End of training

README.md

@@ -1,41 +1,48 @@
+
 ---
-base_model: stabilityai/stable-diffusion-xl-base-1.0
-library_name: diffusers
-license: creativeml-openrail-m
+license: mit
+base_model: warp-ai/wuerstchen-prior
+datasets:
+- haorandai/Mammal_Mice_lr0.01_e0.1_20_with20constraints
 tags:
-- stable-diffusion-xl
-- stable-diffusion-xl-diffusers
+- wuerstchen
 - text-to-image
-- diffusers-training
 - diffusers
+- diffusers-training
 inference: true
 ---
+    
+# Finetuning - haorandai/temp
 
-<!-- This model card has been generated automatically according to the information the training script had access to. You
-should probably proofread and complete it, then remove this comment. -->
-
-
-# Text-to-image finetuning - haorandai/temp
-
-This pipeline was finetuned from **stabilityai/stable-diffusion-xl-base-1.0** on the **haorandai/Vehicle_Bicycle_lr0.01_e0.1_20_with20constraints** dataset. Below are some example images generated with the finetuned pipeline using the following prompt: None: 
-
-
+This pipeline was finetuned from **warp-ai/wuerstchen-prior** on the **haorandai/Mammal_Mice_lr0.01_e0.1_20_with20constraints** dataset. Below are some example images generated with the finetuned pipeline using the following prompts: ['An image of a mice and a cat']: 
 
-Special VAE used for training: None.
+![val_imgs_grid](./val_imgs_grid.png)
 
 
-## Intended uses & limitations
+## Pipeline usage
 
-#### How to use
+You can use the pipeline like so:
 
 ```python
-# TODO: add an example code snippet for running this diffusion pipeline
+from diffusers import DiffusionPipeline
+import torch
+
+pipe_prior = DiffusionPipeline.from_pretrained("haorandai/temp", torch_dtype=torch.float16)
+pipe_t2i = DiffusionPipeline.from_pretrained("warp-ai/wuerstchen", torch_dtype=torch.float16)
+prompt = "An image of a mice and a cat"
+(image_embeds,) = pipe_prior(prompt).to_tuple()
+image = pipe_t2i(image_embeddings=image_embeds, prompt=prompt).images[0]
+image.save("my_image.png")
 ```
 
-#### Limitations and bias
+## Training info
 
-[TODO: provide examples of latent issues and potential remediations]
+These are the key hyperparameters used during training:
 
-## Training details
+* Epochs: 40
+* Learning rate: 1e-05
+* Batch size: 1
+* Gradient accumulation steps: 4
+* Image resolution: 512
+* Mixed-precision: fp16
 
-[TODO: describe the data used to train the model]

prior_pipeline/model_index.json

@@ -0,0 +1,23 @@
+{
+  "_class_name": "WuerstchenPriorPipeline",
+  "_diffusers_version": "0.31.0.dev0",
+  "latent_mean": 42.0,
+  "latent_std": 1.0,
+  "prior": [
+    "wuerstchen",
+    "WuerstchenPrior"
+  ],
+  "resolution_multiple": 42.67,
+  "scheduler": [
+    "diffusers",
+    "DDPMWuerstchenScheduler"
+  ],
+  "text_encoder": [
+    "transformers",
+    "CLIPTextModel"
+  ],
+  "tokenizer": [
+    "transformers",
+    "PreTrainedTokenizerFast"
+  ]
+}

prior_pipeline/prior/config.json

@@ -0,0 +1,12 @@
+{
+  "_class_name": "WuerstchenPrior",
+  "_diffusers_version": "0.31.0.dev0",
+  "_name_or_path": "warp-ai/wuerstchen-prior",
+  "c": 1536,
+  "c_cond": 1280,
+  "c_in": 16,
+  "c_r": 64,
+  "depth": 32,
+  "dropout": 0.1,
+  "nhead": 24
+}

prior_pipeline/prior/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb130d24e0636f30311645c47211d824ad87784147510d1e8975fbc395763141
+size 3974614648

prior_pipeline/scheduler/scheduler_config.json

@@ -0,0 +1,6 @@
+{
+  "_class_name": "DDPMWuerstchenScheduler",
+  "_diffusers_version": "0.31.0.dev0",
+  "s": 0.008,
+  "scaler": 1.0
+}

prior_pipeline/text_encoder/config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "warp-ai/wuerstchen-prior",
+  "architectures": [
+    "CLIPTextModel"
+  ],
+  "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": 512,
+  "torch_dtype": "float16",
+  "transformers_version": "4.44.2",
+  "vocab_size": 49408
+}

prior_pipeline/text_encoder/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aef4e14fde660be314b0d0dcb6c705c843ac9146936cec9a9ed7ea668477c08c
+size 1386105272

prior_pipeline/tokenizer/special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<|startoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

prior_pipeline/tokenizer/tokenizer_config.json

@@ -0,0 +1,30 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "49406": {
+      "content": "<|startoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49407": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|startoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "do_lower_case": true,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "model_max_length": 77,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "unk_token": "<|endoftext|>"
+}