InstantID official gradio ui added.

.gitattributes

@@ -33,3 +33,6 @@ saved_model/**/* 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
+*.jpg filter=lfs diff=lfs merge=lfs -text
+*.jpeg filter=lfs diff=lfs merge=lfs -text
+*.png filter=lfs diff=lfs merge=lfs -text

.gitignore

@@ -0,0 +1,4 @@
+
+*.pyc
+
+gradio_cached_examples/

README.md

@@ -4,7 +4,7 @@ emoji: 📈
 colorFrom: indigo
 colorTo: red
 sdk: gradio
-sdk_version: 4.19.2
+sdk_version: 4.15.0
 app_file: app.py
 pinned: false
 license: mit

app.py

@@ -1,8 +1,347 @@
 
+import random
+import numpy as np
+
+from style_template import styles
+
 import gradio as gr
 
-def greet(name):
-	return "Hello " + name + "!!"
 
-iface = gr.Interface(fn=greet, inputs="text", outputs="text")
-iface.launch()
+
+# global variable
+MAX_SEED = np.iinfo(np.int32).max
+STYLE_NAMES = list(styles.keys())
+DEFAULT_STYLE_NAME = "Spring Festival"
+enable_lcm_arg = False
+
+# Path to InstantID models
+face_adapter = f"./checkpoints/ip-adapter.bin"
+controlnet_path = f"./checkpoints/ControlNetModel"
+
+# controlnet-pose/canny/depth
+controlnet_pose_model = "thibaud/controlnet-openpose-sdxl-1.0"
+controlnet_canny_model = "diffusers/controlnet-canny-sdxl-1.0"
+controlnet_depth_model = "diffusers/controlnet-depth-sdxl-1.0-small"
+
+
+def toggle_lcm_ui (value):
+	if value:
+		return (
+			gr.update(minimum=0, maximum=100, step=1, value=5),
+			gr.update(minimum=0.1, maximum=20.0, step=0.1, value=1.5),
+		)
+	else:
+		return (
+			gr.update(minimum=5, maximum=100, step=1, value=30),
+			gr.update(minimum=0.1, maximum=20.0, step=0.1, value=5),
+		)
+
+
+def randomize_seed_fn (seed: int, randomize_seed: bool) -> int:
+	if randomize_seed:
+		seed = random.randint(0, MAX_SEED)
+	return seed
+
+
+def remove_tips ():
+	return gr.update(visible=False)
+
+
+def get_example ():
+	case = [
+		[
+			"./examples/yann-lecun_resize.jpg",
+			None,
+			"a man",
+			"Spring Festival",
+			"(lowres, low quality, worst quality:1.2), (text:1.2), watermark, (frame:1.2), deformed, ugly, deformed eyes, blur, out of focus, blurry, deformed cat, deformed, photo, anthropomorphic cat, monochrome, photo, pet collar, gun, weapon, blue, 3d, drones, drone, buildings in background, green",
+		],
+		[
+			"./examples/musk_resize.jpeg",
+			"./examples/poses/pose2.jpg",
+			"a man flying in the sky in Mars",
+			"Mars",
+			"(lowres, low quality, worst quality:1.2), (text:1.2), watermark, (frame:1.2), deformed, ugly, deformed eyes, blur, out of focus, blurry, deformed cat, deformed, photo, anthropomorphic cat, monochrome, photo, pet collar, gun, weapon, blue, 3d, drones, drone, buildings in background, green",
+		],
+		[
+			"./examples/sam_resize.png",
+			"./examples/poses/pose4.jpg",
+			"a man doing a silly pose wearing a suite",
+			"Jungle",
+			"(lowres, low quality, worst quality:1.2), (text:1.2), watermark, (frame:1.2), deformed, ugly, deformed eyes, blur, out of focus, blurry, deformed cat, deformed, photo, anthropomorphic cat, monochrome, photo, pet collar, gun, weapon, blue, 3d, drones, drone, buildings in background, gree",
