Copie du paquet image.low : fichiers identiques à segmind/SSD-1B

Origine : https://huggingface.co/segmind/SSD-1B (révision 60987f37e94cd59c36b1cba832b9f97b57395a10). Fichiers LFS dupliqués côté serveur, petits fichiers vérifiés par SHA-256.

.optima-package.json

@@ -0,0 +1,97 @@
+{
+  "schemaVersion": 1,
+  "packageId": "image.low",
+  "packageVersion": "60987f37e94c",
+  "files": [
+    {
+      "path": "model_index.json",
+      "sizeBytes": 577,
+      "sha256": "2f4d71b6da5648627b9a2848b7f430d2294e95abbc5d3282dddd438bf8b466da"
+    },
+    {
+      "path": "scheduler/scheduler_config.json",
+      "sizeBytes": 474,
+      "sha256": "e0140f54cf0f8a5fb1cf8140caa95c1e733b6d9fa45c5e859aae43f3b9a45648"
+    },
+    {
+      "path": "text_encoder/config.json",
+      "sizeBytes": 560,
+      "sha256": "32d8cadf544d77c231efa1381145ac7e8f4cc88f581455c3c5f6369364474c83"
+    },
+    {
+      "path": "text_encoder/model.safetensors",
+      "sizeBytes": 246144864,
+      "sha256": "5487ea0eee9c9a9bff8abd097908d4deff3ae1fa87b3b67397f8b9538139d447"
+    },
+    {
+      "path": "text_encoder_2/config.json",
+      "sizeBytes": 570,
+      "sha256": "79b0f15ad762cf9c2992d50f9679d08c6cb477a50c88d41e216fc2d886e37abb"
+    },
+    {
+      "path": "text_encoder_2/model.safetensors",
+      "sizeBytes": 1389382880,
+      "sha256": "d3df577f6e3799c8e1bd9b40e30133710e02e8e25d0ce48cdcc790e7dfe12d6d"
+    },
+    {
+      "path": "tokenizer/merges.txt",
+      "sizeBytes": 524619,
+      "sha256": "9fd691f7c8039210e0fced15865466c65820d09b63988b0174bfe25de299051a"
+    },
+    {
+      "path": "tokenizer/special_tokens_map.json",
+      "sizeBytes": 472,
+      "sha256": "c4864a9376a8401918425bed71fc14fc0e81f9b59ec45c1cf96cccb2df508eac"
+    },
+    {
+      "path": "tokenizer/tokenizer_config.json",
+      "sizeBytes": 737,
+      "sha256": "19d7b034cb0cc3ce9766c2231373ab8aa8991fc72e2c8f76558bfaae3de0d563"
+    },
+    {
+      "path": "tokenizer/vocab.json",
+      "sizeBytes": 1059962,
+      "sha256": "e089ad92ba36837a0d31433e555c8f45fe601ab5c221d4f607ded32d9f7a4349"
+    },
+    {
+      "path": "tokenizer_2/merges.txt",
+      "sizeBytes": 524619,
+      "sha256": "9fd691f7c8039210e0fced15865466c65820d09b63988b0174bfe25de299051a"
+    },
+    {
+      "path": "tokenizer_2/special_tokens_map.json",
+      "sizeBytes": 460,
+      "sha256": "f118ab3a983206e4f32583448de6bd6aae4ee21869135cef1f5848a753cdaab6"
+    },
+    {
+      "path": "tokenizer_2/tokenizer_config.json",
+      "sizeBytes": 725,
+      "sha256": "c9d23941f76a41cbd50eda9290f57be7828f0a7a677939e9ef181f7e12bd1bdf"
+    },
+    {
+      "path": "tokenizer_2/vocab.json",
+      "sizeBytes": 1059962,
+      "sha256": "e089ad92ba36837a0d31433e555c8f45fe601ab5c221d4f607ded32d9f7a4349"
+    },
+    {
+      "path": "unet/config.json",
+      "sizeBytes": 1768,
+      "sha256": "34e7893a088737536ce0accd3f9d891c01d092886f88bbfa64a9091cb2501d13"
+    },
+    {
+      "path": "unet/diffusion_pytorch_model.safetensors",
+      "sizeBytes": 2662790608,
+      "sha256": "40d8ea9159f3e875278dacc7879442d58c45850cf13c62f5e26681061c51829a"
+    },
+    {
+      "path": "vae/config.json",
+      "sizeBytes": 602,
+      "sha256": "2e425cbde02bdb63e43e8d49db7e14a941a76bb7b2058761200c72dc3d6344fd"
+    },
+    {
+      "path": "vae/diffusion_pytorch_model.safetensors",
+      "sizeBytes": 167335342,
+      "sha256": "6353737672c94b96174cb590f711eac6edf2fcce5b6e91aa9d73c5adc589ee48"
+    }
+  ]
+}

README.md

@@ -1,34 +1,22 @@
-# Optima Tools — image-1
+---
+license: apache-2.0
+---
 
-> **Statut : En préparation — fichiers non publiés, exécution à valider.**
+# Optima Tools — image-low
 
-## Paquet
+SSD-1B — pipeline Diffusers FP16 : paquet complet pour Optima Tools (génération d’images).
 
