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

controlnet_img2img.py

@@ -0,0 +1,77 @@
+#!/usr/bin/env python3
+import torch
+import os
+from huggingface_hub import HfApi
+from pathlib import Path
+from diffusers.utils import load_image
+import cv2
+from PIL import Image
+import numpy as np
+
+from diffusers import (
+    ControlNetModel,
+    StableDiffusionControlNetImg2ImgPipeline,
+    StableDiffusionControlNetInpaintPipeline,
+    DiffusionPipeline,
+    UniPCMultistepScheduler,
+)
+import sys
+
+checkpoint = sys.argv[1]
+
+# image = load_image(
+#     "https://huggingface.co/lllyasviel/sd-controlnet-canny/resolve/main/images/bird.png"
+# )
+
+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"
+image = load_image(img_url).resize((512, 512))
+mask_image = load_image(mask_url).resize((512, 512))
+
+np_image = np.array(image)
+
+low_threshold = 100
+high_threshold = 200
+
+np_image = cv2.Canny(np_image, low_threshold, high_threshold)
+np_image = np_image[:, :, None]
+np_image = np.concatenate([np_image, np_image, np_image], axis=2)
+canny_image = Image.fromarray(np_image)
+
+controlnet = ControlNetModel.from_pretrained(checkpoint, torch_dtype=torch.float16)
+# pipe = DiffusionPipeline.from_pretrained(
+#    "runwayml/stable-diffusion-inpainting", controlnet=controlnet, torch_dtype=torch.float16, custom_pipeline="stable_diffusion_controlnet_inpaint"
+# )
+pipe = StableDiffusionControlNetInpaintPipeline.from_pretrained(
+    "runwayml/stable-diffusion-inpainting",
+    controlnet=controlnet,
+    torch_dtype=torch.float16,
+)
+
+pipe.scheduler = UniPCMultistepScheduler.from_config(pipe.scheduler.config)
+pipe.enable_model_cpu_offload()
+
+generator = torch.manual_seed(0)
+text_prompt="a blue dog"
+# out_image = pipe("A blue dog", num_inference_steps=50, generator=generator, image=image, mask_image=mask_image, controlnet_conditioning_image=canny_image).images[0]
+out_image = pipe(
+    text_prompt,
+    num_inference_steps=20,
+    generator=generator,
+    image=image,
+    mask_image=mask_image,
+    control_image=canny_image,
+).images[0]
+
+path = os.path.join(Path.home(), "images", "aa.png")
+out_image.save(path)
+
+api = HfApi()
+
+api.upload_file(
+    path_or_fileobj=path,
+    path_in_repo=path.split("/")[-1],
+    repo_id="patrickvonplaten/images",
+    repo_type="dataset",
+)
+print("https://huggingface.co/datasets/patrickvonplaten/images/blob/main/aa.png")

parti_prompts.py

@@ -1,6 +1,7 @@
 #!/usr/bin/env python3
 from diffusers import DiffusionPipeline, DDIMScheduler
 import argparse
+from diffusers.pipelines.stable_diffusion import safety_checker
 import torch
 from datasets import load_dataset
 import PIL
@@ -12,12 +13,12 @@ def resize(image: PIL.Image):
     return image.resize(IMAGE_OUTPUT_SIZE, resample=PIL.Image.Resampling.LANCZOS)
 
 def get_sd_eval(ckpt, guidance_scale=7.5):
-    pipe = DiffusionPipeline.from_pretrained(ckpt, torch_dtype=torch.float16)
+    pipe = DiffusionPipeline.from_pretrained(ckpt, torch_dtype=torch.float16, safety_checker=None)
     pipe.to("cuda")
-    pipe.scheduler = DDIMScheduler.from_config(pipe.config)
+    pipe.scheduler = DDIMScheduler.from_config(pipe.scheduler.config)
 
-    def sd_eval(prompt):
-        images = pipe(prompt, num_inference_steps=100, guidance_scale=guidance_scale).images
+    def sd_eval(prompt, generator=None):
+        images = pipe(prompt, generator=generator, num_inference_steps=NUM_INFERENCE_STEPS, guidance_scale=guidance_scale).images
         images = [resize(image) for image in images]
         return images
 
