diff --git a/weights/sdxl_models/image_encoder/config.json b/weights/sdxl_models/image_encoder/config.json
new file mode 100644
index 0000000..c3868ba
--- /dev/null
+++ b/weights/sdxl_models/image_encoder/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
+}