Duplicate from diffusers/sd-to-diffusers

Co-authored-by: Patrick von Platen <patrickvonplaten@users.noreply.huggingface.co>

.gitattributes

@@ -0,0 +1,34 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,14 @@
+---
+title: SD To Diffusers
+emoji: 🎨➡️🧨
+colorFrom: indigo
+colorTo: blue
+sdk: gradio
+sdk_version: 3.9.1
+app_file: app.py
+pinned: false
+license: mit
+duplicated_from: diffusers/sd-to-diffusers
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,198 @@
+import os
+import subprocess
+from huggingface_hub import HfApi, upload_folder
+import gradio as gr
+import hf_utils
+import utils
+from safetensors import safe_open
+import torch
+
+subprocess.run(["git", "clone", "https://github.com/huggingface/diffusers", "diffs"])
+
+def error_str(error, title="Error"):
+    return f"""#### {title}
+            {error}"""  if error else ""
+
+def on_token_change(token):
+    model_names, error = hf_utils.get_my_model_names(token)
+    if model_names:
+        model_names.append("Other")
+
+    return gr.update(visible=bool(model_names)), gr.update(choices=model_names, value=model_names[0] if model_names else None), gr.update(visible=bool(model_names)), gr.update(value=error_str(error))
+
+def url_to_model_id(model_id_str):
+    return model_id_str.split("/")[-2] + "/" + model_id_str.split("/")[-1] if model_id_str.startswith("https://huggingface.co/") else model_id_str
+    
+def get_ckpt_names(token, radio_model_names, input_model):
+    
+    model_id = url_to_model_id(input_model) if radio_model_names == "Other" else radio_model_names
+
+    if token == "" or model_id == "":
+        return error_str("Please enter both a token and a model name.", title="Invalid input"), gr.update(choices=[]), gr.update(visible=False)
+
+    try:
+        api = HfApi(token=token)
+        ckpt_files = [f for f in api.list_repo_files(repo_id=model_id) if f.endswith(".ckpt") or f.endswith(".safetensors")]
+        
+        if not ckpt_files:
+            return error_str("No checkpoint files found in the model repo."), gr.update(choices=[]), gr.update(visible=False)
+        
+        return None, gr.update(choices=ckpt_files, value=ckpt_files[0], visible=True), gr.update(visible=True)
+        
+    except Exception as e:
+        return error_str(e), gr.update(choices=[]), None
+
+def convert_and_push(radio_model_names, input_model, ckpt_name, sd_version, token, path_in_repo, ema, safetensors):
+    extract_ema = ema == "ema"
+    
+    if sd_version == None:
+        return error_str("You must select a stable diffusion version.", title="Invalid input")
+
+    model_id = url_to_model_id(input_model) if radio_model_names == "Other" else radio_model_names
+
+    try:
+        model_id = url_to_model_id(model_id)
+
+        # 1. Download the checkpoint file
+        ckpt_path, revision = hf_utils.download_file(repo_id=model_id, filename=ckpt_name, token=token)
+
+        if safetensors == "yes":
+            tensors = {}
+            with safe_open(ckpt_path, framework="pt", device="cpu") as f:
+               for key in f.keys():
+                   tensors[key] = f.get_tensor(key)
+
+            new_checkpoint_path = "/".join(ckpt_path.split("/")[:-1] + ["model_safe.ckpt"])
+            torch.save(tensors, new_checkpoint_path)
+            ckpt_path = new_checkpoint_path
+            print("Converting ckpt_path", ckpt_path)
+
+        print(ckpt_path)
+
+        # 2. Run the conversion script
+        os.makedirs(model_id, exist_ok=True)
+        run_command = [
+            "python3",
+            "./diffs/scripts/convert_original_stable_diffusion_to_diffusers.py",
+            "--checkpoint_path",
+            ckpt_path,
+            "--dump_path" ,
+            model_id,
+        ]
+        if extract_ema:
+            run_command.append("--extract_ema")
+        subprocess.run(run_command)
+
+        # 3. Push to the model repo
+        commit_message="Add Diffusers weights"
+        upload_folder(
+            folder_path=model_id,
+            repo_id=model_id,
+            path_in_repo=path_in_repo,
+            token=token,
+            create_pr=True,
+            commit_message=commit_message,
+            commit_description=f"Add Diffusers weights converted from checkpoint `{ckpt_name}` in revision {revision}",
+        )
+
+        # # 4. Delete the downloaded checkpoint file, yaml files, and the converted model folder
+        hf_utils.delete_file(revision)
+        subprocess.run(["rm", "-rf", model_id.split('/')[0]])
+        import glob
+        for f in glob.glob("*.yaml*"):
+            subprocess.run(["rm", "-rf", f])
+
+        return f"""Successfully converted the checkpoint and opened a PR to add the weights to the model repo.
+                You can view and merge the PR [here]({hf_utils.get_pr_url(HfApi(token=token), model_id, commit_message)})."""
+
+        return "Done"
+    
+    except Exception as e:
+        return error_str(e)
+
+
+DESCRIPTION = """### Convert a stable diffusion checkpoint to Diffusers🧨
+                With this space, you can easily convert a CompVis stable diffusion checkpoint to Diffusers and automatically create a pull request to the model repo.
+                You can choose to convert a checkpoint from one of your own models, or from any other model on the Hub.
+                You can skip the queue by running the app in the colab: [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/gist/qunash/f0f3152c5851c0c477b68b7b98d547fe/convert-sd-to-diffusers.ipynb)"""
+
+with gr.Blocks() as demo:
+
+    gr.Markdown(DESCRIPTION)
+    with gr.Row():
+
+        with gr.Column(scale=11):
+            with gr.Column():
+                gr.Markdown("## 1. Load model info")
+                input_token = gr.Textbox(
+                    max_lines=1,
+                    type="password",
+                    label="Enter your Hugging Face token",
+                    placeholder="READ permission is sufficient"
+                )
+                gr.Markdown("You can get a token [here](https://huggingface.co/settings/tokens)")
+                with gr.Group(visible=False) as group_model:
+                    radio_model_names = gr.Radio(label="Choose a model")
+                    input_model = gr.Textbox(
+                        max_lines=1,
+                        label="Model name or URL",
+                        placeholder="username/model_name",
+                        visible=False,
+                    )
+
+            btn_get_ckpts = gr.Button("Load", visible=False)
+
+        with gr.Column(scale=10):
+            with gr.Column(visible=False) as group_convert:
+                gr.Markdown("## 2. Convert to Diffusers🧨")
+                radio_ckpts = gr.Radio(label="Choose the checkpoint to convert", visible=False)
+                path_in_repo = gr.Textbox(label="Path where the weights will be saved", placeholder="Leave empty for root folder")
+                ema = gr.Radio(label="Extract EMA or non-EMA?", choices=["ema", "non-ema"])
+                safetensors = gr.Radio(label="Extract from safetensors", choices=["yes", "no"], value="no")
+                radio_sd_version = gr.Radio(label="Choose the model version", choices=["v1", "v2", "v2.1"])
+                gr.Markdown("Conversion may take a few minutes.")
+                btn_convert = gr.Button("Convert & Push")
+
+    error_output = gr.Markdown(label="Output")
+
+    input_token.change(
+        fn=on_token_change,
+        inputs=input_token,
+        outputs=[group_model, radio_model_names, btn_get_ckpts, error_output],
+        queue=False,
+        scroll_to_output=True)
+    
+    radio_model_names.change(
+        lambda x: gr.update(visible=x == "Other"),
+        inputs=radio_model_names,
+        outputs=input_model,
+        queue=False,
+        scroll_to_output=True)
+    
+    btn_get_ckpts.click(
+        fn=get_ckpt_names,
+        inputs=[input_token, radio_model_names, input_model],
+        outputs=[error_output, radio_ckpts, group_convert],
+        scroll_to_output=True,
+        queue=False
+    )
+
+    btn_convert.click(
+        fn=convert_and_push,
+        inputs=[radio_model_names, input_model, radio_ckpts, radio_sd_version, input_token, path_in_repo, ema, safetensors],
+        outputs=error_output,
+        scroll_to_output=True
+    )
+
+    # gr.Markdown("""<img src="https://raw.githubusercontent.com/huggingface/diffusers/main/docs/source/imgs/diffusers_library.jpg" width="150"/>""")
+    gr.HTML("""
+    <div style="border-top: 1px solid #303030;">
+      <br>
+      <p>Space by: <a href="https://twitter.com/hahahahohohe"><img src="https://img.shields.io/twitter/follow/hahahahohohe?label=%40anzorq&style=social" alt="Twitter Follow"></a></p><br>
+      <a href="https://www.buymeacoffee.com/anzorq" target="_blank"><img src="https://cdn.buymeacoffee.com/buttons/v2/default-yellow.png" alt="Buy Me A Coffee" style="height: 45px !important;width: 162px !important;" ></a><br><br>
+      <p><img src="https://visitor-badge.glitch.me/badge?page_id=anzorq.sd-to-diffusers" alt="visitors"></p>
+    </div>
+    """)
+    
+demo.queue()
+demo.launch(debug=True, share=utils.is_google_colab())

