End of training

README.md

@@ -0,0 +1,49 @@
+
+---
+license: creativeml-openrail-m
+base_model: kandinsky-community/kandinsky-2-2-prior
+datasets:
+- lambdalabs/pokemon-blip-captions
+tags:
+- kandinsky
+- text-to-image
+- diffusers
+inference: true
+---
+    
+# Finetuning - YiYiXu/kandinsky_prior_pokemon
+
+This pipeline was finetuned from **kandinsky-community/kandinsky-2-2-prior** on the **lambdalabs/pokemon-blip-captions** dataset. Below are some example images generated with the finetuned pipeline using the following prompts: ['A robot pokemon, 4k photo']: 
+
+![val_imgs_grid](./val_imgs_grid.png)
+
+
+## Pipeline usage
+
+You can use the pipeline like so:
+
+```python
+from diffusers import DiffusionPipeline
+import torch
+
+pipe_prior = DiffusionPipeline.from_pretrained("YiYiXu/kandinsky_prior_pokemon", torch_dtype=torch.float16)
+pipe_t2i = DiffusionPipeline.from_pretrained("kandinsky-community/kandinsky-2-2-decoder", torch_dtype=torch.float16)
+prompt = "A robot pokemon, 4k photo"
+image_embeds, negative_image_embeds = pipe_prior(prompt, guidance_scale=1.0).to_tuple()
+image = pipe_t2i(image_embeds=image_embeds, negative_image_embeds=negative_image_embeds).images[0]
+image.save("my_image.png")
+```
+
+## Training info
+
+These are the key hyperparameters used during training:
+
+* Epochs: 2
+* Learning rate: 1e-05
+* Batch size: 1
+* Gradient accumulation steps: 1
+* Image resolution: 768
+* Mixed-precision: fp16
+
+
+More information on all the CLI arguments and the environment are available on your [`wandb` run page](https://wandb.ai/yiyixu/text2image-fine-tune/runs/90ljjfwe).

checkpoint-10/optimizer.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f68f907d03df6e3a81c829f260b9dd9debf1ed754a550df8008384b6e1ccf8d2
+size 8210072757

checkpoint-10/prior/config.json

@@ -0,0 +1,20 @@
+{
+  "_class_name": "PriorTransformer",
+  "_diffusers_version": "0.21.0.dev0",
+  "_name_or_path": "kandinsky-community/kandinsky-2-2-prior",
+  "added_emb_type": "prd",
+  "additional_embeddings": 4,
+  "attention_head_dim": 64,
+  "clip_embed_dim": null,
+  "dropout": 0.0,
+  "embedding_dim": 1280,
+  "embedding_proj_dim": null,
+  "embedding_proj_norm_type": null,
+  "encoder_hid_proj_type": "linear",
+  "norm_in_type": null,
+  "num_attention_heads": 32,
+  "num_embeddings": 77,
+  "num_layers": 20,
+  "time_embed_act_fn": "silu",
+  "time_embed_dim": null
+}

checkpoint-10/prior/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d15ab9af57d6dc140dd3bbc69470be7964a1f87726082c8046ea0961d76f5d3f
+size 4104940968

checkpoint-10/random_states_0.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aec06db37fd6db7b53d1a0c498ae6afc0dbc645b54432a4a990a7943dc760e7d
+size 14599

checkpoint-10/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:285e76ebe66a23f043b42182e14294a93d529fdc5c0c08159fd9fc10bbeaad36
+size 557

checkpoint-10/scheduler.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40d0b17e9c9b0baf0c44a59b9d7e8b78aed0545d5ab2b9d9d9dbb13aed8db9e8
+size 563

checkpoint-5/optimizer.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e9fb5f161bd4a6a550b934cc266b8a08806d8c7d6b7b34e812553bc8cee7b1b
+size 8210072757

checkpoint-5/prior/config.json

@@ -0,0 +1,20 @@
+{
+  "_class_name": "PriorTransformer",
+  "_diffusers_version": "0.21.0.dev0",
+  "_name_or_path": "kandinsky-community/kandinsky-2-2-prior",
+  "added_emb_type": "prd",
+  "additional_embeddings": 4,
+  "attention_head_dim": 64,
+  "clip_embed_dim": null,
+  "dropout": 0.0,
+  "embedding_dim": 1280,
+  "embedding_proj_dim": null,
+  "embedding_proj_norm_type": null,
+  "encoder_hid_proj_type": "linear",
+  "norm_in_type": null,
+  "num_attention_heads": 32,
+  "num_embeddings": 77,
+  "num_layers": 20,
+  "time_embed_act_fn": "silu",
+  "time_embed_dim": null
+}

checkpoint-5/prior/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:917dfaab7d9d50a2272c0c67353809e2f2744b6faa72a1d9048a05473e0691b1
+size 4104940968

checkpoint-5/random_states_0.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef25d2441df4b7554fef43f3fd3f16bee2eef325f36552193085a890974f4e47
+size 14599

