up

mass_branches_retrieval.sh

@@ -2,6 +2,5 @@
 touch all_branches.txt
 
 while read p; do
-	echo "-------------------------------" >> all_branches.txt
 	python check_for_branches.py --model_id ${p} >> all_branches.txt
 done <model_ids.txt

mass_open_controlnet_pr.sh → mass_fp16_branch_pr.sh

@@ -2,5 +2,5 @@
 while read p; do
 	echo "-------------------------------"
 	echo "Open PR for $p"
-	python convert_flax_to_pt.py $p
-done <model_ids.txt
+	python open_pr_version.py $p
+done <all_branches.txt

open_pr_version.py

@@ -5,6 +5,7 @@ import torch
 import shutil
 from tempfile import TemporaryDirectory
 from typing import List, Optional
+from diffusers import DiffusionPipeline
 
 from huggingface_hub import CommitInfo, CommitOperationAdd, Discussion, HfApi, hf_hub_download
 from huggingface_hub.file_download import repo_folder_name
@@ -44,24 +45,27 @@ def is_index_stable_diffusion_like(config_dict):
 
 
 def convert_single(model_id: str, folder: str) -> List["CommitOperationAdd"]:
-    pipe = DiffusionPipeline.from_pretrained(model_id)
+    pipe = DiffusionPipeline.from_pretrained(model_id, cache_dir="/home/patrick/cache_to_delete")
 
     try:
         pipe.to(torch_dtype=torch.float16)
-        pipe.save_pretrained(model_id, variant="fp16")
-        pipe.save_pretrained(model_id, variant="fp16", safe_serialization=True)
-        import ipdb; ipdb.set_trace()
-
-        operations = [CommitOperationAdd(path_in_repo=config_file, path_or_fileobj=new_config_file)]
-    except:
-        import ipdb; ipdb.set_trace()
-
-    if success:
-        model_type = success
-        return operations, model_type
-    else:
-        return False, False
-
+        pipe.save_pretrained(folder, variant="fp16")
+        pipe.save_pretrained(folder, variant="fp16", safe_serialization=True)
+
+        all_files = []
+        def find_files_in_dir(directory):
+            for root, dirs, files in os.walk(directory):
+                for file in files:
+                    all_files.append(os.path.join(root, file))
+
+        find_files_in_dir(folder)
+        files = [f for f in all_files if ".fp16." in f]
+
+        operations = [CommitOperationAdd(path_in_repo='/'.join(f.split("/")[-2:]), path_or_fileobj=f) for f in files]
+        return operations
+    except Exception as e:
+        print(e)
+        return False
 
 def convert_file(
     old_config: str,
@@ -96,18 +100,7 @@ def previous_pr(api: "HfApi", model_id: str, pr_title: str) -> Optional["Discuss
 
 
 def convert(api: "HfApi", model_id: str, force: bool = False) -> Optional["CommitInfo"]:
-#    pr_title = "Correct `sample_size` of {}'s unet to have correct width and height default"
-    pr_title = "Fix deprecation warning by changing `CLIPFeatureExtractor` to `CLIPImageProcessor`."
-    info = api.model_info(model_id)
-    filenames = set(s.rfilename for s in info.siblings)
-
-    if "model_index.json" not in filenames:
-        print(f"Model: {model_id} has no model_index.json file to change")
-        return
-
-    # if "vae/config.json" not in filenames:
-    #     print(f"Model: {model_id} has no 'vae/config.json' file to change")
-    #     return
+    pr_title = "Fix deprecated float16/fp16 variant loading through new `version` API."
 