+		],
+		[
+			"./examples/schmidhuber_resize.png",
+			"./examples/poses/pose3.jpg",
+			"a man sit on a chair",
+			"Neon",
+			"(lowres, low quality, worst quality:1.2), (text:1.2), watermark, (frame:1.2), deformed, ugly, deformed eyes, blur, out of focus, blurry, deformed cat, deformed, photo, anthropomorphic cat, monochrome, photo, pet collar, gun, weapon, blue, 3d, drones, drone, buildings in background, green",
+		],
+		[
+			"./examples/kaifu_resize.png",
+			"./examples/poses/pose.jpg",
+			"a man",
+			"Vibrant Color",
+			"(lowres, low quality, worst quality:1.2), (text:1.2), watermark, (frame:1.2), deformed, ugly, deformed eyes, blur, out of focus, blurry, deformed cat, deformed, photo, anthropomorphic cat, monochrome, photo, pet collar, gun, weapon, blue, 3d, drones, drone, buildings in background, green",
+		],
+	]
+	return case
+
+
+def run_for_examples (face_file, pose_file, prompt, style, negative_prompt):
+	return generate_image(
+		face_file,
+		pose_file,
+		prompt,
+		negative_prompt,
+		style,
+		20,  # num_steps
+		0.8,  # identitynet_strength_ratio
+		0.8,  # adapter_strength_ratio
+		0.4,  # pose_strength
+		0.3,  # canny_strength
+		0.5,  # depth_strength
+		["pose", "canny"],  # controlnet_selection
+		5.0,  # guidance_scale
+		42,  # seed
+		"EulerDiscreteScheduler",  # scheduler
+		False,  # enable_LCM
+		True,  # enable_Face_Region
+	)
+
+
+def generate_image (
+	face_image_path,
+	pose_image_path,
+	prompt,
+	negative_prompt,
+	style_name,
+	num_steps,
+	identitynet_strength_ratio,
+	adapter_strength_ratio,
+	pose_strength,
+	canny_strength,
+	depth_strength,
+	controlnet_selection,
+	guidance_scale,
+	seed,
+	scheduler,
+	enable_LCM,
+	enhance_face_region,
+	progress=gr.Progress(track_tqdm=True),
+):
+	return None, gr.update(visible=True)
+
+
+# Description
+title = r"""
+<h1 align="center">InstantID: Zero-shot Identity-Preserving Generation in Seconds</h1>
+"""
+
+description = r"""
+<b>Official 🤗 Gradio demo</b> for <a href='https://github.com/InstantID/InstantID' target='_blank'><b>InstantID: Zero-shot Identity-Preserving Generation in Seconds</b></a>.<br>
+
+We are organizing a Spring Festival event with HuggingFace from 2.7 to 2.25, and you can now generate pictures of Spring Festival costumes. Happy Dragon Year 🐲 ! Share the joy with your family.<br>
+
+How to use:<br>
+1. Upload an image with a face. For images with multiple faces, we will only detect the largest face. Ensure the face is not too small and is clearly visible without significant obstructions or blurring.
+2. (Optional) You can upload another image as a reference for the face pose. If you don't, we will use the first detected face image to extract facial landmarks. If you use a cropped face at step 1, it is recommended to upload it to define a new face pose.
