app.py: added base model option.

app.py

@@ -17,7 +17,8 @@ from style_template import styles
 # global variable
 MAX_SEED = np.iinfo(np.int32).max
 STYLE_NAMES = list(styles.keys())
-DEFAULT_STYLE_NAME = 'Spring Festival'
+DEFAULT_STYLE_NAME = 'Watercolor'
+DEFAULT_MODEL_NAME = 'sd_xl_base_1.0'
 enable_lcm_arg = False
 
 # Path to InstantID models
@@ -29,6 +30,76 @@ 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'
 
+SDXL_MODELS = [
+	"albedobaseXL_v04_130099",
+	"altxl_v60_146691",
+	"animeArtDiffusionXL_alpha2_91872",
+	"animeArtDiffusionXL_alpha3_93120",
+	"animeIllustDiffusion_v04_117809",
+	"animagineXLV3_v30_231047",
+	"breakdomainxl_V05g_124265",
+	"brixlAMustInYour_v40Dagobah_145992",
+	"cinemaxAlphaSDXLCinema_alpha1_107473",
+	"cineroXLPhotomatic_v12aPHENO_137703",
+	"clearhungAnimeXL_v10_117716",
+	"copaxTimelessxlSDXL1_colorfulV2_100729",
+	"counterfeitxl__98184",
+	"counterfeitxl_v10_108721",
+	"crystalClearXL_ccxl_97637",
+	"dreamshaperXL09Alpha_alpha2Xl10_91562",
+	"dynavisionXLAllInOneStylized_alpha036FP16Bakedvae_99980",
+	"dynavisionXLAllInOneStylized_beta0411Bakedvae_109970",
+	"dynavisionXLAllInOneStylized_release0534bakedvae_129001",
+	"fenrisxl_145_134980",
+	"foddaxlPhotorealism_v45_122788",
+	"formulaxl_v10_104889",
+	"juggernautXL_version2_113240",
+	"juggernautXL_version5_126522",
+	"juggernautXL_v8Rundiffusion_227002",
+	"kohakuXL_alpha7_111843",
+	"LahMysteriousSDXL_v40_122478",
+	"leosamsHelloworldSDXLModel_helloworldSDXL10_112178",
+	"leosamsHelloworldSDXL_helloworldSDXL50_268813",
+	"mbbxlUltimate_v10RC_94686",
+	"moefusionSDXL_v10_114018",
+	"nightvisionXLPhotorealisticPortrait_beta0681Bakedvae_108833",
+	"nightvisionXLPhotorealisticPortrait_beta0702Bakedvae_113098",
+	"nightvisionXLPhotorealisticPortrait_release0770Bakedvae_154525",
+	"novaPrimeXL_v10_107899",
+	"pixelwave_v10_117722",
+	"protovisionXLHighFidelity3D_beta0520Bakedvae_106612",
+	"protovisionXLHighFidelity3D_release0620Bakedvae_131308",
+	"protovisionXLHighFidelity3D_release0630Bakedvae_154359",
+	"realismEngineSDXL_v05b_131513",
+	"realismEngineSDXL_v10_136287",
+	"realisticStockPhoto_v10_115618",
+	"RealitiesEdgeXL_4_122673",
+	"realvisxlV20_v20Bakedvae_129156",
+	"riotDiffusionXL_v20_139293",
+	"roxl_v10_109354",
+	"sd_xl_base_0.9",
+	"sd_xl_base_1.0",
+	"sdxlNijiSpecial_sdxlNijiSE_115638",
+	"sdxlNijiV3_sdxlNijiV3_104571",
+	"sdxlNijiV51_sdxlNijiV51_112807",
+	"sd_xl_refiner_1.0",
+	"sdxlUnstableDiffusers_v8HEAVENSWRATH_133813",
+	"sdXL_v10Refiner_91495",
+	"sdxlYamersAnimeUltra_yamersAnimeV3_121537",
+	"shikianimexl_v10_93788",
+	#"stable-diffusion-xl-base-1.0",
+	"theTalosProject_v10_117893",
+	"thinkdiffusionxl_v10_145931",
+	"protovisionXLHighFidelity3D_releaseV660Bakedvae_207131",
+	"voidnoisecorexl_r1486_150780",
+	"wlopArienwlopstylexl_v10_101973",
+	"wlopSTYLEXL_v2_126171",
+	"xl13AsmodeusSFWNSFW_v22BakedVAE_111954",
+	"xxmix9realisticsdxl_v10_123235",
+	"zavychromaxl_b2_103298",
+	"zavychromaxl_v21_129006",
+]
+
 
