initial commit

README.md

@@ -0,0 +1,106 @@
+# Model Card for PickScore v1
+
+This model is a scoring function for images generated from text. It takes as input a prompt and a generated image and outputs a score. 
+It can be used as a general scoring function, and for tasks such as human preference prediction, model evaluation, image ranking, and more. 
+See our paper [Pick-a-Pic: An Open Dataset of User Preferences for Text-to-Image Generation](https://arxiv.org/abs/2305.01569) for more details.
+
+
+## Model Details
+
+### Model Description
+
+This model was finetuned from CLIP-H using the [Pick-a-Pic dataset](https://huggingface.co/datasets/yuvalkirstain/pickapic_v1).
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [See the PickScore repo](https://github.com/yuvalkirstain/PickScore)
+- **Paper:** [Pick-a-Pic: An Open Dataset of User Preferences for Text-to-Image Generation](https://arxiv.org/abs/2305.01569).
+- **Demo [optional]:** [Huggingface Spaces demo for PickScore](https://huggingface.co/spaces/yuvalkirstain/PickScore)
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+```python
+# import
+from transformers import AutoProcessor, AutoModel
+
+# load model
+device = "cuda"
+processor_name_or_path = "laion/CLIP-ViT-H-14-laion2B-s32B-b79K"
+model_pretrained_name_or_path = "yuvalkirstain/PickScore_v1"
+
+processor = AutoProcessor.from_pretrained(processor_name_or_path)
+model = AutoModel.from_pretrained(model_pretrained_name_or_path).eval().to(device)
+
+def calc_probs(prompt, images):
+    
+    # preprocess
+    image_inputs = processor(
+        images=images,
+        padding=True,
+        truncation=True,
+        max_length=77,
+        return_tensors="pt",
+    ).to(device)
+    
+    text_inputs = processor(
+        text=prompt,
+        padding=True,
+        truncation=True,
+        max_length=77,
+        return_tensors="pt",
+    ).to(device)
+
+
+    with torch.no_grad():
+        # embed
+        image_embs = model.get_image_features(**image_inputs)
+        image_embs = image_embs / torch.norm(image_embs, dim=-1, keepdim=True)
+    
+        text_embs = model.get_text_features(**text_inputs)
+        text_embs = text_embs / torch.norm(text_embs, dim=-1, keepdim=True)
+    
+        # score
+        scores = model.logit_scale.exp() * (text_embs @ image_embs.T)[0]
+        
+        # get probabilities if you have multiple images to choose from
+        probs = torch.softmax(scores, dim=-1)
+    
+    return probs.cpu().tolist()
+
+pil_images = [Image.open("my_amazing_images/1.jpg"), Image.open("my_amazing_images/2.jpg")]
+prompt = "fantastic, increadible prompt"
+print(calc_probs(prompt, pil_images))
+```
+## Training Details
+
+### Training Data
+
+This model was trained on the [Pick-a-Pic dataset](https://huggingface.co/datasets/yuvalkirstain/pickapic_v1).
+
+
+### Training Procedure 
+
+TODO - add paper.
+
+
+## Citation [optional]
+
+If you find this work useful, please cite:
+
+```bibtex
+@inproceedings{Kirstain2023PickaPicAO,
+  title={Pick-a-Pic: An Open Dataset of User Preferences for Text-to-Image Generation},
+  author={Yuval Kirstain and Adam Polyak and Uriel Singer and Shahbuland Matiana and Joe Penna and Omer Levy},
+  year={2023}
+}
+```
+
+**APA:**
+
+[More Information Needed]
+
+

config.json

@@ -0,0 +1,168 @@
+{
+  "_commit_hash": null,
+  "_name_or_path": "/fsx/yuval/preference_predictor_v2",
+  "architectures": [
+    "CLIPModel"
+  ],
+  "initializer_factor": 1.0,
+  "logit_scale_init_value": 2.6592,
+  "model_type": "clip",
+  "projection_dim": 1024,
+  "text_config": {
+    "_name_or_path": "",
+    "add_cross_attention": false,
+    "architectures": null,
+    "attention_dropout": 0.0,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": 0,
+    "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": 2,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "hidden_act": "gelu",
+    "hidden_size": 1024,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_factor": 1.0,
+    "initializer_range": 0.02,
+    "intermediate_size": 4096,
+    "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,
+    "max_position_embeddings": 77,
+    "min_length": 0,
+    "model_type": "clip_text_model",
+    "no_repeat_ngram_size": 0,
+    "num_attention_heads": 16,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_hidden_layers": 24,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": 1,
+    "prefix": null,
+    "problem_type": null,
+    "projection_dim": 1024,
+    "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": "4.27.3",
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "vocab_size": 49408
+  },
+  "torch_dtype": "float32",
+  "transformers_version": null,
+  "vision_config": {
+    "_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": 1280,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "image_size": 224,
+    "initializer_factor": 1.0,
+    "initializer_range": 0.02,
+    "intermediate_size": 5120,
+    "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": 32,
+    "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,
+    "projection_dim": 1024,
+    "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": "4.27.3",
+    "typical_p": 1.0,
+    "use_bfloat16": false
+  }
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef31ef6fc5ff4d9bb90dd232df4e145887ba62c5a03aa2841415f8c25f18d52e
+size 3944552236

preprocessor_config.json

@@ -0,0 +1,29 @@
+{
+  "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
+  ],
+  "processor_class": "CLIPProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "shortest_edge": 224
+  }
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f0cf1c6e533f478534404cb3ca6938103becbfe4312c6affc077c274a757972
+size 3944742093

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_config.json

@@ -0,0 +1,34 @@
+{
+  "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|>",
+  "processor_class": "CLIPProcessor",
+  "tokenizer_class": "CLIPTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}