-- **Paquet Optima Tools :** `image-1`
-- **Usage :** Génération d’image
-- **Niveau :** Léger
-- **Modèle envisagé :** SSD-1B FP16
+**Copie identique, octet pour octet, de fichiers publiés par leurs auteurs.** Dépôt d'origine : https://huggingface.co/segmind/SSD-1B (révision `60987f37e94cd59c36b1cba832b9f97b57395a10`). Seuls les noms de fichiers ci-dessous sont adaptés au chargement par Optima Tools ; leur contenu est inchangé.
 
-## Statut
+- `text_encoder/model.safetensors` ← `text_encoder/model.fp16.safetensors`
+- `text_encoder_2/model.safetensors` ← `text_encoder_2/model.fp16.safetensors`
+- `unet/diffusion_pytorch_model.safetensors` ← `unet/diffusion_pytorch_model.fp16.safetensors`
+- `vae/diffusion_pytorch_model.safetensors` ← `vae/diffusion_pytorch_model.fp16.safetensors`
 
-En préparation — fichiers non publiés, exécution à valider.
+## Licence
 
-Ce dépôt est une structure d’accueil : il ne contient pour l’instant aucun fichier de modèle, aucune empreinte SHA-256, aucune mesure de performance et aucun manifeste d’installation.
+Apache License 2.0 (Apache-2.0) : https://www.apache.org/licenses/LICENSE-2.0
 
-## Droits des auteurs d’origine
+## Vérification
 
-Les auteurs d’origine du modèle conservent l’ensemble de leurs droits. Optima Tools n’est pas le créateur de ce modèle : ce dépôt est destiné à en préparer la distribution vérifiée pour l’application Optima Tools, avec mention des sources, des licences et des crédits.
-
-## Sources, licences et crédits
-
-À compléter avant publication.
-
-La licence n’a pas été vérifiée à ce jour et n’est donc volontairement pas renseignée.
-
-## Fichiers du paquet
-
-À compléter.
-
-## Compatibilité matérielle
-
-Les exigences matérielles restent à mesurer. Aucune valeur n’est annoncée à ce stade.
+`.optima-package.json` liste la taille et l'empreinte SHA-256 de chaque fichier ; Optima Tools les vérifie à l'installation.

model_index.json

@@ -0,0 +1,33 @@
+{
+  "_class_name": "StableDiffusionXLPipeline",
+  "_diffusers_version": "0.19.0",
+  "force_zeros_for_empty_prompt": true,
+  "scheduler": [
+    "diffusers",
+    "EulerDiscreteScheduler"
+  ],
+  "text_encoder": [
+    "transformers",
+    "CLIPTextModel"
+  ],
+  "text_encoder_2": [
+    "transformers",
+    "CLIPTextModelWithProjection"
+  ],
+  "tokenizer": [
+    "transformers",
+    "CLIPTokenizer"
+  ],
+  "tokenizer_2": [
+    "transformers",
+    "CLIPTokenizer"
+  ],
+  "unet": [
+    "diffusers",
+    "UNet2DConditionModel"
+  ],
+  "vae": [
+    "diffusers",
+    "AutoencoderKL"
+  ]
+}

scheduler/scheduler_config.json

@@ -0,0 +1,18 @@
+{
+  "_class_name": "EulerDiscreteScheduler",
+  "_diffusers_version": "0.19.0",
+  "beta_end": 0.012,
+  "beta_schedule": "scaled_linear",
+  "beta_start": 0.00085,
+  "clip_sample": false,
+  "interpolation_type": "linear",
+  "num_train_timesteps": 1000,
+  "prediction_type": "epsilon",
+  "sample_max_value": 1.0,
+  "set_alpha_to_one": false,
+  "skip_prk_steps": true,
+  "steps_offset": 1,
+  "timestep_spacing": "leading",
+  "trained_betas": null,
+  "use_karras_sigmas": false
+}

text_encoder/config.json

@@ -0,0 +1,24 @@
+{
+  "architectures": [
+    "CLIPTextModel"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "dropout": 0.0,
+  "eos_token_id": 2,
+  "hidden_act": "quick_gelu",
+  "hidden_size": 768,
+  "initializer_factor": 1.0,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 77,
+  "model_type": "clip_text_model",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "projection_dim": 768,
+  "torch_dtype": "float32",
+  "transformers_version": "4.29.2",
+  "vocab_size": 49408
+}

text_encoder/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5487ea0eee9c9a9bff8abd097908d4deff3ae1fa87b3b67397f8b9538139d447
+size 246144864