+3. (Optional) You can select multiple ControlNet models to control the generation process. The default is to use the IdentityNet only. The ControlNet models include pose skeleton, canny, and depth. You can adjust the strength of each ControlNet model to control the generation process.
+4. Enter a text prompt, as done in normal text-to-image models.
+5. Click the <b>Submit</b> button to begin customization.
+6. Share your customized photo with your friends and enjoy! 😊"""
+
+article = r"""
+---
+"""
+
+tips = r"""
+### Usage tips of InstantID
+1. If you're not satisfied with the similarity, try increasing the weight of "IdentityNet Strength" and "Adapter Strength."	
+2. If you feel that the saturation is too high, first decrease the Adapter strength. If it remains too high, then decrease the IdentityNet strength.
+3. If you find that text control is not as expected, decrease Adapter strength.
+4. If you find that realistic style is not good enough, go for our Github repo and use a more realistic base model.
+"""
+
+css = """
+.gradio-container {width: 85% !important}
+"""
+with gr.Blocks(css=css) as demo:
+	# description
+	gr.Markdown(title)
+	gr.Markdown(description)
+
+	with gr.Row():
+		with gr.Column():
+			with gr.Row(equal_height=True):
+				# upload face image
+				face_file = gr.Image(
+					label="Upload a photo of your face", type="filepath"
+				)
+				# optional: upload a reference pose image
+				pose_file = gr.Image(
+					label="Upload a reference pose image (Optional)",
+					type="filepath",
+				)
+
+			# prompt
+			prompt = gr.Textbox(
+				label="Prompt",
+				info="Give simple prompt is enough to achieve good face fidelity",
+				placeholder="A photo of a person",
+				value="",
+			)
+
+			submit = gr.Button("Submit", variant="primary")
+			enable_LCM = gr.Checkbox(
+				label="Enable Fast Inference with LCM", value=enable_lcm_arg,
+				info="LCM speeds up the inference step, the trade-off is the quality of the generated image. It performs better with portrait face images rather than distant faces",
+			)
+			style = gr.Dropdown(
+				label="Style template",
+				choices=STYLE_NAMES,
+				value=DEFAULT_STYLE_NAME,
+			)
+
+			# strength
+			identitynet_strength_ratio = gr.Slider(
+				label="IdentityNet strength (for fidelity)",
+				minimum=0,
+				maximum=1.5,
+				step=0.05,
+				value=0.80,
+			)
+			adapter_strength_ratio = gr.Slider(
+				label="Image adapter strength (for detail)",
+				minimum=0,
+				maximum=1.5,
+				step=0.05,
+				value=0.80,
+			)
+			with gr.Accordion("Controlnet"):
+				controlnet_selection = gr.CheckboxGroup(
+					["pose", "canny", "depth"], label="Controlnet", value=["pose"],
+					info="Use pose for skeleton inference, canny for edge detection, and depth for depth map estimation. You can try all three to control the generation process"
+				)
+				pose_strength = gr.Slider(
+					label="Pose strength",
+					minimum=0,
+					maximum=1.5,
+					step=0.05,
