Hugging Face's logo

sangoi-exe
/
sd-webui-codex

Text-to-Image
GGUF
stable-diffusion
stable-diffusion-xl
sdxl
flux
wan22
lora
klein
ltx-2
ltx2
image-to-image
video
codex-webui
Model card Files
xet
 Community
2
sangoi-exe commited on
Commit
8530cbd
·
verified ·
1 Parent(s): e5b7983

Upload 10 files

Browse files
Files changed (10) hide show
  1. ip_adapter/image_encoders/ViT-H-VISIONONLY/ViT-H.safetensors +3 -0
  2. ip_adapter/image_encoders/ViT-H-VISIONONLY/config.json +23 -0
  3. ip_adapter/image_encoders/ViT-H-VISIONONLY/huggingface_repo.json +46 -0
  4. ip_adapter/image_encoders/ViT-bigG-VISIONONLY/ViT-bigG.safetensors +3 -0
  5. ip_adapter/image_encoders/ViT-bigG-VISIONONLY/config.json +81 -0
  6. ip_adapter/image_encoders/ViT-bigG-VISIONONLY/huggingface_repo.json +49 -0
  7. ip_adapter/models/sdxl/ip-adapter-plus-face_sdxl_vit-h.bin +3 -0
  8. ip_adapter/models/sdxl/ip-adapter-plus_sdxl_vit-h.bin +3 -0
  9. ip_adapter/models/sdxl/ip-adapter_sdxl.bin +3 -0
  10. ip_adapter/models/sdxl/ip-adapter_sdxl_vit-h.bin +3 -0
ip_adapter/image_encoders/ViT-H-VISIONONLY/ViT-H.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6ca9667da1ca9e0b0f75e46bb030f7e011f44f86cbfb8d5a36590fcd7507b030
3
+ size 2528373448
ip_adapter/image_encoders/ViT-H-VISIONONLY/config.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "./image_encoder",
3
+ "architectures": [
4
+ "CLIPVisionModelWithProjection"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "dropout": 0.0,
8
+ "hidden_act": "gelu",
9
+ "hidden_size": 1280,
10
+ "image_size": 224,
11
+ "initializer_factor": 1.0,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 5120,
14
+ "layer_norm_eps": 1e-05,
15
+ "model_type": "clip_vision_model",
16
+ "num_attention_heads": 16,
17
+ "num_channels": 3,
18
+ "num_hidden_layers": 32,
19
+ "patch_size": 14,
20
+ "projection_dim": 1024,
21
+ "torch_dtype": "float16",
22
+ "transformers_version": "4.28.0.dev0"
23
+ }
ip_adapter/image_encoders/ViT-H-VISIONONLY/huggingface_repo.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "schema_version": 1,
3
+ "purpose": "Upstream Hugging Face provenance for a locally repacked VISIONONLY CLIP image encoder folder.",
4
+ "created_by": "stable-diffusion-webui-codex",
5
+ "created_at_utc": "2026-03-28T00:00:00Z",
6
+ "recommended_local_folder_name": "ViT-H-VISIONONLY",
7
+ "upstream": {
8
+ "provider": "huggingface",
9
+ "repo_type": "model",
10
+ "repo_id": "laion/CLIP-ViT-H-14-laion2B-s32B-b79K",
11
+ "repo_url": "https://huggingface.co/laion/CLIP-ViT-H-14-laion2B-s32B-b79K",
12
+ "tree_url": "https://huggingface.co/laion/CLIP-ViT-H-14-laion2B-s32B-b79K/tree/main",
13
+ "api_url": "https://huggingface.co/api/models/laion/CLIP-ViT-H-14-laion2B-s32B-b79K",
14
+ "revision": "main",
15
+ "sha": "1c2b8495b28150b8a4922ee1c8edee224c284c0c",
16
+ "last_modified": "2025-01-22T04:38:44.000Z",
17
+ "license": "mit",
18
+ "library_name": "open_clip",
19
+ "pipeline_tag": "zero-shot-image-classification"
20
+ },
21
+ "local_repack": {
22
+ "folder_name": "ViT-H-VISIONONLY",
23
+ "intended_contents": [
24
+ "config.json",
25
+ "model.safetensors"
26
+ ],
27
+ "preferred_runtime_weight_file": "model.safetensors",
28
+ "note": "Provenance sidecar only. Current Codex IP-Adapter runtime loads the selected encoder weight file directly and does not read this JSON."