text_encoder_2/config.json

@@ -0,0 +1,24 @@
+{
+  "architectures": [
+    "CLIPTextModelWithProjection"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "dropout": 0.0,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_size": 1280,
+  "initializer_factor": 1.0,
+  "initializer_range": 0.02,
+  "intermediate_size": 5120,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 77,
+  "model_type": "clip_text_model",
+  "num_attention_heads": 20,
+  "num_hidden_layers": 32,
+  "pad_token_id": 1,
+  "projection_dim": 1280,
+  "torch_dtype": "float32",
+  "transformers_version": "4.29.2",
+  "vocab_size": 49408
+}

text_encoder_2/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3df577f6e3799c8e1bd9b40e30133710e02e8e25d0ce48cdcc790e7dfe12d6d
+size 1389382880

tokenizer/special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<|startoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|endoftext|>",
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer/tokenizer_config.json

@@ -0,0 +1,33 @@
+{
+  "add_prefix_space": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<|startoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": true,
+  "do_lower_case": true,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "errors": "replace",
+  "model_max_length": 77,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "CLIPTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_2/special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<|startoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "!",
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_2/tokenizer_config.json

@@ -0,0 +1,33 @@
+{
+  "add_prefix_space": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<|startoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": true,
+  "do_lower_case": true,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "errors": "replace",
+  "model_max_length": 77,
+  "pad_token": "!",
+  "tokenizer_class": "CLIPTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

unet/config.json

@@ -0,0 +1,74 @@
+{
+  "_class_name": "UNet2DConditionModel",
+  "_diffusers_version": "0.19.0.dev0",
+  "act_fn": "silu",
+  "addition_embed_type": "text_time",
+  "addition_embed_type_num_heads": 64,
+  "addition_time_embed_dim": 256,
+  "attention_head_dim": [
+    5,
+    10,
+    20
+  ],
+  "block_out_channels": [
+    320,
+    640,
+    1280
+  ],
+  "center_input_sample": false,
+  "class_embed_type": null,
+  "class_embeddings_concat": false,
+  "conv_in_kernel": 3,
+  "conv_out_kernel": 3,
+  "cross_attention_dim": 2048,
+  "cross_attention_norm": null,
+  "down_block_types": [
+    "DownBlock2D",
+    "CrossAttnDownBlock2D",
+    "CrossAttnDownBlock2D"
+  ],
+  "downsample_padding": 1,
+  "dual_cross_attention": false,
+  "encoder_hid_dim": null,
+  "encoder_hid_dim_type": null,
+  "flip_sin_to_cos": true,
+  "freq_shift": 0,
+  "in_channels": 4,
+  "layers_per_block": 2,
+  "mid_block_only_cross_attention": null,
+  "mid_block_scale_factor": 1,
+  "mid_block_type": "UNetMidBlock2D",
+  "norm_eps": 1e-05,
+  "norm_num_groups": 32,
+  "num_attention_heads": null,
+  "num_class_embeds": null,
+  "only_cross_attention": false,
+  "out_channels": 4,
+  "projection_class_embeddings_input_dim": 2816,
+  "resnet_out_scale_factor": 1.0,
+  "resnet_skip_time_act": false,
+  "resnet_time_scale_shift": "default",
+  "sample_size": 128,
+  "time_cond_proj_dim": null,
+  "time_embedding_act_fn": null,
+  "time_embedding_dim": null,
+  "time_embedding_type": "positional",
+  "timestep_post_act": null,
+  "transformer_layers_per_block": [
+    [1],
+    [2,2],
+    [4,4]
+  ],
+  "reverse_transformer_layers_per_block": [
+      [4,4,10],
+      [2,1,1],
+      1
+  ],
+  "up_block_types": [
+    "CrossAttnUpBlock2D",
+    "CrossAttnUpBlock2D",
+    "UpBlock2D"
+  ],
+  "upcast_attention": null,
+  "use_linear_projection": true
+}

unet/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40d8ea9159f3e875278dacc7879442d58c45850cf13c62f5e26681061c51829a
+size 2662790608

vae/config.json

@@ -0,0 +1,31 @@
+{
+  "_class_name": "AutoencoderKL",
+  "_diffusers_version": "0.19.0",
+  "act_fn": "silu",
+  "block_out_channels": [
+    128,
+    256,
+    512,
+    512
+  ],
+  "down_block_types": [
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D"
+  ],
+  "force_upcast": true,
+  "in_channels": 3,
+  "latent_channels": 4,
+  "layers_per_block": 2,
+  "norm_num_groups": 32,
+  "out_channels": 3,
+  "sample_size": 1024,
+  "scaling_factor": 0.13025,
+  "up_block_types": [
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D"
+  ]
+}

vae/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6353737672c94b96174cb590f711eac6edf2fcce5b6e91aa9d73c5adc589ee48
+size 167335342