Merge branch 'main' of https://huggingface.co./diffusers/tools

benchmark/if.py

@@ -0,0 +1,32 @@
+#!/usr/bin/env python3
+from diffusers import DiffusionPipeline
+import torch
+
+run_compile = True  # Set True / False
+
+pipe = DiffusionPipeline.from_pretrained("DeepFloyd/IF-I-M-v1.0", variant="fp16", text_encoder=None, torch_dtype=torch.float16)
+pipe.to("cuda")
+pipe_2 = DiffusionPipeline.from_pretrained("DeepFloyd/IF-II-M-v1.0", variant="fp16", text_encoder=None, torch_dtype=torch.float16)
+pipe_2.to("cuda")
+pipe_3 = DiffusionPipeline.from_pretrained("stabilityai/stable-diffusion-x4-upscaler", torch_dtype=torch.float16)
+pipe_3.to("cuda")
+
+
+pipe.unet.to(memory_format=torch.channels_last)
+pipe_2.unet.to(memory_format=torch.channels_last)
+pipe_3.unet.to(memory_format=torch.channels_last)
+
+if run_compile:
+    pipe.unet = torch.compile(pipe.unet, mode="reduce-overhead", fullgraph=True)
+    pipe_2.unet = torch.compile(pipe_2.unet, mode="reduce-overhead", fullgraph=True)
+    pipe_3.unet = torch.compile(pipe_3.unet, mode="reduce-overhead", fullgraph=True)
+
+prompt = "the blue hulk"
+
+prompt_embeds = torch.randn((1, 2, 4096), dtype=torch.float16)
+neg_prompt_embeds = torch.randn((1, 2, 4096), dtype=torch.float16)
+
+for _ in range(3):
+    image = pipe(prompt_embeds=prompt_embeds, negative_prompt_embeds=neg_prompt_embeds, output_type="pt").images
+    image_2 = pipe_2(image=image, prompt_embeds=prompt_embeds, negative_prompt_embeds=neg_prompt_embeds, output_type="pt").images
+    image_3 = pipe_3(prompt=prompt, image=image, noise_level=100).images

benchmark/if_no_compile.py

@@ -0,0 +1,32 @@
+#!/usr/bin/env python3
+from diffusers import DiffusionPipeline
+import torch
+
+run_compile = False# Set True / False
+
+pipe = DiffusionPipeline.from_pretrained("DeepFloyd/IF-I-M-v1.0", variant="fp16", text_encoder=None, torch_dtype=torch.float16)
+pipe.to("cuda")
+pipe_2 = DiffusionPipeline.from_pretrained("DeepFloyd/IF-II-M-v1.0", variant="fp16", text_encoder=None, torch_dtype=torch.float16)
+pipe_2.to("cuda")
+pipe_3 = DiffusionPipeline.from_pretrained("stabilityai/stable-diffusion-x4-upscaler", torch_dtype=torch.float16)
+pipe_3.to("cuda")
+
+
+pipe.unet.to(memory_format=torch.channels_last)
+pipe_2.unet.to(memory_format=torch.channels_last)
+pipe_3.unet.to(memory_format=torch.channels_last)
+
+if run_compile:
+    pipe.unet = torch.compile(pipe.unet, mode="reduce-overhead", fullgraph=True)
+    pipe_2.unet = torch.compile(pipe_2.unet, mode="reduce-overhead", fullgraph=True)
+    pipe_3.unet = torch.compile(pipe_3.unet, mode="reduce-overhead", fullgraph=True)
+
+prompt = "the blue hulk"
+
+prompt_embeds = torch.randn((1, 2, 4096), dtype=torch.float16)
+neg_prompt_embeds = torch.randn((1, 2, 4096), dtype=torch.float16)
+
+for _ in range(3):
+    image = pipe(prompt_embeds=prompt_embeds, negative_prompt_embeds=neg_prompt_embeds, output_type="pt").images
+    image_2 = pipe_2(image=image, prompt_embeds=prompt_embeds, negative_prompt_embeds=neg_prompt_embeds, output_type="pt").images
+    image_3 = pipe_3(prompt=prompt, image=image, noise_level=100).images