29
+ },
30
+ "upstream_files": [
31
+ ".gitattributes",
32
+ "README.md",
33
+ "config.json",
34
+ "merges.txt",
35
+ "model.safetensors",
36
+ "open_clip_config.json",
37
+ "open_clip_model.safetensors",
38
+ "open_clip_pytorch_model.bin",
39
+ "preprocessor_config.json",
40
+ "pytorch_model.bin",
41
+ "special_tokens_map.json",
42
+ "tokenizer.json",
43
+ "tokenizer_config.json",
44
+ "vocab.json"
45
+ ]
46
+ }
ip_adapter/image_encoders/ViT-bigG-VISIONONLY/ViT-bigG.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:657723e09f46a7c3957df651601029f66b1748afb12b419816330f16ed45d64d
3
+ size 3689912664
ip_adapter/image_encoders/ViT-bigG-VISIONONLY/config.json ADDED
@@ -0,0 +1,81 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "CLIPVisionModelWithProjection"
4
+ ],
5
+ "_name_or_path": "",
6
+ "add_cross_attention": false,
7
+ "architectures": null,
8
+ "attention_dropout": 0.0,
9
+ "bad_words_ids": null,
10
+ "begin_suppress_tokens": null,
11
+ "bos_token_id": null,
12
+ "chunk_size_feed_forward": 0,
13
+ "cross_attention_hidden_size": null,
14
+ "decoder_start_token_id": null,
15
+ "diversity_penalty": 0.0,
16
+ "do_sample": false,
17
+ "dropout": 0.0,
18
+ "early_stopping": false,
19
+ "encoder_no_repeat_ngram_size": 0,
20
+ "eos_token_id": null,
21
+ "exponential_decay_length_penalty": null,
22
+ "finetuning_task": null,
23
+ "forced_bos_token_id": null,
24
+ "forced_eos_token_id": null,
25
+ "hidden_act": "gelu",
26
+ "hidden_size": 1664,
27
+ "id2label": {
28
+ "0": "LABEL_0",
29
+ "1": "LABEL_1"
30
+ },
31
+ "image_size": 224,
32
+ "initializer_factor": 1.0,
33
+ "initializer_range": 0.02,
34
+ "intermediate_size": 8192,
35
+ "is_decoder": false,
36
+ "is_encoder_decoder": false,
37
+ "label2id": {
38
+ "LABEL_0": 0,
39
+ "LABEL_1": 1
40
+ },
41
+ "layer_norm_eps": 1e-05,
42
+ "length_penalty": 1.0,
43
+ "max_length": 20,
44
+ "min_length": 0,
45
+ "model_type": "clip_vision_model",
46
+ "no_repeat_ngram_size": 0,
47
+ "num_attention_heads": 16,
48
+ "num_beam_groups": 1,
49
+ "num_beams": 1,
50
+ "num_channels": 3,
51
+ "num_hidden_layers": 48,
52
+ "num_return_sequences": 1,
53
+ "output_attentions": false,
54
+ "output_hidden_states": false,
55
+ "output_scores": false,
56
+ "pad_token_id": null,
57
+ "patch_size": 14,
58
+ "prefix": null,
59
+ "problem_type": null,
60
+ "pruned_heads": {},
61
+ "remove_invalid_values": false,
62
+ "repetition_penalty": 1.0,
63
+ "return_dict": true,
64
+ "return_dict_in_generate": false,
65
+ "sep_token_id": null,
66
+ "suppress_tokens": null,
67
+ "task_specific_params": null,
68
+ "temperature": 1.0,
69
+ "tf_legacy_loss": false,
70
+ "tie_encoder_decoder": false,
71
+ "tie_word_embeddings": true,
72
+ "tokenizer_class": null,
73
+ "top_k": 50,
74
+ "top_p": 1.0,
75
+ "torch_dtype": null,
76
+ "torchscript": false,
77
+ "transformers_version": "4.24.0",
