codex IP-Adapter runtime loads the selected encoder weight file directly and does not read this JSON."
+  },
+  "upstream_files": [
+    ".gitattributes",
+    "README.md",
+    "config.json",
+    "merges.txt",
+    "model.safetensors",
+    "open_clip_config.json",
+    "open_clip_model.safetensors",
+    "open_clip_pytorch_model.bin",
+    "preprocessor_config.json",
+    "pytorch_model.bin",
+    "special_tokens_map.json",
+    "tokenizer.json",
+    "tokenizer_config.json",
+    "vocab.json"
+  ]
+}

ip_adapter/image_encoders/ViT-bigG-VISIONONLY/ViT-bigG.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:657723e09f46a7c3957df651601029f66b1748afb12b419816330f16ed45d64d
+size 3689912664

ip_adapter/image_encoders/ViT-bigG-VISIONONLY/config.json

@@ -0,0 +1,81 @@
+{
+  "architectures": [
+    "CLIPVisionModelWithProjection"
+  ],
+  "_name_or_path": "",
+  "add_cross_attention": false,
+  "architectures": null,
+  "attention_dropout": 0.0,
+  "bad_words_ids": null,
+  "begin_suppress_tokens": null,
+  "bos_token_id": null,
+  "chunk_size_feed_forward": 0,
+  "cross_attention_hidden_size": null,
+  "decoder_start_token_id": null,
+  "diversity_penalty": 0.0,
+  "do_sample": false,
+  "dropout": 0.0,
+  "early_stopping": false,
+  "encoder_no_repeat_ngram_size": 0,
+  "eos_token_id": null,
+  "exponential_decay_length_penalty": null,
+  "finetuning_task": null,
+  "forced_bos_token_id": null,
+  "forced_eos_token_id": null,
+  "hidden_act": "gelu",
+  "hidden_size": 1664,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1"
+      },
+  "image_size": 224,
+  "initializer_factor": 1.0,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "is_decoder": false,
+  "is_encoder_decoder": false,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1
+      },
+  "layer_norm_eps": 1e-05,
+  "length_penalty": 1.0,
+  "max_length": 20,
+  "min_length": 0,
+  "model_type": "clip_vision_model",
+  "no_repeat_ngram_size": 0,
+  "num_attention_heads": 16,
+  "num_beam_groups": 1,
+  "num_beams": 1,
+  "num_channels": 3,
+  "num_hidden_layers": 48,
+  "num_return_sequences": 1,
+  "output_attentions": false,
+  "output_hidden_states": false,
+  "output_scores": false,
+  "pad_token_id": null,
+  "patch_size": 14,
+  "prefix": null,
+  "problem_type": null,
+  "pruned_heads": {},
+  "remove_invalid_values": false,
+  "repetition_penalty": 1.0,
+  "return_dict": true,
+  "return_dict_in_generate": false,
+  "sep_token_id": null,
+  "suppress_tokens": null,
+  "task_specific_params": null,
+  "temperature": 1.0,
+  "tf_legacy_loss": false,
+  "tie_encoder_decoder": false,
+  "tie_word_embeddings": true,
+  "tokenizer_class": null,
+  "top_k": 50,
+  "top_p": 1.0,
+  "torch_dtype": null,
+  "torchscript": false,
+  "transformers_version": "4.24.0",
+  "typical_p": 1.0,
+  "use_bfloat16": false,
+  "projection_dim": 1280
+}

ip_adapter/image_encoders/ViT-bigG-VISIONONLY/huggingface_repo.json

@@ -0,0 +1,49 @@
+{
+  "schema_version": 1,
+  "purpose": "Upstream Hugging Face provenance for a locally repacked VISIONONLY CLIP image encoder folder.",
+  "created_by": "stable-diffusion-webui-codex",
+  "created_at_utc": "2026-03-28T00:00:00Z",
+  "recommended_local_folder_name": "ViT-bigG-VISIONONLY",
+  "upstream": {
+    "provider": "huggingface",
+    "repo_type": "model",
+    "repo_id": "laion/CLIP-ViT-bigG-14-laion2B-39B-b160k",
+    "repo_url": "https://huggingface.co/laion/CLIP-ViT-bigG-14-laion2B-39B-b160k",
+    "tree_url": "https://huggingface.co/laion/CLIP-ViT-bigG-14-laion2B-39B-b160k/tree/main",
+    "api_url": "https://huggingface.co/api/models/laion/CLIP-ViT-bigG-14-laion2B-39B-b160k",
+    "revision": "main",
+    "sha": "743c27bd53dfe508a0ade0f50698f99b39d03bec",
+    "last_modified": "2025-01-22T04:37:32.000Z",
+    "license": "mit",
+    "library_name": "open_clip",
+    "pipeline_tag": "zero-shot-image-classification"
+  },
+  "local_repack": {
+    "folder_name": "ViT-bigG-VISIONONLY",
+    "intended_contents": [
+      "config.json",
+      "model.safetensors"
+    ],
+    "preferred_runtime_weight_file": "model.safetensors",
+    "note": "Provenance sidecar only. Current Codex IP-Adapter runtime loads the selected encoder weight file directly and does not read this JSON."
+  },
+  "upstream_files": [
+    ".gitattributes",
+    "README.md",
+    "config.json",
+    "merges.txt",
+    "open_clip_config.json",
+    "open_clip_model.safetensors",
+    "open_clip_pytorch_model.bin",
+    "preprocessor_config.json",
+    "pytorch_model-00001-of-00002.bin",
+    "pytorch_model-00001-of-00002.safetensors",
+    "pytorch_model-00002-of-00002.bin",
+    "pytorch_model-00002-of-00002.safetensors",
+    "pytorch_model.bin.index.json",
+    "special_tokens_map.json",
+    "tokenizer.json",
+    "tokenizer_config.json",
+    "vocab.json"
+  ]
+}

ip_adapter/models/sdxl/ip-adapter-plus-face_sdxl_vit-h.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50e886d82940b3c5873d80c2b06d8a4b0d0fccec70bc44fd53f16ac3cfd7fc36
+size 1013454761

ip_adapter/models/sdxl/ip-adapter-plus_sdxl_vit-h.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec70edb7cc8e769c9388d94eeaea3e4526352c9fae793a608782d1d8951fde90
+size 1013454427

ip_adapter/models/sdxl/ip-adapter_sdxl.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7525f2731e9e86d1368e0b68467615d55dda459691965bdd7d37fa3d7fd84c12
+size 702585097

ip_adapter/models/sdxl/ip-adapter_sdxl_vit-h.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b382e2501d0ab3fe2e09312e561a59cd3f21262aff25373700e0cd62c635929
+size 698390793