Upload 14 files

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 multiclip_tokenizer/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+tokenizer/tokenizer.json filter=lfs diff=lfs merge=lfs -text

model_index.json

@@ -0,0 +1,28 @@
+{
+  "_class_name": "KandinskyPipeline",
+  "_diffusers_version": "0.17.0.dev0",
+  "text_encoder": [
+    "kandinsky",
+    "MultilingualCLIP"
+  ],
+  "tokenizer": [
+    "transformers",
+    "XLMRobertaTokenizerFast"
+  ],
+  "scheduler": [
+    "diffusers",
+    "UnCLIPScheduler"
+  ],
+  "unet": [
+    "diffusers",
+    "UNet2DConditionModel"
+  ],
+  "text_proj": [
+    "kandinsky",
+    "KandinskyTextProjModel"
+  ],
+  "decoder": [
+    "diffusers",
+    "VQModel"
+  ]
+}

scheduler/scheduler_config.json

@@ -0,0 +1,16 @@
+{
+  "_class_name": "UnCLIPScheduler",
+  "_diffusers_version": "0.17.0.dev0",
+  "clip_sample": true,
+  "clip_sample_range": 2.0,
+  "sample_min_value": 1.0,
+  "sample_max_value": null,
+  "num_train_timesteps": 1000,
+  "prediction_type": "epsilon",
+  "variance_type": "learned_range",
+  "thresholding": true,
+  "beta_schedule": "linear",
+  "beta_start": 0.00085,
+  "beta_end":0.012
+  
+}

text_encoder/config.json

@@ -0,0 +1,12 @@
+{
+  "_name_or_path": "M-CLIP/XLM-Roberta-Large-Vit-L-14",
+  "architectures": [
+    "MultilingualCLIP"
+  ],
+  "modelBase": "xlm-roberta-large",
+  "model_type": "M-CLIP",
+  "numDims": 768,
+  "torch_dtype": "float32",
+  "transformerDimensions": 1024,
+  "transformers_version": "4.28.1"
+}

text_encoder/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:152bab8bc5813ec882ec634c7301978a0ef29340d4c17b3ae77b6468e017dfbe
+size 2242843757

text_proj/config.json

@@ -0,0 +1,9 @@
+{
+  "_class_name": "KandinskyTextProjModel",
+  "_diffusers_version": "0.17.0.dev0",
+  "clip_embeddings_dim": 768,
+  "clip_extra_context_tokens": 10,
+  "clip_text_encoder_hidden_states_dim": 1024,
+  "cross_attention_dim": 768,
+  "time_embed_dim": 1536
+}

text_proj/diffusion_pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a354d1a2b48e060baa48cac814d800540683392a88f3f39b884605e72feb1bcb
+size 36237255

tokenizer/sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
+size 5069051

tokenizer/special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11f3aa31ab2b0fa69e0e7f941f6badc4efd31066fb5221669ba55c48f5e6752a
+size 18082828

tokenizer/tokenizer_config.json

@@ -0,0 +1,19 @@
+{
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "__type": "AddedToken",
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}

unet/config.json

@@ -0,0 +1,60 @@
+{
+  "_class_name": "UNet2DConditionModel",
+  "_diffusers_version": "0.17.0.dev0",
+  "act_fn": "silu",
+  "addition_embed_type": null,
+  "addition_embed_type_num_heads": 64,
+  "attention_head_dim": 64,
+  "block_out_channels": [
+    384,
+    768,
+    1152,
+    1536
+  ],
+  "center_input_sample": false,
+  "class_embed_type": "identity",
+  "class_embeddings_concat": false,
+  "conv_in_kernel": 3,
+  "conv_out_kernel": 3,
+  "cross_attention_dim": 768,
+  "cross_attention_norm": null,
+  "down_block_types": [
+    "ResnetDownsampleBlock2D",
+    "SimpleCrossAttnDownBlock2D",
+    "SimpleCrossAttnDownBlock2D",
+    "SimpleCrossAttnDownBlock2D"
+  ],
+  "downsample_padding": 1,
+  "dual_cross_attention": false,
+  "encoder_hid_dim": null,
+  "flip_sin_to_cos": true,
+  "freq_shift": 0,
+  "in_channels": 4,
+  "layers_per_block": 3,
+  "mid_block_only_cross_attention": null,
+  "mid_block_scale_factor": 1,
+  "mid_block_type": "UNetMidBlock2DSimpleCrossAttn",
+  "norm_eps": 1e-05,
+  "norm_num_groups": 32,
+  "num_class_embeds": null,
+  "only_cross_attention": false,
+  "out_channels": 8,
+  "projection_class_embeddings_input_dim": null,
+  "resnet_out_scale_factor": 1.0,
+  "resnet_skip_time_act": false,
+  "resnet_time_scale_shift": "scale_shift",
+  "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,
+  "up_block_types": [
+    "SimpleCrossAttnUpBlock2D",
+    "SimpleCrossAttnUpBlock2D",
+    "SimpleCrossAttnUpBlock2D",
+    "ResnetUpsampleBlock2D"
+  ],
+  "upcast_attention": false,
+  "use_linear_projection": false
+}

unet/diffusion_pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26d7beb3feb041844df83c080c195bd45f2b6d7d992a6cbd0efbcd4aefadc696
+size 4878670709