benchmark/sd_controlnet.py

@@ -0,0 +1,34 @@
+#!/usr/bin/env python3
+from diffusers import StableDiffusionControlNetPipeline, ControlNetModel
+import requests
+import torch
+from PIL import Image
+from io import BytesIO
+
+url = "https://raw.githubusercontent.com/CompVis/stable-diffusion/main/assets/stable-samples/img2img/sketch-mountains-input.jpg"
+
+response = requests.get(url)
+init_image = Image.open(BytesIO(response.content)).convert("RGB")
+init_image = init_image.resize((512, 512))
+
+path = "runwayml/stable-diffusion-v1-5"
+
+run_compile = True  # Set True / False
+controlnet = ControlNetModel.from_pretrained("lllyasviel/sd-controlnet-canny", torch_dtype=torch.float16)
+pipe = StableDiffusionControlNetPipeline.from_pretrained(
+    path, controlnet=controlnet, torch_dtype=torch.float16
+)
+
+pipe = pipe.to("cuda:0")
+pipe.unet.to(memory_format=torch.channels_last)
+pipe.controlnet.to(memory_format=torch.channels_last)
+
+if run_compile:
+    print("Run torch compile")
+    pipe.unet = torch.compile(pipe.unet, mode="reduce-overhead", fullgraph=True)
+    pipe.controlnet = torch.compile(pipe.controlnet, mode="reduce-overhead", fullgraph=True)
+
+prompt = "ghibli style, a fantasy landscape with castles"
+
+for _ in range(3):
+    image = pipe(prompt=prompt, image=init_image).images[0]

benchmark/sd_controlnet_no_compile.py

@@ -0,0 +1,34 @@
+#!/usr/bin/env python3
+from diffusers import StableDiffusionControlNetPipeline, ControlNetModel
+import requests
+import torch
+from PIL import Image
+from io import BytesIO
+
+url = "https://raw.githubusercontent.com/CompVis/stable-diffusion/main/assets/stable-samples/img2img/sketch-mountains-input.jpg"
+
+response = requests.get(url)
+init_image = Image.open(BytesIO(response.content)).convert("RGB")
+init_image = init_image.resize((512, 512))
+
+path = "runwayml/stable-diffusion-v1-5"
+
+run_compile = False # Set True / False
+controlnet = ControlNetModel.from_pretrained("lllyasviel/sd-controlnet-canny", torch_dtype=torch.float16)
+pipe = StableDiffusionControlNetPipeline.from_pretrained(
+    path, controlnet=controlnet, torch_dtype=torch.float16
+)
+
+pipe = pipe.to("cuda:0")
+pipe.unet.to(memory_format=torch.channels_last)
+pipe.controlnet.to(memory_format=torch.channels_last)
+
+if run_compile:
+    print("Run torch compile")
+    pipe.unet = torch.compile(pipe.unet, mode="reduce-overhead", fullgraph=True)
+    pipe.controlnet = torch.compile(pipe.controlnet, mode="reduce-overhead", fullgraph=True)
+
+prompt = "ghibli style, a fantasy landscape with castles"
+
+for _ in range(3):
+    image = pipe(prompt=prompt, image=init_image).images[0]

benchmark/sd_img2img.py

@@ -0,0 +1,29 @@
+#!/usr/bin/env python3
+from diffusers import StableDiffusionImg2ImgPipeline
+import requests
+import torch
+from PIL import Image
+from io import BytesIO
+
+url = "https://raw.githubusercontent.com/CompVis/stable-diffusion/main/assets/stable-samples/img2img/sketch-mountains-input.jpg"
+
+response = requests.get(url)
+init_image = Image.open(BytesIO(response.content)).convert("RGB")
+init_image = init_image.resize((512, 512))
+
+path = "runwayml/stable-diffusion-v1-5"
+
+run_compile = True  # Set True / False
+
+pipe = StableDiffusionImg2ImgPipeline.from_pretrained(path, torch_dtype=torch.float16)
+pipe = pipe.to("cuda:0")
+pipe.unet.to(memory_format=torch.channels_last)
+
+if run_compile:
+    print("Run torch compile")
+    pipe.unet = torch.compile(pipe.unet, mode="reduce-overhead", fullgraph=True)
+
+prompt = "ghibli style, a fantasy landscape with castles"
+
+for _ in range(3):
+    image = pipe(prompt=prompt, image=init_image).images[0]

benchmark/sd_img2img_no_compile.py

@@ -0,0 +1,29 @@
+#!/usr/bin/env python3
+from diffusers import StableDiffusionImg2ImgPipeline
+import requests
+import torch
+from PIL import Image
+from io import BytesIO
+
+url = "https://raw.githubusercontent.com/CompVis/stable-diffusion/main/assets/stable-samples/img2img/sketch-mountains-input.jpg"
+
+response = requests.get(url)
+init_image = Image.open(BytesIO(response.content)).convert("RGB")
+init_image = init_image.resize((512, 512))
+
+path = "runwayml/stable-diffusion-v1-5"
+
+run_compile = False  # Set True / False
+
+pipe = StableDiffusionImg2ImgPipeline.from_pretrained(path, torch_dtype=torch.float16)
+pipe = pipe.to("cuda:0")
+pipe.unet.to(memory_format=torch.channels_last)
+
+if run_compile:
+    print("Run torch compile")
+    pipe.unet = torch.compile(pipe.unet, mode="reduce-overhead", fullgraph=True)
+
+prompt = "ghibli style, a fantasy landscape with castles"
+
+for _ in range(3):
+    image = pipe(prompt=prompt, image=init_image).images[0]