+					value=0.40,
+				)
+				canny_strength = gr.Slider(
+					label="Canny strength",
+					minimum=0,
+					maximum=1.5,
+					step=0.05,
+					value=0.40,
+				)
+				depth_strength = gr.Slider(
+					label="Depth strength",
+					minimum=0,
+					maximum=1.5,
+					step=0.05,
+					value=0.40,
+				)
+			with gr.Accordion(open=False, label="Advanced Options"):
+				negative_prompt = gr.Textbox(
+					label="Negative Prompt",
+					placeholder="low quality",
+					value="(lowres, low quality, worst quality:1.2), (text:1.2), watermark, (frame:1.2), deformed, ugly, deformed eyes, blur, out of focus, blurry, deformed cat, deformed, photo, anthropomorphic cat, monochrome, pet collar, gun, weapon, blue, 3d, drones, drone, buildings in background, green",
+				)
+				num_steps = gr.Slider(
+					label="Number of sample steps",
+					minimum=1,
+					maximum=100,
+					step=1,
+					value=5 if enable_lcm_arg else 30,
+				)
+				guidance_scale = gr.Slider(
+					label="Guidance scale",
+					minimum=0.1,
+					maximum=20.0,
+					step=0.1,
+					value=0.0 if enable_lcm_arg else 5.0,
+				)
+				seed = gr.Slider(
+					label="Seed",
+					minimum=0,
+					maximum=MAX_SEED,
+					step=1,
+					value=42,
+				)
+				schedulers = [
+					"DEISMultistepScheduler",
+					"HeunDiscreteScheduler",
+					"EulerDiscreteScheduler",
+					"DPMSolverMultistepScheduler",
+					"DPMSolverMultistepScheduler-Karras",
+					"DPMSolverMultistepScheduler-Karras-SDE",
+				]
+				scheduler = gr.Dropdown(
+					label="Schedulers",
+					choices=schedulers,
+					value="EulerDiscreteScheduler",
+				)
+				randomize_seed = gr.Checkbox(label="Randomize seed", value=True)
+				enhance_face_region = gr.Checkbox(label="Enhance non-face region", value=True)
+
+		with gr.Column(scale=1):
+			gallery = gr.Image(label="Generated Images")
+			usage_tips = gr.Markdown(
+				label="InstantID Usage Tips", value=tips, visible=False
+			)
+
+		submit.click(
+			fn=remove_tips,
+			outputs=usage_tips,
+		).then(
+			fn=randomize_seed_fn,
+			inputs=[seed, randomize_seed],
+			outputs=seed,
+			queue=False,
+			api_name=False,
+		).then(
+			fn=generate_image,
+			inputs=[
+				face_file,
+				pose_file,
+				prompt,
+				negative_prompt,
+				style,
+				num_steps,
+				identitynet_strength_ratio,
+				adapter_strength_ratio,
+				pose_strength,
+				canny_strength,
+				depth_strength,
+				controlnet_selection,
+				guidance_scale,
+				seed,
+				scheduler,
+				enable_LCM,
+				enhance_face_region,
+			],
+			outputs=[gallery, usage_tips],
+		)
+
+		enable_LCM.input(
+			fn=toggle_lcm_ui,
+			inputs=[enable_LCM],
+			outputs=[num_steps, guidance_scale],
+			queue=False,
+		)
+
+	gr.Examples(
+		examples=get_example(),
+		inputs=[face_file, pose_file, prompt, style, negative_prompt],
+		fn=run_for_examples,
+		outputs=[gallery, usage_tips],
+		cache_examples=True,
+	)
+
+	gr.Markdown(article)
+
+demo.queue(api_open=False)
+demo.launch()

