Upload folder using huggingface_hub

model_index.json

@@ -23,7 +23,7 @@
   ],
   "tokenizer": [
     "transformers",
-    "CLIPTokenizerFast"
+    "CLIPTokenizer"
   ],
   "tokenizer_2": [
     "transformers",

text_encoder/config.json

@@ -3,49 +3,21 @@
     "CLIPTextModel"
   ],
   "attention_dropout": 0.0,
+  "bos_token_id": 49406,
+  "eos_token_id": 49407,
   "hidden_act": "gelu",
   "hidden_size": 32,
   "initializer_factor": 1.0,
+  "initializer_range": 0.02,
   "intermediate_size": 37,
   "layer_norm_eps": 1e-05,
-  "logit_scale_init_value": 2.6592,
   "max_position_embeddings": 77,
-  "model_type": "clip",
-  "num_attention_heads": 8,
-  "num_hidden_layers": 1,
-  "projection_dim": 512,
-  "text_config": {
-    "attention_dropout": 0.0,
-    "hidden_act": "quick_gelu",
-    "hidden_size": 512,
-    "initializer_factor": 1.0,
-    "initializer_range": 0.02,
-    "intermediate_size": 2048,
-    "layer_norm_eps": 1e-05,
-    "max_position_embeddings": 77,
-    "model_type": "clip_text_model",
-    "num_attention_heads": 8,
-    "num_hidden_layers": 12,
-    "projection_dim": 512,
-    "vocab_size": 49408
-  },
+  "model_type": "clip_text_model",
+  "num_attention_heads": 4,
+  "num_hidden_layers": 5,
+  "pad_token_id": 1,
+  "projection_dim": 32,
   "torch_dtype": "float32",
-  "transformers_version": "4.54.0.dev0",
-  "vision_config": {
-    "attention_dropout": 0.0,
-    "hidden_act": "quick_gelu",
-    "hidden_size": 768,
-    "image_size": 224,
-    "initializer_factor": 1.0,
-    "initializer_range": 0.02,
-    "intermediate_size": 3072,
-    "layer_norm_eps": 1e-05,
-    "model_type": "clip_vision_model",
-    "num_attention_heads": 12,
-    "num_channels": 3,
-    "num_hidden_layers": 12,
-    "patch_size": 32,
-    "projection_dim": 512
-  },
-  "vocab_size": 49408
+  "transformers_version": "4.51.3",
+  "vocab_size": 1000
 }

text_encoder/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:17f380bc42c36b6074372fed8b6584b104757a744095b6f759d48e8fcd05d235
-size 6363756
+oid sha256:0ea36437f6030f4b55001bec74b64b37d793a27cac46cb6cc6c265547dd8a28d
+size 283212

text_encoder_2/config.json

@@ -22,7 +22,7 @@
   "relative_attention_max_distance": 128,
   "relative_attention_num_buckets": 32,
   "torch_dtype": "float32",
-  "transformers_version": "4.54.0.dev0",
+  "transformers_version": "4.51.3",
   "use_cache": true,
   "vocab_size": 32128
 }

text_encoder_2/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6cb317f3d2b86e1dcbda3df0af4371153a24f076a4925722e54790ec7532e9ba
+oid sha256:dd89137a066a2235d6d33c445166d1309701822a5c34ef3ef1cb5780fde800fd
 size 4275288

transformer/config.json

@@ -1,20 +1,19 @@
 {
   "_class_name": "FluxTransformer2DModel",
   "_diffusers_version": "0.35.0.dev0",
-  "_name_or_path": "black-forest-labs/FLUX.1-Kontext-dev",
-  "attention_head_dim": 4,
+  "attention_head_dim": 16,
   "axes_dims_rope": [
     16,
     56,
     56
   ],
-  "guidance_embeds": true,
-  "in_channels": 4,
-  "joint_attention_dim": 8,
+  "guidance_embeds": false,
+  "in_channels": 20,
+  "joint_attention_dim": 32,
   "num_attention_heads": 2,
   "num_layers": 1,
   "num_single_layers": 1,
   "out_channels": null,
   "patch_size": 1,
-  "pooled_projection_dim": 4
+  "pooled_projection_dim": 32
 }

transformer/diffusion_pytorch_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4edf5900823e06e6450458a03206a387d0066c3a7ea4ebe764d675e45f1552f9
-size 39752
+oid sha256:c33571d7e575700c18e9fbe7963fa2fe50a11303498933969e1265d2a684da77
+size 284504

vae/config.json

@@ -16,7 +16,7 @@
   ],
   "force_upcast": true,
   "in_channels": 3,
-  "latent_channels": 1,
+  "latent_channels": 2,
   "latents_mean": null,
   "latents_std": null,
   "layers_per_block": 1,

vae/diffusion_pytorch_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d36a13e223ad92a2491beb9f93232a27ac6289212e3d10cb55261e847f9ee804
-size 247108196
+oid sha256:cb1f6fd1391550257eb361ec4b01913b7b5c82986d8575fe22ee52b51f18eeb9
+size 247163572