 def get_novita_client (novita_key):
 	client = NovitaClient(novita_key, os.getenv('NOVITA_API_URI', None))
@@ -120,10 +191,11 @@ def get_example ():
 
 
 def run_for_examples_with_key (novita_key):
-	def run_for_examples (face_file, pose_file, prompt, style, negative_prompt):
+	def run_for_examples (model_name, face_file, pose_file, prompt, style, negative_prompt):
 		print('run_for_examples:', novita_key, face_file)
 		#return generate_image(
 		#	novita_key,
+		#	model_name,
 		#	face_file,
 		#	pose_file,
 		#	prompt,
@@ -148,6 +220,7 @@ def run_for_examples_with_key (novita_key):
 
 def generate_image (
 	novita_key1,
+	model_name,
 	face_image_path,
 	pose_image_path,
 	prompt,
@@ -194,7 +267,7 @@ def generate_image (
 			'extra': {
 				'response_image_type': 'jpeg',
 			},
-			'model_name': 'sd_xl_base_1.0.safetensors',
+			'model_name': f'{model_name}.safetensors',
 			'face_image_assets_ids': client.upload_assets([face_image_path]),
 			'ref_image_assets_ids': client.upload_assets([pose_image_path]) if pose_image_path else [],
 			'prompt': prompt,
@@ -235,15 +308,14 @@ def generate_image (
 
 # Description
 title = r'''
-<h1 align="center">InstantID: Zero-shot Identity-Preserving Generation in Seconds</h1>
+<h1 align="center">InstantID: Zero-shot Identity-Preserving Generation in Seconds (via Novita)</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>
+<a href='https://github.com/InstantID/InstantID' target="_blank"><b>InstantID</b></a> demo via <a href="https://novita.ai/" target="_blank"><b>Novita API</b></a>.<br>
 
 How to use:<br>
+0. Input your <a href="https://novita.ai/dashboard/key" target="_blank"><b>Novita API Key</b></a>.
 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.
@@ -273,7 +345,7 @@ with gr.Blocks(css=css) as demo:
 
 	with gr.Row():
 		with gr.Column(scale=1):
-			novita_key = gr.Textbox(value='', label='Novita.AI API KEY (store in broweser)', placeholder='novita.ai api key', type='password')
+			novita_key = gr.Textbox(value='', label='Novita.AI API KEY', placeholder='novita.ai api key', type='password')
 		with gr.Column(scale=1):
 			user_balance = gr.Textbox(label='User Balance', value='0.0')
 
@@ -303,6 +375,13 @@ with gr.Blocks(css=css) as demo:
 			#	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',
 			#)
+
+			model_name = gr.Dropdown(
+				label='Base model',
+				choices=SDXL_MODELS,
+				value=DEFAULT_MODEL_NAME,
+			)
+
 			style = gr.Dropdown(
 				label='Style template',
 				choices=STYLE_NAMES,
@@ -415,6 +494,7 @@ with gr.Blocks(css=css) as demo:
 			fn=generate_image,
 			inputs=[
 				novita_key,
+				model_name,
 				face_file,
 				pose_file,
 				prompt,
@@ -445,7 +525,7 @@ with gr.Blocks(css=css) as demo:
 
 	#gr.Examples(
 	#	examples=get_example(),
-	#	inputs=[face_file, pose_file, prompt, style, negative_prompt],
+	#	inputs=[model_name, face_file, pose_file, prompt, style, negative_prompt],
 	#	fn=run_for_examples_with_key(novita_key),
 	#	run_on_click=True,
 	#	outputs=[gallery, usage_tips],