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

all_branches_diffusers.txt

@@ -0,0 +1,56 @@
+google/ncsnpp-ffhq-1024: ['master']
+google/ncsnpp-ffhq-1024: ['master']
+shalpin87/diffusion_conditional: ['backup']
+CompVis/stable-diffusion-v1-3: ['fp16']
+CompVis/stable-diffusion-v1-1: ['fp16']
+CompVis/stable-diffusion-v1-2: ['fp16']
+CompVis/stable-diffusion-v1-4: ['non-ema', 'onnx', 'bf16', 'flax', 'fp16']
+hakurei/waifu-diffusion: ['fp16']
+rinna/japanese-stable-diffusion: ['fp16']
+naclbit/trinart_stable_diffusion_v2: ['diffusers-95k', 'diffusers-60k', 'diffusers-115k']
+pcuenq/stable-diffusion-v1-4: ['onnx']
+lambdalabs/sd-pokemon-diffusers: ['onnx']
+CompVis/stable-diffusion-v1-5: ['fp16']
+Gazoche/sd-gundam-diffusers: ['epoch-000020', 'epoch-000081', 'epoch-000025']
+runwayml/stable-diffusion-inpainting: ['onnx', 'fp16']
+fusing/sd-inpaint-temp: ['fp16']
+runwayml/stable-diffusion-v1-5: ['onnx', 'fp16', 'non-ema', 'flax', 'bf16']
+ckpt/sd15: ['flax', 'bf16', 'fp16']
+aarondotwork/sd-pokemon-diffusers: ['fp16']
+technillogue/waifu-diffusion: ['fp16']
+DGSpitzer/Cyberpunk-Anime-Diffusion: ['fp16']
+uripper/GIANNIS: ['ONNX', 'Traced', 'ONNX-Q']
+microsoft/vq-diffusion-ithq: ['fp16']
+fusing/rdm: ['fp16']
+CompVis/ldm-super-resolution-4x-openimages: ['fp16']
+lilpotat/f2: ['flax']
+lilpotat/a3: ['flax']
+lilpotat/rbm: ['flax']
+BAAI/AltDiffusion: ['fp16']
+fusing/test: ['fp16']
+stabilityai/stable-diffusion-2: ['fp16', 'bf16']
+stabilityai/stable-diffusion-2-base: ['onnx', 'fp16']
+stabilityai/stable-diffusion-2-depth: ['fp16']
+stabilityai/stable-diffusion-2-inpainting: ['fp16']
+stabilityai/stable-diffusion-x4-upscaler: ['fp16']
+Abhilashvj/openjourney_copy: ['master']
+questcoast/clone-wars-diffusion-v1: ['readme']
+lilpotat/ashleymoore: ['flax']
+jplumail/matthieu-v1-pipe: ['fp16']
+stabilityai/stable-diffusion-2-1: ['bf16', 'fp16']
+stabilityai/stable-diffusion-2-1-base: ['fp16']
+jplumail/matthieu-v2-pipe: ['fp16']
+NickKolok/arikioyami-20221223_1: ['backforward_overfit']
+mann-e/mann-e: ['master']
+DucHaiten/DucHaitenAIart: ['safetensors']
+ShibaDeveloper/olivia-v1.0: ['safetensors']
+cdefghijkl/luber: ['safetensors']
+mddy/abyss2-diffusers: ['master']
+OFA-Sys/small-stable-diffusion-v0: ['onnx']
+timbrooks/instruct-pix2pix: ['fp16']
+DucHaiten/DucHaitenAnime: ['vae']
+neemspees/dnd-maps-2: ['v2', 'v3']
+ruiruin/counmargemodel: ['fp16']
+Nacholmo/AbyssOrangeMix2-hard-vae-swapped: ['fp16']
+Nacholmo/Counterfeit-V2.5-vae-swapped: ['de_vae', 'dvae', 'fp16']
+Nacholmo/VOXO-v0-vtuber-diffusers: ['fp16']

cat.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:aa9441dc014d5e86567c5ef165e10b50d2a7b3a68d90686d0cd1006792adf334
-size 237300

dog.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:becf079d61d7f35727bcc0d8506ddcdcddb61e62d611840ff3d18eca7fb6338c
-size 237300

get_model_ids.py

@@ -4,6 +4,7 @@ from huggingface_hub import HfApi
 api = HfApi()
 out = api.list_models(filter="diffusers")
 model_ids = [x.modelId for x in out]
+print(len(model_ids))
 
 with open("./model_ids.txt", "w") as f:
     for _id in model_ids:

run_local.py

@@ -1,5 +1,6 @@
 #!/usr/bin/env python3
 from diffusers import StableDiffusionPipeline, DPMSolverSinglestepScheduler, DPMSolverMultistepScheduler, DEISMultistepScheduler, HeunDiscreteScheduler
+from diffusers.schedulers.scheduling_unipc_multistep import UniPCMultistepScheduler
 import time
 import os
 from huggingface_hub import HfApi
@@ -14,12 +15,13 @@ start_time = time.time()
 #pipe = StableDiffusionPipeline.from_pretrained(path, torch_dtype=torch.float16, device_map="auto")
 #pipe.scheduler = HeunDiscreteScheduler.from_config(pipe.scheduler.config)
 pipe = StableDiffusionPipeline.from_pretrained(path, torch_dtype=torch.float16)
-pipe.scheduler = HeunDiscreteScheduler.from_config(pipe.scheduler.config)
+pipe.scheduler = UniPCMultistepScheduler.from_config(pipe.scheduler.config)
 pipe = pipe.to("cuda")
 
 prompt = "a highly realistic photo of green turtle"
+
 generator = torch.Generator(device="cuda").manual_seed(0)
-image = pipe(prompt, generator=generator, num_inference_steps=25).images[0]
+image = pipe(prompt, generator=generator, num_inference_steps=15).images[0]
 print("Time", time.time() - start_time)
 
 path = os.path.join(Path.home(), "images", "aa.png")

run_pix2pix0.py

@@ -2,44 +2,52 @@
 from huggingface_hub import HfApi
 import torch
 
-# https://github.com/pix2pixzero/pix2pix-zero/blob/main/src/edit_synthetic.py
 import requests
+from PIL import Image
 
 from diffusers import DDIMScheduler, StableDiffusionPix2PixZeroPipeline
+from diffusers.schedulers.scheduling_ddim_inverse import DDIMInverseScheduler
+from transformers import BlipForConditionalGeneration, BlipProcessor
 
 api = HfApi()
+img_url = "https://github.com/pix2pixzero/pix2pix-zero/raw/main/assets/test_images/cats/cat_6.png"
+raw_image = Image.open(requests.get(img_url, stream=True).raw).convert('RGB').resize((512, 512))
 
-
-def download(embedding_url, local_filepath):
-    r = requests.get(embedding_url)
-    with open(local_filepath, "wb") as f:
-        f.write(r.content)
-
+processor = BlipProcessor.from_pretrained("Salesforce/blip-image-captioning-base")
+model = BlipForConditionalGeneration.from_pretrained("Salesforce/blip-image-captioning-base", torch_dtype=torch.float16, low_cpu_mem_usage=True)
 
 model_ckpt = "CompVis/stable-diffusion-v1-4"
 pipeline = StableDiffusionPix2PixZeroPipeline.from_pretrained(
-    model_ckpt, conditions_input_image=False, torch_dtype=torch.float16
+    model_ckpt, caption_generator=model, caption_processor=processor, torch_dtype=torch.float16, safety_checker=None,
 )
+pipeline.enable_model_cpu_offload()
+
+caption = pipeline.generate_caption(raw_image)
+
 pipeline.scheduler = DDIMScheduler.from_config(pipeline.scheduler.config)
-pipeline.to("cuda")
+pipeline.inverse_scheduler = DDIMInverseScheduler.from_config(pipeline.scheduler.config)
+
+print(caption)
 
+generator = torch.manual_seed(0)
+inv_latents = pipeline.invert(caption, image=raw_image, generator=generator).latents
 
-prompt = "a high resolution painting of a cat in the style of van gough"
-source_embedding_url = "https://github.com/pix2pixzero/pix2pix-zero/raw/main/assets/embeddings_sd_1.4/cat.pt"
-target_embedding_url = "https://github.com/pix2pixzero/pix2pix-zero/raw/main/assets/embeddings_sd_1.4/dog.pt"
+source_prompts = 4 * ["a cat sitting on the street", "a cat playing in the field", "a face of a cat"]
+target_prompts = 4 * ["a dog sitting on the street", "a dog playing in the field", "a face of a dog"]
 
-for url in [source_embedding_url, target_embedding_url]:
-    download(url, url.split("/")[-1])
+source_embeds = pipeline.get_embeds(source_prompts, batch_size=2)
+target_embeds = pipeline.get_embeds(target_prompts, batch_size=2)
 
-source_embeds = torch.load(source_embedding_url.split("/")[-1])
-target_embeds = torch.load(target_embedding_url.split("/")[-1])
 
 image = pipeline(
-    prompt,
+    caption,
     source_embeds=source_embeds,
     target_embeds=target_embeds,
     num_inference_steps=50,
     cross_attention_guidance_amount=0.15,
+    generator=generator,
+    latents=inv_latents,
+    negative_prompt=caption,
 ).images[0]
 
 path = "/home/patrick_huggingface_co/images/aa.png"