Upload WuerstchenCombinedPipeline

README.md

@@ -0,0 +1,198 @@
+---
+library_name: diffusers
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+This is the model card of a 🧨 diffusers model that has been pushed on the Hub. This model card has been automatically generated.
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]

decoder/config.json

@@ -0,0 +1,44 @@
+{
+  "_class_name": "WuerstchenDiffNeXt",
+  "_diffusers_version": "0.30.2",
+  "_name_or_path": "/root/.cache/huggingface/hub/models--warp-ai--wuerstchen/snapshots/c3da41406ddd4d9c48c49aa93981a82354351b83/decoder",
+  "blocks": [
+    4,
+    4,
+    14,
+    4
+  ],
+  "c_cond": 1024,
+  "c_hidden": [
+    320,
+    640,
+    1280,
+    1280
+  ],
+  "c_in": 4,
+  "c_out": 4,
+  "c_r": 64,
+  "clip_embd": 1024,
+  "dropout": 0.1,
+  "effnet_embd": 16,
+  "inject_effnet": [
+    false,
+    true,
+    true,
+    true
+  ],
+  "kernel_size": 3,
+  "level_config": [
+    "CT",
+    "CTA",
+    "CTA",
+    "CTA"
+  ],
+  "nhead": [
+    -1,
+    10,
+    20,
+    20
+  ],
+  "patch_size": 2
+}

decoder/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5691820999485b22f413b27c9643ebd7464294cf765f9f372ba2c46ec144ccc6
+size 2110837264

model_index.json

@@ -0,0 +1,41 @@
+{
+  "_class_name": "WuerstchenCombinedPipeline",
+  "_diffusers_version": "0.30.2",
+  "_name_or_path": "warp-ai/wuerstchen",
+  "decoder": [
+    "wuerstchen",
+    "WuerstchenDiffNeXt"
+  ],
+  "prior_prior": [
+    "wuerstchen",
+    "WuerstchenPrior"
+  ],
+  "prior_scheduler": [
+    "diffusers",
+    "DDPMWuerstchenScheduler"
+  ],
+  "prior_text_encoder": [
+    "transformers",
+    "CLIPTextModel"
+  ],
+  "prior_tokenizer": [
+    "transformers",
+    "CLIPTokenizerFast"
+  ],
+  "scheduler": [
+    "diffusers",
+    "DDPMWuerstchenScheduler"
+  ],
+  "text_encoder": [
+    "transformers",
+    "CLIPTextModel"
+  ],
+  "tokenizer": [
+    "transformers",
+    "CLIPTokenizerFast"
+  ],
+  "vqgan": [
+    "wuerstchen",
+    "PaellaVQModel"
+  ]
+}

prior_prior/config.json

@@ -0,0 +1,12 @@
+{
+  "_class_name": "WuerstchenPrior",
+  "_diffusers_version": "0.30.2",
+  "_name_or_path": "/root/.cache/huggingface/hub/models--warp-diffusion--wuerstchen-prior/snapshots/c41be6339e1b93f95ece99825327cdf9f4abc436/prior",
+  "c": 1536,
+  "c_cond": 1280,
+  "c_in": 16,
+  "c_r": 64,
+  "depth": 32,
+  "dropout": 0.1,
+  "nhead": 24
+}

prior_prior/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d1265e1856d333b1adbf8ec32aaeda44f5f850b706881947a161de649771912
+size 1987340504

prior_scheduler/scheduler_config.json

@@ -0,0 +1,6 @@
+{
+  "_class_name": "DDPMWuerstchenScheduler",
+  "_diffusers_version": "0.30.2",
+  "s": 0.008,
+  "scaler": 1.0
+}

prior_text_encoder/config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "/root/.cache/huggingface/hub/models--warp-diffusion--wuerstchen-prior/snapshots/c41be6339e1b93f95ece99825327cdf9f4abc436/text_encoder",
+  "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_text_encoder/model.safetensors

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

prior_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_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": "CLIPTokenizer",
+  "unk_token": "<|endoftext|>"
+}

scheduler/scheduler_config.json

@@ -0,0 +1,6 @@
+{
+  "_class_name": "DDPMWuerstchenScheduler",
+  "_diffusers_version": "0.30.2",
+  "s": 0.008,
+  "scaler": 1.0
+}

text_encoder/config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "/root/.cache/huggingface/hub/models--warp-ai--wuerstchen/snapshots/c3da41406ddd4d9c48c49aa93981a82354351b83/text_encoder",
+  "architectures": [
+    "CLIPTextModel"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "dropout": 0.0,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_size": 1024,
+  "initializer_factor": 1.0,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 77,
+  "model_type": "clip_text_model",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 1,
+  "projection_dim": 1024,
+  "torch_dtype": "float16",
+  "transformers_version": "4.44.2",
+  "vocab_size": 49408
+}

text_encoder/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0eb4cf70d7768f4f61bb25e98b2ddaf545f6b33ecc2d7cc3eaa4670a09722fd2
+size 706014768

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
+  }
+}

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": "CLIPTokenizer",
+  "unk_token": "<|endoftext|>"
+}

vqgan/config.json

@@ -0,0 +1,14 @@
+{
+  "_class_name": "PaellaVQModel",
+  "_diffusers_version": "0.30.2",
+  "_name_or_path": "/root/.cache/huggingface/hub/models--warp-ai--wuerstchen/snapshots/c3da41406ddd4d9c48c49aa93981a82354351b83/vqgan",
+  "bottleneck_blocks": 12,
+  "embed_dim": 384,
+  "in_channels": 3,
+  "latent_channels": 4,
+  "levels": 2,
+  "num_vq_embeddings": 8192,
+  "out_channels": 3,
+  "scale_factor": 0.3764,
+  "up_down_scale_factor": 2
+}

vqgan/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:491e14e929e290fc198428fe2bc714ff5e71cf7778db04447a50528c7e3d019c
+size 36825700