checkpoint-5/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4226304fb62e961f1febc70be2db3d4aa0fa092f6ffb6147df348b679da41079
+size 557

checkpoint-5/scheduler.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1894240ca421fa02ed0c3d0e2575cbea2b8fd81af0b78468586be461b7937ec6
+size 563

image_encoder/config.json

@@ -0,0 +1,23 @@
+{
+  "_name_or_path": "kandinsky-community/kandinsky-2-2-prior",
+  "architectures": [
+    "CLIPVisionModelWithProjection"
+  ],
+  "attention_dropout": 0.0,
+  "dropout": 0.0,
+  "hidden_act": "gelu",
+  "hidden_size": 1664,
+  "image_size": 224,
+  "initializer_factor": 1.0,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "layer_norm_eps": 1e-05,
+  "model_type": "clip_vision_model",
+  "num_attention_heads": 16,
+  "num_channels": 3,
+  "num_hidden_layers": 48,
+  "patch_size": 14,
+  "projection_dim": 1280,
+  "torch_dtype": "float16",
+  "transformers_version": "4.33.0"
+}

image_encoder/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dabf125eaf7f339da6b900a7a14f8190f02913b7d46cab80e09cd0755c4ce39c
+size 3689910512

image_processor/preprocessor_config.json

@@ -0,0 +1,28 @@
+{
+  "crop_size": {
+    "height": 224,
+    "width": 224
+  },
+  "do_center_crop": true,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "feature_extractor_type": "CLIPFeatureExtractor",
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_processor_type": "CLIPImageProcessor",
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "shortest_edge": 224
+  }
+}

model_index.json

@@ -0,0 +1,28 @@
+{
+  "_class_name": "KandinskyV22PriorPipeline",
+  "_diffusers_version": "0.21.0.dev0",
+  "image_encoder": [
+    "transformers",
+    "CLIPVisionModelWithProjection"
+  ],
+  "image_processor": [
+    "transformers",
+    "CLIPImageProcessor"
+  ],
+  "prior": [
+    "diffusers",
+    "PriorTransformer"
+  ],
+  "scheduler": [
+    "diffusers",
+    "UnCLIPScheduler"
+  ],
+  "text_encoder": [
+    "transformers",
+    "CLIPTextModelWithProjection"
+  ],
+  "tokenizer": [
+    "transformers",
+    "CLIPTokenizer"
+  ]
+}

prior/config.json

@@ -0,0 +1,20 @@
+{
+  "_class_name": "PriorTransformer",
+  "_diffusers_version": "0.21.0.dev0",
+  "_name_or_path": "kandinsky-community/kandinsky-2-2-prior",
+  "added_emb_type": "prd",
+  "additional_embeddings": 4,
+  "attention_head_dim": 64,
+  "clip_embed_dim": null,
+  "dropout": 0.0,
+  "embedding_dim": 1280,
+  "embedding_proj_dim": null,
+  "embedding_proj_norm_type": null,
+  "encoder_hid_proj_type": "linear",
+  "norm_in_type": null,
+  "num_attention_heads": 32,
+  "num_embeddings": 77,
+  "num_layers": 20,
+  "time_embed_act_fn": "silu",
+  "time_embed_dim": null
+}

prior/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d15ab9af57d6dc140dd3bbc69470be7964a1f87726082c8046ea0961d76f5d3f
+size 4104940968

scheduler/scheduler_config.json

@@ -0,0 +1,10 @@
+{
+  "_class_name": "UnCLIPScheduler",
+  "_diffusers_version": "0.21.0.dev0",
+  "beta_schedule": "squaredcos_cap_v2",
+  "clip_sample": true,
+  "clip_sample_range": 10.0,
+  "num_train_timesteps": 1000,
+  "prediction_type": "sample",
+  "variance_type": "fixed_small_log"
+}

text_encoder/config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "kandinsky-community/kandinsky-2-2-prior",
+  "architectures": [
+    "CLIPTextModelWithProjection"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "dropout": 0.0,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_size": 1280,
+  "initializer_factor": 1.0,
+  "initializer_range": 0.02,
+  "intermediate_size": 5120,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 77,
+  "model_type": "clip_text_model",
+  "num_attention_heads": 20,
+  "num_hidden_layers": 32,
+  "pad_token_id": 1,
+  "projection_dim": 1280,
+  "torch_dtype": "float16",
+  "transformers_version": "4.33.0",
+  "vocab_size": 49408
+}

text_encoder/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec310df2af79c318e24d20511b601a591ca8cd4f1fce1d8dff822a356bcdb1f4
+size 1389382176

tokenizer/special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<|startoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|endoftext|>",
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer/tokenizer_config.json

@@ -0,0 +1,33 @@
+{
+  "add_prefix_space": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<|startoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": true,
+  "do_lower_case": true,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "errors": "replace",
+  "model_max_length": 77,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "CLIPTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}