Update

model_index.json

@@ -1,13 +1,17 @@
 {
   "_class_name": "BlipDiffusionPipeline",
   "_diffusers_version": "0.18.0.dev0",
+  "qformer": [
+    "src.diffusers.pipelines.blip_diffusion.modeling_blip2",
+    "Blip2QFormerModel"
+  ],
   "scheduler": [
     "diffusers",
-    "DDPMScheduler"
+    "PNDMScheduler"
   ],
   "text_encoder": [
-    null,
-    null
+    "src.diffusers.pipelines.blip_diffusion.modeling_ctx_clip",
+    "CtxCLIPTextModel"
   ],
   "tokenizer": [
     "transformers",
@@ -20,9 +24,5 @@
   "vae": [
     "diffusers",
     "AutoencoderKL"
-  ],
-  "vision_encoder": [
-    "src.diffusers.pipelines.blip_diffusion.modeling_blip2",
-    "Blip2VisionModel"
   ]
 }

qformer/config.json

@@ -0,0 +1,248 @@
+{
+  "_commit_hash": null,
+  "_name_or_path": "./blip2diffusion/qformer",
+  "architectures": [
+    "Blip2QFormerModel"
+  ],
+  "initializer_factor": 1.0,
+  "initializer_range": 0.02,
+  "model_type": "blip-2",
+  "num_query_tokens": 16,
+  "qformer_config": {
+    "_name_or_path": "",
+    "add_cross_attention": false,
+    "architectures": null,
+    "attention_probs_dropout_prob": 0.1,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": null,
+    "chunk_size_feed_forward": 0,
+    "cross_attention_frequency": 1,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "early_stopping": false,
+    "encoder_hidden_size": 1024,
+    "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_dropout_prob": 0.1,
+    "hidden_size": 768,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_range": 0.02,
+    "intermediate_size": 3072,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layer_norm_eps": 1e-12,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "max_position_embeddings": 512,
+    "min_length": 0,
+    "model_type": "blip_2_qformer",
+    "no_repeat_ngram_size": 0,
+    "num_attention_heads": 12,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_hidden_layers": 12,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": 0,
+    "position_embedding_type": "absolute",
+    "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": "4.31.0",
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "vocab_size": 30523
+  },
+  "text_config": {
+    "_name_or_path": "",
+    "_remove_final_layer_norm": false,
+    "activation_function": "relu",
+    "add_cross_attention": false,
+    "architectures": null,
+    "attention_dropout": 0.0,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": 2,
+    "chunk_size_feed_forward": 0,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_layer_norm_before": true,
+    "do_sample": false,
+    "dropout": 0.1,
+    "early_stopping": false,
+    "enable_bias": true,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": 2,
+    "exponential_decay_length_penalty": null,
+    "ffn_dim": 3072,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "hidden_size": 768,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "init_std": 0.02,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layer_norm_elementwise_affine": true,
+    "layerdrop": 0.0,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "max_position_embeddings": 2048,
+    "min_length": 0,
+    "model_type": "opt",
+    "no_repeat_ngram_size": 0,
+    "num_attention_heads": 12,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_hidden_layers": 12,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": 1,
+    "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": "4.31.0",
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "use_cache": true,
+    "vocab_size": 50272,
+    "word_embed_proj_dim": 768
+  },
+  "torch_dtype": "float32",
+  "transformers_version": null,
+  "use_decoder_only_language_model": true,
+  "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,
+    "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": "quick_gelu",
+    "hidden_size": 1024,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "image_size": 224,
+    "initializer_range": 1e-10,
+    "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,
+    "min_length": 0,
+    "model_type": "blip_2_vision_model",
+    "no_repeat_ngram_size": 0,
+    "num_attention_heads": 16,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_hidden_layers": 23,
+    "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": {},
+    "qkv_bias": true,
+    "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": "4.31.0",
+    "typical_p": 1.0,
+    "use_bfloat16": false
+  }
+}

qformer/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:709f641c6a2b4a932c51e57f14ebcb3b270efd9bbf31db0c34af7c208aa06bc6
+size 1976162665

scheduler/scheduler_config.json

@@ -1,19 +1,13 @@
 {
-  "_class_name": "DDPMScheduler",
+  "_class_name": "PNDMScheduler",
   "_diffusers_version": "0.16.0",
   "beta_end": 0.012,
   "beta_schedule": "scaled_linear",
   "beta_start": 0.00085,
-  "clip_sample": false,
-  "clip_sample_range": 1.0,
-  "dynamic_thresholding_ratio": 0.995,
   "num_train_timesteps": 1000,
   "prediction_type": "epsilon",
-  "sample_max_value": 1.0,
   "set_alpha_to_one": false,
   "skip_prk_steps": true,
-  "steps_offset": 1,
-  "thresholding": false,
-  "trained_betas": null,
-  "variance_type": "fixed_small"
+  "steps_offset": 0,
+  "trained_betas": null
 }

text_encoder/config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "./blipdiffusion_hf_ckpt/text_encoder",
+  "architectures": [
+    "CtxCLIPTextModel"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "dropout": 0.0,
+  "eos_token_id": 2,
+  "hidden_act": "quick_gelu",
+  "hidden_size": 768,
+  "initializer_factor": 1.0,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 77,
+  "model_type": "clip_text_model",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "projection_dim": 768,
+  "torch_dtype": "float32",
+  "transformers_version": "4.31.0",
+  "vocab_size": 49408
+}

text_encoder/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b374042419b2a5a28e7ee94503ff233719c7bd1345f5896ad982fdeff7c8cccc
+size 492307041

unet/config.json

@@ -1,7 +1,7 @@
 {
   "_class_name": "UNet2DConditionModel",
   "_diffusers_version": "0.16.0",
-  "_name_or_path": "runwayml/stable-diffusion-v1-5",
+  "_name_or_path": "./blipdiffusion_hf_ckpt/",
   "act_fn": "silu",
   "addition_embed_type": null,
   "addition_embed_type_num_heads": 64,

unet/diffusion_pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ebd8473673dfd403816acf5f09aa901c033246af9f6a3c62f3dd2580b78c8365
+oid sha256:c42d7cf4e4f028e3c955e13f4406231c946b602329de281b67c214f5efcb5137
 size 3438366373

vae/config.json

@@ -1,7 +1,7 @@
 {
   "_class_name": "AutoencoderKL",
   "_diffusers_version": "0.16.0",
-  "_name_or_path": "runwayml/stable-diffusion-v1-5",
+  "_name_or_path": "./blipdiffusion_hf_ckpt/",
   "act_fn": "silu",
   "block_out_channels": [
     128,