Add img2img model

.gitattributes

@@ -32,3 +32,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* 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": "KandinskyImg2ImgPipeline",
+  "_diffusers_version": "0.17.0.dev0",
+  "movq": [
+    "diffusers",
+    "VQModel"
+  ],
+  "scheduler": [
+    "diffusers",
+    "DDPMScheduler"
+  ],
+  "text_encoder": [
+    "kandinsky",
+    "MultilingualCLIP"
+  ],
+  "text_proj": [
+    "kandinsky",
+    "KandinskyTextProjModel"
+  ],
+  "tokenizer": [
+    "transformers",
+    "XLMRobertaTokenizerFast"
+  ],
+  "unet": [
+    "diffusers",
+    "UNet2DConditionModel"
+  ]
+}

movq/config.json

@@ -0,0 +1,34 @@
+{
+  "_class_name": "VQModel",
+  "_diffusers_version": "0.17.0.dev0",
+  "_name_or_path": "E:\\Kandinksy\\models--YiYiXu--Kandinsky\\snapshots\\c040bbdee2e718caa2c94566b36c8e34413f9f77\\movq",
+  "act_fn": "silu",
+  "block_out_channels": [
+    128,
+    256,
+    256,
+    512
+  ],
+  "down_block_types": [
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D",
+    "AttnDownEncoderBlock2D"
+  ],
+  "in_channels": 3,
+  "latent_channels": 4,
+  "layers_per_block": 2,
+  "norm_num_groups": 32,
+  "norm_type": "spatial",
+  "num_vq_embeddings": 16384,
+  "out_channels": 3,
+  "sample_size": 32,
+  "scaling_factor": 0.18215,
+  "up_block_types": [
+    "AttnUpDecoderBlock2D",
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D"
+  ],
+  "vq_embed_dim": 4
+}

movq/diffusion_pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ce923fc147d30510b4625a70f66b534602b7311a74405778a96efeceedf5212
+size 271499699

scheduler/scheduler_config.json

@@ -0,0 +1,16 @@
+{
+  "_class_name": "DDPMScheduler",
+  "_diffusers_version": "0.17.0.dev0",
+  "beta_end": 0.012,
+  "beta_schedule": "linear",
+  "beta_start": 0.00085,
+  "clip_sample": true,
+  "clip_sample_range": 2.0,
+  "dynamic_thresholding_ratio": 0.995,
+  "num_train_timesteps": 1000,
+  "prediction_type": "epsilon",
+  "sample_max_value": null,
+  "thresholding": true,
+  "trained_betas": null,
+  "variance_type": "learned_range"
+}

text_encoder/config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "E:\\Kandinksy\\models--YiYiXu--Kandinsky\\snapshots\\c040bbdee2e718caa2c94566b36c8e34413f9f77\\text_encoder",
+  "architectures": [
+    "MultilingualCLIP"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "M-CLIP",
+  "numDims": 768,
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformerDimensions": 1024,
+  "transformers_version": "4.29.1",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

text_encoder/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91eecf22fea2a52a3e86ec3ea25f6f6b766a7c979e0456623d1126609842f7f6
+size 2242846645

text_proj/config.json

@@ -0,0 +1,10 @@
+{
+  "_class_name": "KandinskyTextProjModel",
+  "_diffusers_version": "0.17.0.dev0",
+  "_name_or_path": "E:\\Kandinksy\\models--YiYiXu--Kandinsky\\snapshots\\c040bbdee2e718caa2c94566b36c8e34413f9f77\\text_proj",
+  "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 sha256:90f67079bad6df9b6f1b697e7ddbfa2f629d980b2569063732e2ec30f453431d
+size 36238087

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 sha256:62c24cdc13d4c9952d63718d6c9fa4c287974249e16b7ade6d5a85e7bbb75626
+size 17082660

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 +1,61 @@
+{
+  "_class_name": "UNet2DConditionModel",
+  "_diffusers_version": "0.17.0.dev0",
+  "_name_or_path": "E:\\Kandinksy\\models--YiYiXu--Kandinsky\\snapshots\\c040bbdee2e718caa2c94566b36c8e34413f9f77\\unet",
+  "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 sha256:41c11f4bfbfc86b78546a9b397b556dd242c59fd07bb51ea876bcc9a574114db
+size 4878682709