requirements.txt

@@ -1,2 +1,2 @@
 novita_client==0.4.12
-gradio==3.50.2
+gradio==4.15.0

style_template.py

@@ -0,0 +1,54 @@
+style_list = [
+    {
+        "name": "(No style)",
+        "prompt": "{prompt}",
+        "negative_prompt": "",
+    },
+    {
+        "name": "Spring Festival",
+        "prompt": "Flat illustration, a Chinese {prompt}, ancient style, wearing a red cloth, smile face, white skin, clean background, fireworks blooming, red lanterns",
+        "negative_prompt": "photo, deformed, black and white, realism, disfigured, low contrast, realistic, cropped, worst quality, missing fingers, extra digit, jpeg artifacts, signature, multiple, (lowres, low quality, worst quality:1.2)",
+    },
+    {
+        "name": "Watercolor",
+        "prompt": "watercolor painting, {prompt}. vibrant, beautiful, painterly, detailed, textural, artistic",
+        "negative_prompt": "(lowres, low quality, worst quality:1.2), (text:1.2), watermark, anime, photorealistic, 35mm film, deformed, glitch, low contrast, noisy",
+    },
+    {
+        "name": "Film Noir",
+        "prompt": "film noir style, ink sketch|vector, {prompt} highly detailed, sharp focus, ultra sharpness, monochrome, high contrast, dramatic shadows, 1940s style, mysterious, cinematic",
+        "negative_prompt": "(lowres, low quality, worst quality:1.2), (text:1.2), watermark, (frame:1.2), deformed, ugly, deformed eyes, blur, out of focus, blurry, deformed cat, deformed, photo, anthropomorphic cat, monochrome, photo, pet collar, gun, weapon, blue, 3d, drones, drone, buildings in background, green",
+    },
+    {
+        "name": "Neon",
+        "prompt": "masterpiece painting, buildings in the backdrop, kaleidoscope, lilac orange blue cream fuchsia bright vivid gradient colors, the scene is cinematic, {prompt}, emotional realism, double exposure, watercolor ink pencil, graded wash, color layering, magic realism, figurative painting, intricate motifs, organic tracery, polished",
+        "negative_prompt": "(lowres, low quality, worst quality:1.2), (text:1.2), watermark, (frame:1.2), deformed, ugly, deformed eyes, blur, out of focus, blurry, deformed cat, deformed, photo, anthropomorphic cat, monochrome, photo, pet collar, gun, weapon, blue, 3d, drones, drone, buildings in background, green",
+    },
+    {
+        "name": "Jungle",
+        "prompt": 'waist-up "{prompt} in a Jungle" by Syd Mead, tangerine cold color palette, muted colors, detailed, 8k,photo r3al,dripping paint,3d toon style,3d style,Movie Still',
+        "negative_prompt": "(lowres, low quality, worst quality:1.2), (text:1.2), watermark, (frame:1.2), deformed, ugly, deformed eyes, blur, out of focus, blurry, deformed cat, deformed, photo, anthropomorphic cat, monochrome, photo, pet collar, gun, weapon, blue, 3d, drones, drone, buildings in background, green",
+    },
+    {
+        "name": "Mars",
+        "prompt": "{prompt}, Post-apocalyptic. Mars Colony, Scavengers roam the wastelands searching for valuable resources, rovers, bright morning sunlight shining, (detailed) (intricate) (8k) (HDR) (cinematic lighting) (sharp focus)",
+        "negative_prompt": "(lowres, low quality, worst quality:1.2), (text:1.2), watermark, (frame:1.2), deformed, ugly, deformed eyes, blur, out of focus, blurry, deformed cat, deformed, photo, anthropomorphic cat, monochrome, photo, pet collar, gun, weapon, blue, 3d, drones, drone, buildings in background, green",
+    },
+    {
+        "name": "Vibrant Color",
+        "prompt": "vibrant colorful, ink sketch|vector|2d colors, at nightfall, sharp focus, {prompt}, highly detailed, sharp focus, the clouds,colorful,ultra sharpness",
+        "negative_prompt": "(lowres, low quality, worst quality:1.2), (text:1.2), watermark, (frame:1.2), deformed, ugly, deformed eyes, blur, out of focus, blurry, deformed cat, deformed, photo, anthropomorphic cat, monochrome, photo, pet collar, gun, weapon, blue, 3d, drones, drone, buildings in background, green",
+    },
+    {
+        "name": "Snow",
+        "prompt": "cinema 4d render, {prompt}, high contrast, vibrant and saturated, sico style, surrounded by magical glow,floating ice shards, snow crystals, cold, windy background, frozen natural landscape in background  cinematic atmosphere,highly detailed, sharp focus, intricate design, 3d, unreal engine, octane render, CG best quality, highres, photorealistic, dramatic lighting, artstation, concept art, cinematic, epic Steven Spielberg movie still, sharp focus, smoke, sparks, art by pascal blanche and greg rutkowski and repin, trending on artstation, hyperrealism painting, matte painting, 4k resolution",
+        "negative_prompt": "(lowres, low quality, worst quality:1.2), (text:1.2), watermark, (frame:1.2), deformed, ugly, deformed eyes, blur, out of focus, blurry, deformed cat, deformed, photo, anthropomorphic cat, monochrome, photo, pet collar, gun, weapon, blue, 3d, drones, drone, buildings in background, green",
+    },
+    {
+        "name": "Line art",
+        "prompt": "line art drawing {prompt} . professional, sleek, modern, minimalist, graphic, line art, vector graphics",
+        "negative_prompt": "anime, photorealistic, 35mm film, deformed, glitch, blurry, noisy, off-center, deformed, cross-eyed, closed eyes, bad anatomy, ugly, disfigured, mutated, realism, realistic, impressionism, expressionism, oil, acrylic",
+    },
+]
+
+styles = {k["name"]: (k["prompt"], k["negative_prompt"]) for k in style_list}