     with TemporaryDirectory() as d:
         folder = os.path.join(d, repo_folder_name(repo_id=model_id, repo_type="models"))
@@ -121,27 +114,22 @@ def convert(api: "HfApi", model_id: str, force: bool = False) -> Optional["Commi
                 new_pr = pr
                 raise AlreadyExists(f"Model {model_id} already has an open PR check out {url}")
             else:
-                operations, model_type = convert_single(model_id, folder)
+                operations = convert_single(model_id, folder)
 
             if operations:
-                pr_title = pr_title.format(model_type)
-#                if model_type == "Stable Diffusion 1":
-#                    sample_size = 64
-#                    image_size = 512
-#                elif model_type == "Stable Diffusion 2":
-#                    sample_size = 96
-#                    image_size = 768
-
-#                pr_description = (
-#                        f"Since `diffusers==0.9.0` the width and height is automatically inferred from the `sample_size` attribute of your unet's config. It seems like your diffusion model has the same architecture as {model_type} which means that when using this model, by default an image size of {image_size}x{image_size} should be generated. This in turn means the unet's sample size should be **{sample_size}**. \n\n In order to suppress to update your configuration on the fly and to suppress the deprecation warning added in this PR: https://github.com/huggingface/diffusers/pull/1406/files#r1035703505 it is strongly recommended to merge this PR."
-#                )
                 contributor = model_id.split("/")[0]
                 pr_description = (
-                        f"Hey {contributor} 👋, \n\n Your model repository seems to contain logic to load a feature extractor that is deprecated, which you should notice by seeing the warning: "
-                        "\n\n ```\ntransformers/models/clip/feature_extraction_clip.py:28: FutureWarning: The class CLIPFeatureExtractor is deprecated and will be removed in version 5 of Transformers. "
-                        f"Please use CLIPImageProcessor instead. warnings.warn(\n``` \n\n when running `pipe = DiffusionPipeline.from_pretrained({model_id})`."
-                        "This PR makes sure that the warning does not show anymore by replacing `CLIPFeatureExtractor` with `CLIPImageProcessor`. This will certainly not change or break your checkpoint, but only" 
-                        "make sure that everything is up to date. \n\n Best, the 🧨 Diffusers team."
+                        f"Hey {contributor} 👋, \n\n Your model repository seems to contain a [`fp16` branch](https://huggingface.co/{model_id}/tree/fp16) to load the model in float16 precision. "
+                        "Loading `fp16` versions from a branch instead of the main branch is deprecated and will eventually be forbidden. "
+                        "Instead, we strongly recommend to save `fp16` versions of the model under `.fp16.` version files directly on the 'main' branch as enabled through this PR."
+                        f"This PR makes sure that your model repository allows the user to correctly download float16 precision model weights by adding `fp16` model weights in both safetensors and PyTorch bin format:"
+                        "\n\n"
+                        "```py\n"
+                        f"pipe = DiffusionPipeline.from_pretrained({model_id}, torch_dtype=torch.float16, variant='fp16')"
+                        "\n```"
+                        "\n\n"
+                        "For more information please have a look at: https://huggingface.co/docs/diffusers/using-diffusers/loading#checkpoint-variants."
+                        "\nWe made sure you that you can safely merge this pull request. \n\n Best, the 🧨 Diffusers team."
                 )
                 new_pr = api.create_commit(
                     repo_id=model_id,