78
+ "typical_p": 1.0,
79
+ "use_bfloat16": false,
80
+ "projection_dim": 1280
81
+ }
ip_adapter/image_encoders/ViT-bigG-VISIONONLY/huggingface_repo.json ADDED
@@ -0,0 +1,49 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "schema_version": 1,
3
+ "purpose": "Upstream Hugging Face provenance for a locally repacked VISIONONLY CLIP image encoder folder.",
4
+ "created_by": "stable-diffusion-webui-codex",
5
+ "created_at_utc": "2026-03-28T00:00:00Z",
6
+ "recommended_local_folder_name": "ViT-bigG-VISIONONLY",
7
+ "upstream": {
8
+ "provider": "huggingface",
9
+ "repo_type": "model",
10
+ "repo_id": "laion/CLIP-ViT-bigG-14-laion2B-39B-b160k",
11
+ "repo_url": "https://huggingface.co/laion/CLIP-ViT-bigG-14-laion2B-39B-b160k",
12
+ "tree_url": "https://huggingface.co/laion/CLIP-ViT-bigG-14-laion2B-39B-b160k/tree/main",
13
+ "api_url": "https://huggingface.co/api/models/laion/CLIP-ViT-bigG-14-laion2B-39B-b160k",
14
+ "revision": "main",
15
+ "sha": "743c27bd53dfe508a0ade0f50698f99b39d03bec",
16
+ "last_modified": "2025-01-22T04:37:32.000Z",
17
+ "license": "mit",
18
+ "library_name": "open_clip",
19
+ "pipeline_tag": "zero-shot-image-classification"
20
+ },
21
+ "local_repack": {
22
+ "folder_name": "ViT-bigG-VISIONONLY",
23
+ "intended_contents": [
24
+ "config.json",
25
+ "model.safetensors"
26
+ ],
27
+ "preferred_runtime_weight_file": "model.safetensors",
28
+ "note": "Provenance sidecar only. Current Codex IP-Adapter runtime loads the selected encoder weight file directly and does not read this JSON."
29
+ },
30
+ "upstream_files": [
31
+ ".gitattributes",
32
+ "README.md",
33
+ "config.json",
34
+ "merges.txt",
35
+ "open_clip_config.json",
36
+ "open_clip_model.safetensors",
37
+ "open_clip_pytorch_model.bin",
38
+ "preprocessor_config.json",
39
+ "pytorch_model-00001-of-00002.bin",
40
+ "pytorch_model-00001-of-00002.safetensors",
41
+ "pytorch_model-00002-of-00002.bin",
42
+ "pytorch_model-00002-of-00002.safetensors",
43
+ "pytorch_model.bin.index.json",
44
+ "special_tokens_map.json",
45
+ "tokenizer.json",
46
+ "tokenizer_config.json",
47
+ "vocab.json"
48
+ ]
49
+ }
ip_adapter/models/sdxl/ip-adapter-plus-face_sdxl_vit-h.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:50e886d82940b3c5873d80c2b06d8a4b0d0fccec70bc44fd53f16ac3cfd7fc36
3
+ size 1013454761
ip_adapter/models/sdxl/ip-adapter-plus_sdxl_vit-h.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec70edb7cc8e769c9388d94eeaea3e4526352c9fae793a608782d1d8951fde90
3
+ size 1013454427
ip_adapter/models/sdxl/ip-adapter_sdxl.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7525f2731e9e86d1368e0b68467615d55dda459691965bdd7d37fa3d7fd84c12
3
+ size 702585097
ip_adapter/models/sdxl/ip-adapter_sdxl_vit-h.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b382e2501d0ab3fe2e09312e561a59cd3f21262aff25373700e0cd62c635929
3
+ size 698390793