Upload model

README.md

@@ -0,0 +1,200 @@
+---
+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]
+
+

config.json

@@ -0,0 +1,115 @@
+{
+  "_class_name": "ForwardModelUNet2DConditionModel",
+  "_diffusers_version": "0.26.3",
+  "_name_or_path": "ckpts/unet_lgm",
+  "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,
+  "lgm_cam_radius": 1.5,
+  "lgm_down_attention": [
+    false,
+    false,
+    false,
+    true,
+    true,
+    true
+  ],
+  "lgm_down_channels": [
+    64,
+    128,
+    256,
+    512,
+    1024,
+    1024
+  ],
+  "lgm_fovy": 49.1343,
+  "lgm_input_size": 256,
+  "lgm_mid_attention": true,
+  "lgm_output_size": 512,
+  "lgm_splat_size": 128,
+  "lgm_up_attention": [
+    true,
+    true,
+    true,
+    false,
+    false
+  ],
+  "lgm_up_channels": [
+    1024,
+    1024,
+    512,
+    256,
+    128
+  ],
+  "lgm_zfar": 2.5,
+  "lgm_znear": 0.5,
+  "num_train_timesteps": 1000,
+  "prediction_type": "epsilon",
+  "rescale_betas_zero_snr": false,
+  "sample_max_value": 1.0,
+  "set_alpha_to_one": false,
+  "thresholding": false,
+  "unet_adm_in_channels": null,
+  "unet_attention_resolutions": [
+    4,
+    2,
+    1
+  ],
+  "unet_camera_dim": 16,
+  "unet_channel_mult": [
+    1,
+    2,
+    4,
+    4
+  ],
+  "unet_context_dim": 1024,
+  "unet_conv_resample": true,
+  "unet_dims": 2,
+  "unet_dropout": 0,
+  "unet_image_size": 32,
+  "unet_in_channels": 4,
+  "unet_ip_dim": 16,
+  "unet_ip_weight": 1.0,
+  "unet_model_channels": 320,
+  "unet_n_embed": null,
+  "unet_num_attention_blocks": null,
+  "unet_num_classes": null,
+  "unet_num_head_channels": 64,
+  "unet_num_heads": -1,
+  "unet_num_heads_upsample": -1,
+  "unet_num_res_blocks": 2,
+  "unet_out_channels": 4,
+  "unet_resblock_updown": false,
+  "unet_transformer_depth": 1,
+  "unet_use_scale_shift_norm": false,
+  "vae_act_fn": "silu",
+  "vae_block_out_channels": [
+    128,
+    256,
+    512,
+    512
+  ],
+  "vae_down_block_types": [
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D"
+  ],
+  "vae_force_upcast": true,
+  "vae_in_channels": 3,
+  "vae_latent_channels": 4,
+  "vae_layers_per_block": 2,
+  "vae_norm_num_groups": 32,
+  "vae_out_channels": 3,
+  "vae_sample_size": 512,
+  "vae_scaling_factor": 0.18215,
+  "vae_up_block_types": [
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D"
+  ]
+}

diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ee864adadd756f6ae963eab1a8e1f993ce6cde67685bc09d243571a72250ddf
+size 2880905326