run_local_img2img_xl.py

@@ -0,0 +1,46 @@
+#!/usr/bin/env python3
+from diffusers import DiffusionPipeline, EulerDiscreteScheduler, StableDiffusionPipeline, KDPM2DiscreteScheduler, StableDiffusionImg2ImgPipeline, HeunDiscreteScheduler, KDPM2AncestralDiscreteScheduler, DDIMScheduler
+import time
+import os
+from huggingface_hub import HfApi
+# from compel import Compel
+import torch
+import sys
+from pathlib import Path
+import requests
+from PIL import Image
+from io import BytesIO
+
+path = sys.argv[1]
+
+api = HfApi()
+start_time = time.time()
+pipe = DiffusionPipeline.from_pretrained(path, torch_dtype=torch.float16)
+pipe.scheduler = EulerDiscreteScheduler.from_config(pipe.scheduler.config)
+# pipe.scheduler = DDIMScheduler.from_config(pipe.scheduler.config)
+# pipe = StableDiffusionImg2ImgPipeline.from_pretrained(path, torch_dtype=torch.float16, safety_checker=None
+
+# compel = Compel(tokenizer=pipe.tokenizer, text_encoder=pipe.text_encoder)
+
+
+pipe = pipe.to("cuda")
+
+prompt = "Elon Musk riding a green horse on Mars"
+
+# pipe.unet.to(memory_format=torch.channels_last)
+pipe.unet = torch.compile(pipe.unet, mode="reduce-overhead", fullgraph=True)
+pipe(prompt=prompt, num_inference_steps=2).images[0]
+
+image = pipe(prompt=prompt).images[0]
+
+file_name = f"aaa"
+path = os.path.join(Path.home(), "images", f"{file_name}.png")
+image.save(path)
+
+api.upload_file(
+    path_or_fileobj=path,
+    path_in_repo=path.split("/")[-1],
+    repo_id="patrickvonplaten/images",
+    repo_type="dataset",
+)
+print(f"https://huggingface.co/datasets/patrickvonplaten/images/blob/main/{file_name}.png")

run_local_xl.py

@@ -0,0 +1,46 @@
+#!/usr/bin/env python3
+from diffusers import DiffusionPipeline, EulerDiscreteScheduler, StableDiffusionPipeline, KDPM2DiscreteScheduler, StableDiffusionImg2ImgPipeline, HeunDiscreteScheduler, KDPM2AncestralDiscreteScheduler, DDIMScheduler
+import time
+import os
+from huggingface_hub import HfApi
+# from compel import Compel
+import torch
+import sys
+from pathlib import Path
+import requests
+from PIL import Image
+from io import BytesIO
+
+path = sys.argv[1]
+
+api = HfApi()
+start_time = time.time()
+pipe = DiffusionPipeline.from_pretrained(path, torch_dtype=torch.float16)
+pipe.scheduler = EulerDiscreteScheduler.from_config(pipe.scheduler.config)
+# pipe.scheduler = DDIMScheduler.from_config(pipe.scheduler.config)
+# pipe = StableDiffusionImg2ImgPipeline.from_pretrained(path, torch_dtype=torch.float16, safety_checker=None
+
+# compel = Compel(tokenizer=pipe.tokenizer, text_encoder=pipe.text_encoder)
+
+
+pipe = pipe.to("cuda")
+
+prompt = "Elon Musk riding a green horse on Mars"
+
+# pipe.unet.to(memory_format=torch.channels_last)
+pipe.unet = torch.compile(pipe.unet, mode="reduce-overhead", fullgraph=True)
+pipe(prompt=prompt, num_inference_steps=2).images[0]
+
+image = pipe(prompt=prompt).images[0]
+
+file_name = f"aaa"
+path = os.path.join(Path.home(), "images", f"{file_name}.png")
+image.save(path)
+
+api.upload_file(
+    path_or_fileobj=path,
+    path_in_repo=path.split("/")[-1],
+    repo_id="patrickvonplaten/images",
+    repo_type="dataset",
+)
+print(f"https://huggingface.co/datasets/patrickvonplaten/images/blob/main/{file_name}.png")

run_video.py

@@ -0,0 +1,12 @@
+#!/usr/bin/env python3
+import torch
+from diffusers import DiffusionPipeline, DPMSolverMultistepScheduler
+from diffusers.utils import export_to_video
+
+pipe = DiffusionPipeline.from_pretrained("cerspense/zeroscope_v2_576w", torch_dtype=torch.float16)
+pipe.scheduler = DPMSolverMultistepScheduler.from_config(pipe.scheduler.config)
+pipe.enable_model_cpu_offload()
+
+prompt = "Darth Vader is surfing on waves"
+video_frames = pipe(prompt, num_inference_steps=40, height=320, width=576, num_frames=24).frames
+video_path = export_to_video(video_frames, output_video_path="/home/patrick/videos/video_10.mp4")