@@ -28,28 +29,29 @@ def get_karlo_eval(ckpt):
     pipe.to("cuda")
 
     def karlo_eval(prompt):
-        images = pipe(prompt, prior_num_inference_steps=50, decoder_num_inference_steps=100).images
+        images = pipe(prompt, prior_num_inference_steps=50, decoder_num_inference_steps=NUM_INFERENCE_STEPS).images
         return images
 
     return karlo_eval
 
 def get_if_eval(ckpt):
-    pipe_low = DiffusionPipeline.from_pretrained(ckpt, torch_dtype=torch.float16)
+    pipe_low = DiffusionPipeline.from_pretrained(ckpt, safety_checker=None, watermarker=None, torch_dtype=torch.float16, variant="fp16")
     pipe_low.enable_model_cpu_offload()
 
-    pipe_up = DiffusionPipeline.from_pretrained("DeepFloyd/IF-II-L-v1.0", text_encoder=pipe_low.text_encoder, torch_dtype=torch.float16)
+    pipe_up = DiffusionPipeline.from_pretrained("DeepFloyd/IF-II-L-v1.0", safety_checker=None, watermarker=None, text_encoder=pipe_low.text_encoder, torch_dtype=torch.float16, variant="fp16")
     pipe_up.enable_model_cpu_offload()
 
-    def sd_eval(prompt):
-        images = pipe_low(prompt, num_inference_steps=100, output_type="pt").images
-        images = pipe_up(promtp=prompt, images=images, num_inference_steps=100).images
+    def if_eval(prompt, generator=None):
+        prompt_embeds, negative_prompt_embeds = pipe_low.encode_prompt(prompt)
+        images = pipe_low(prompt_embeds=prompt_embeds, negative_prompt_embeds=negative_prompt_embeds, num_inference_steps=NUM_INFERENCE_STEPS, generator=generator, output_type="pt").images
+        images = pipe_up(prompt_embeds=prompt_embeds, negative_prompt_embeds=negative_prompt_embeds, image=images, num_inference_steps=NUM_INFERENCE_STEPS, generator=generator).images
         return images
 
-    return sd_eval
+    return if_eval
 
 MODELS = {
     "runwayml/stable-diffusion-v1-5": get_sd_eval,
-    "stabilityai/stable-diffusion-v2-1": get_sd_eval,
+    "stabilityai/stable-diffusion-2-1": get_sd_eval,
     "kakaobrain/karlo-alpha": get_karlo_eval,
     "DeepFloyd/IF-I-XL-v1.0": get_if_eval,
 }
@@ -59,24 +61,29 @@ MODELS = {
 
 if __name__ == "__main__":
     parser = argparse.ArgumentParser(description='Run Parti Prompt Evaluation')
-    parser.add_argument('model_repo_or_id', type=str, help='ID or URL of the model repository.', required=True)
+    parser.add_argument('model_repo_or_id', type=str, help='ID or URL of the model repository.')
     parser.add_argument('--dataset_repo_or_id', type=str, default='diffusers/prompt_generations', help='ID or URL of the dataset repository (default: "diffusers/prompt_generations")')
     parser.add_argument('--batch_size', type=int, default=8, help="Batch size for the eval function")
     parser.add_argument('--upload_to_hub', action='store_true', help='whether to upload the dataset to the Hugging Face dataset hub')
+    parser.add_argument('--seed', type=int, default=0, help='Random seed')
 
     args = parser.parse_args()
 
-    eval_fn = MODELS[args.model_repo_or_id](args.model_repo_or_id)
+    dataset = load_dataset("nateraw/parti-prompts")["train"]
+    # dataset = dataset.select(range(4))
 
-    dataset = load_dataset("nateraw/parti-prompts")
+    eval_fn = MODELS[args.model_repo_or_id](args.model_repo_or_id)
 
     def map_fn(batch):
-        batch["images"] = eval_fn(batch["prompt"])
+        generators = [torch.Generator(device="cuda").manual_seed(args.seed) for _ in range(args.batch_size)]
+        batch["images"] = eval_fn(batch["Prompt"], generator=generators)
+        batch["model_name"] = len(batch["images"]) * [args.model_repo_or_id]
+        batch["seed"] = len(batch["images"]) * [args.seed]
         return batch
 
-    dataset_images = dataset.map(map_fn, batched=True, batch_size=8)
+    dataset_images = dataset.map(map_fn, batched=True, batch_size=args.batch_size)
 
     if args.upload_to_hub:
-        dataset.push_to_hub(args.dataset_repo_or_id)
+        dataset_images.push_to_hub(args.dataset_repo_or_id)
     else:
-        dataset.save_to_disk(args.dataset_repo_or_id.split("/")[-1])
+        dataset_images.save_to_disk(args.dataset_repo_or_id.split("/")[-1])