hf_utils.py

@@ -0,0 +1,50 @@
+from huggingface_hub import get_hf_file_metadata, hf_hub_url, hf_hub_download, scan_cache_dir, whoami, list_models
+
+
+def get_my_model_names(token):
+    
+    try:
+        author = whoami(token=token)
+        model_infos = list_models(author=author["name"], use_auth_token=token)
+        return [model.modelId for model in model_infos], None
+        
+    except Exception as e:
+        return [], e
+
+def download_file(repo_id: str, filename: str, token: str):
+    """Download a file from a repo on the Hugging Face Hub.
+
+    Returns:
+        file_path (:obj:`str`): The path to the downloaded file.
+        revision (:obj:`str`): The commit hash of the file.
+        """
+
+    md = get_hf_file_metadata(hf_hub_url(repo_id=repo_id, filename=filename), token=token)
+    revision = md.commit_hash
+
+    file_path = hf_hub_download(repo_id=repo_id, filename=filename, revision=revision, token=token)
+
+    return file_path, revision
+
+def delete_file(revision: str):
+    """Delete a file from local cache.
+
+    Args:
+        revision (:obj:`str`): The commit hash of the file.
+    Returns:
+        None
+        """
+    scan_cache_dir().delete_revisions(revision).execute()
+
+def get_pr_url(api, repo_id, title):
+    try:
+        discussions = api.get_repo_discussions(repo_id=repo_id)
+    except Exception:
+        return None
+    for discussion in discussions:
+        if (
+            discussion.status == "open"
+            and discussion.is_pull_request
+            and discussion.title == title
+        ):
+            return f"https://huggingface.co/{repo_id}/discussions/{discussion.num}"

requirements.txt

@@ -0,0 +1,9 @@
+git+https://github.com/huggingface/huggingface_hub@main
+git+https://github.com/huggingface/diffusers.git
+torch
+#transformers
+git+https://github.com/huggingface/transformers
+pytorch_lightning
+OmegaConf
+ftfy
+safetensors

utils.py

@@ -0,0 +1,6 @@
+def is_google_colab():
+    try:
+        import google.colab
+        return True
+    except:
+        return False