benchmark/sd_inpaint.py

@@ -0,0 +1,36 @@
+#!/usr/bin/env python3
+from diffusers import StableDiffusionInpaintPipeline
+import requests
+import torch
+from PIL import Image
+from io import BytesIO
+
+url = "https://raw.githubusercontent.com/CompVis/stable-diffusion/main/assets/stable-samples/img2img/sketch-mountains-input.jpg"
+
+def download_image(url):
+    response = requests.get(url)
+    return Image.open(BytesIO(response.content)).convert("RGB")
+
+
+img_url = "https://raw.githubusercontent.com/CompVis/latent-diffusion/main/data/inpainting_examples/overture-creations-5sI6fQgYIuo.png"
+mask_url = "https://raw.githubusercontent.com/CompVis/latent-diffusion/main/data/inpainting_examples/overture-creations-5sI6fQgYIuo_mask.png"
+
+init_image = download_image(img_url).resize((512, 512))
+mask_image = download_image(mask_url).resize((512, 512))
+
+path = "runwayml/stable-diffusion-inpainting"
+
+run_compile = True  # Set True / False
+
+pipe = StableDiffusionInpaintPipeline.from_pretrained(path, torch_dtype=torch.float16)
+pipe = pipe.to("cuda:0")
+pipe.unet.to(memory_format=torch.channels_last)
+
+if run_compile:
+    print("Run torch compile")
+    pipe.unet = torch.compile(pipe.unet, mode="reduce-overhead", fullgraph=True)
+
+prompt = "ghibli style, a fantasy landscape with castles"
+
+for _ in range(3):
+    image = pipe(prompt=prompt, image=init_image, mask_image=mask_image).images[0]

benchmark/sd_inpaint_no_compile.py

@@ -0,0 +1,36 @@
+#!/usr/bin/env python3
+from diffusers import StableDiffusionInpaintPipeline
+import requests
+import torch
+from PIL import Image
+from io import BytesIO
+
+url = "https://raw.githubusercontent.com/CompVis/stable-diffusion/main/assets/stable-samples/img2img/sketch-mountains-input.jpg"
+
+def download_image(url):
+    response = requests.get(url)
+    return Image.open(BytesIO(response.content)).convert("RGB")
+
+
+img_url = "https://raw.githubusercontent.com/CompVis/latent-diffusion/main/data/inpainting_examples/overture-creations-5sI6fQgYIuo.png"
+mask_url = "https://raw.githubusercontent.com/CompVis/latent-diffusion/main/data/inpainting_examples/overture-creations-5sI6fQgYIuo_mask.png"
+
+init_image = download_image(img_url).resize((512, 512))
+mask_image = download_image(mask_url).resize((512, 512))
+
+path = "runwayml/stable-diffusion-inpainting"
+
+run_compile = False  # Set True / False
+
+pipe = StableDiffusionInpaintPipeline.from_pretrained(path, torch_dtype=torch.float16)
+pipe = pipe.to("cuda:0")
+pipe.unet.to(memory_format=torch.channels_last)
+
+if run_compile:
+    print("Run torch compile")
+    pipe.unet = torch.compile(pipe.unet, mode="reduce-overhead", fullgraph=True)
+
+prompt = "ghibli style, a fantasy landscape with castles"
+
+for _ in range(3):
+    image = pipe(prompt=prompt, image=init_image, mask_image=mask_image).images[0]

benchmark/sd_txt2img.py

@@ -0,0 +1,20 @@
+#!/usr/bin/env python3
+from diffusers import DiffusionPipeline
+import torch
+
+path = "runwayml/stable-diffusion-v1-5"
+
+run_compile = True  # Set True / False
+
+pipe = DiffusionPipeline.from_pretrained(path, torch_dtype=torch.float16)
+pipe = pipe.to("cuda:0")
+pipe.unet.to(memory_format=torch.channels_last)
+
+if run_compile:
+    print("Run torch compile")
+    pipe.unet = torch.compile(pipe.unet, mode="reduce-overhead", fullgraph=True)
+
+prompt = "ghibli style, a fantasy landscape with castles"
+
+for _ in range(3):
+    images = pipe(prompt=prompt).images

benchmark/sd_txt2img_no_compile.py

@@ -0,0 +1,20 @@
+#!/usr/bin/env python3
+from diffusers import DiffusionPipeline
+import torch
+
+path = "runwayml/stable-diffusion-v1-5"
+
+run_compile = False  # Set True / False
+
+pipe = DiffusionPipeline.from_pretrained(path, torch_dtype=torch.float16)
+pipe = pipe.to("cuda:0")
+pipe.unet.to(memory_format=torch.channels_last)
+
+if run_compile:
+    print("Run torch compile")
+    pipe.unet = torch.compile(pipe.unet, mode="reduce-overhead", fullgraph=True)
+
+prompt = "ghibli style, a fantasy landscape with castles"
+
+for _ in range(3):
+    images = pipe(prompt=prompt).images