Upload folder using huggingface_hub

README.md

@@ -0,0 +1,5 @@
+---
+license: apache-2.0
+---
+
+Coming soon!

experts/global.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37eb394f655596166035d4d92477437a26dbe44ae0270e8c9d34a56a7f199cd2
+size 197560149

experts/task_embs.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d85f4ae06fb6d461dcb9a4850503fe4a4d192e648c89fc8ca3036e3b626cdad
+size 44243

experts/viewpoint.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af1824b3830ceeb0fbea398ae50ae192124d0e2d2f2ddab4da28a9031c5a0d8f
+size 197560149

experts/visual_bbox.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67b13ccc8cae73e70e04a02515379e94e47735e81ef2c601f80a295d0810b2cb
+size 197560149

experts/visual_dep.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e358f4c53f0767ed80c9cf85cc89812ae9832a844cd00daca688a6ba2551c130
+size 197560149

experts/visual_mat.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c7f5bde1147eb53104a0564a52580ea9a45831bb59742e2d2488158ecfa75f8
+size 197560149

experts/visual_ref.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae0ef315d1ab40b2c6adebdd6859c6f28a28be81416c6df1cecd9ba31d628b20
+size 197560149

experts/visual_scr.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d837cb848fe38819070ea9f15853aaf831178b8e775d67ca7d4bb0540571df19
+size 197560149

experts/visual_seg.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7cb5937e1323007bffbf1ad38cde58c009865a8a90a3f9e7af4d35fb618900ab
+size 197560149

experts/visual_ske.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4ba66a05e188ac25109e149f1d44e81fdfb56bf23f5afde463744d600d4c7c2
+size 197560149

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
+}

image_encoder/model.safetensors

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

unet/config.json

@@ -0,0 +1,68 @@
+{
+  "_class_name": "UNet2DConditionModel",
+  "_diffusers_version": "0.31.0.dev0",
+  "_name_or_path": "/home2/yqf/FLUX_Edit/AnyDM/instruct-pix2pix-model/stage1-sd15/checkpoint-53200",
+  "act_fn": "silu",
+  "addition_embed_type": null,
+  "addition_embed_type_num_heads": 64,
+  "addition_time_embed_dim": null,
+  "attention_head_dim": 8,
+  "attention_type": "default",
+  "block_out_channels": [
+    320,
+    640,
+    1280,
+    1280
+  ],
+  "center_input_sample": false,
+  "class_embed_type": null,
+  "class_embeddings_concat": false,
+  "conv_in_kernel": 3,
+  "conv_out_kernel": 3,
+  "cross_attention_dim": 768,
+  "cross_attention_norm": null,
+  "down_block_types": [
+    "CrossAttnDownBlock2D",
+    "CrossAttnDownBlock2D",
+    "CrossAttnDownBlock2D",
+    "DownBlock2D"
+  ],
+  "downsample_padding": 1,
+  "dropout": 0.0,
+  "dual_cross_attention": false,
+  "encoder_hid_dim": null,
+  "encoder_hid_dim_type": null,
+  "flip_sin_to_cos": true,
+  "freq_shift": 0,
+  "in_channels": 8,
+  "layers_per_block": 2,
+  "mid_block_only_cross_attention": null,
+  "mid_block_scale_factor": 1,
+  "mid_block_type": "UNetMidBlock2DCrossAttn",
+  "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": null,
+  "resnet_out_scale_factor": 1.0,
+  "resnet_skip_time_act": false,
+  "resnet_time_scale_shift": "default",
+  "reverse_transformer_layers_per_block": null,
+  "sample_size": 64,
+  "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,
+  "up_block_types": [
+    "UpBlock2D",
+    "CrossAttnUpBlock2D",
+    "CrossAttnUpBlock2D",
+    "CrossAttnUpBlock2D"
+  ],
+  "upcast_attention": false,
+  "use_linear_projection": false
+}

unet/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33303b849e26287339e19e7d490c3f8d408ebd325e68f2a32281bdb3bba3748c
+size 3438213624