Upload 2 files

app.py

@@ -76,12 +76,16 @@ with gr.Blocks(fill_width=True, elem_id="container", css=css, delete_cache=(60,
                 with gr.Row():
                     seed = gr.Slider(label="Seed", minimum=0, maximum=MAX_SEED, step=1, value=0)
                     randomize_seed = gr.Checkbox(label="Randomize seed", value=True)
+                    gpu_duration = gr.Number(minimum=5, maximum=240, value=59, show_label=False, container=False, info="GPU time duration (seconds)")
 
                 with gr.Row():
                     width = gr.Slider(label="Width", minimum=256, maximum=MAX_IMAGE_SIZE, step=32, value=1024) # 832
                     height = gr.Slider(label="Height", minimum=256, maximum=MAX_IMAGE_SIZE, step=32, value=1024) # 1216
                     guidance_scale = gr.Slider(label="Guidance scale", minimum=0.0, maximum=30.0, step=0.1, value=7)
                     num_inference_steps = gr.Slider(label="Number of inference steps", minimum=1, maximum=100, step=1, value=28)
+                    pag_scale = gr.Slider(minimum=0.0, maximum=10.0, step=0.1, value=0.0, label="PAG Scale")
+                    clip_skip = gr.Checkbox(value=True, label="Layer 2 Clip Skip")
+                    free_u = gr.Checkbox(value=False, label="FreeU")
 
                 with gr.Row():
                     with gr.Column(scale=4):
@@ -204,7 +208,8 @@ with gr.Blocks(fill_width=True, elem_id="container", css=css, delete_cache=(60,
         inputs=[prompt, negative_prompt, seed, randomize_seed, width, height,
                 guidance_scale, num_inference_steps, model_name,
                 lora1, lora1_wt, lora2, lora2_wt, lora3, lora3_wt, lora4, lora4_wt, lora5, lora5_wt,
-                sampler, vae_model, auto_trans, schedule_type, schedule_prediction_type, recom_prompt],
+                sampler, vae_model, auto_trans, schedule_type, schedule_prediction_type,
+                clip_skip, pag_scale, free_u, gpu_duration, recom_prompt],
         outputs=[result],
         queue=True,
         show_progress="full",
@@ -217,7 +222,8 @@ with gr.Blocks(fill_width=True, elem_id="container", css=css, delete_cache=(60,
         inputs=[prompt, negative_prompt, seed, randomize_seed, width, height,
                 guidance_scale, num_inference_steps, model_name,
                 lora1, lora1_wt, lora2, lora2_wt, lora3, lora3_wt, lora4, lora4_wt, lora5, lora5_wt,
-                sampler, vae_model, auto_trans, schedule_type, schedule_prediction_type, recom_prompt],
+                sampler, vae_model, auto_trans, schedule_type, schedule_prediction_type,
+                clip_skip, pag_scale, free_u, gpu_duration, recom_prompt],
         outputs=[result],
         queue=False,
         show_api=True,
@@ -240,7 +246,8 @@ with gr.Blocks(fill_width=True, elem_id="container", css=css, delete_cache=(60,
         inputs=[prompt, negative_prompt, seed, randomize_seed, width, height,
                 guidance_scale, num_inference_steps, model_name,
                 lora1, lora1_wt, lora2, lora2_wt, lora3, lora3_wt, lora4, lora4_wt, lora5, lora5_wt,
-                sampler, vae_model, auto_trans, schedule_type, schedule_prediction_type, recom_prompt],
+                sampler, vae_model, auto_trans, schedule_type, schedule_prediction_type,
+                clip_skip, pag_scale, free_u, gpu_duration, recom_prompt],
         outputs=[result],
         queue=True,
         show_progress="full",

dc.py

@@ -139,7 +139,7 @@ class GuiSD:
         self.last_load = datetime.now()
         self.inventory = []
 
-    def update_storage_models(self, storage_floor_gb=42, required_inventory_for_purge=3):
+    def update_storage_models(self, storage_floor_gb=32, required_inventory_for_purge=3):
         while get_used_storage_gb() > storage_floor_gb:
             if len(self.inventory) < required_inventory_for_purge:
                 break
@@ -726,23 +726,21 @@ from modutils import (safe_float, escape_lora_basename, to_lora_key, to_lora_pat
 
 #@spaces.GPU
 def infer(prompt, negative_prompt, seed, randomize_seed, width, height, guidance_scale, num_inference_steps,
-           model_name = load_diffusers_format_model[0], lora1 = None, lora1_wt = 1.0, lora2 = None, lora2_wt = 1.0,
-           lora3 = None, lora3_wt = 1.0, lora4 = None, lora4_wt = 1.0, lora5 = None, lora5_wt = 1.0,
-           sampler = "Euler", vae = None, translate=True, schedule_type=SCHEDULE_TYPE_OPTIONS[0], schedule_prediction_type=SCHEDULE_PREDICTION_TYPE_OPTIONS[0],
-           recom_prompt = True, progress=gr.Progress(track_tqdm=True)):
+          model_name=load_diffusers_format_model[0], lora1=None, lora1_wt=1.0, lora2=None, lora2_wt=1.0,
+          lora3=None, lora3_wt=1.0, lora4=None, lora4_wt=1.0, lora5=None, lora5_wt=1.0,
+          sampler="Euler", vae=None, translate=False, schedule_type=SCHEDULE_TYPE_OPTIONS[0], schedule_prediction_type=SCHEDULE_PREDICTION_TYPE_OPTIONS[0],
+          clip_skip=True, pag_scale=0.0, free_u=False, gpu_duration=59, recom_prompt=True, progress=gr.Progress(track_tqdm=True)):
     MAX_SEED = np.iinfo(np.int32).max
 
     image_previews = True
     load_lora_cpu = False
     verbose_info = False
-    gpu_duration = 59
     filename_pattern = "model,seed"
 
     images: list[tuple[PIL.Image.Image, str | None]] = []
     progress(0, desc="Preparing...")
 
-    if randomize_seed:
-        seed = random.randint(0, MAX_SEED)
+    if randomize_seed: seed = random.randint(0, MAX_SEED)
 
     generator = torch.Generator().manual_seed(seed).seed()
 
@@ -767,15 +765,15 @@ def infer(prompt, negative_prompt, seed, randomize_seed, width, height, guidance
     progress(1, desc="Model loaded.")
     progress(0, desc="Starting Inference...")
     for info_state, stream_images, info_images in sd_gen_generate_pipeline(prompt, negative_prompt, 1, num_inference_steps,
-        guidance_scale, True, generator, lora1, lora1_wt, lora2, lora2_wt, lora3, lora3_wt,
+        guidance_scale, clip_skip, generator, lora1, lora1_wt, lora2, lora2_wt, lora3, lora3_wt,
         lora4, lora4_wt, lora5, lora5_wt, sampler, schedule_type, schedule_prediction_type,
         height, width, model_name, vae, TASK_MODEL_LIST[0], None, "Canny", 512, 1024,
         None, None, None, 0.35, 100, 200, 0.1, 0.1, 1.0, 0., 1., False, "Classic", None,
         1.0, 100, 10, 30, 0.55, "Use same sampler", "", "",
         False, True, 1, True, False, image_previews, False, False, filename_pattern, "./images", False, False, False, True, 1, 0.55,
-        False, False, False, True, False, "Use same sampler", False, "", "", 0.35, True, True, False, 4, 4, 32,
+        False, free_u, False, True, False, "Use same sampler", False, "", "", 0.35, True, True, False, 4, 4, 32,
         False, "", "", 0.35, True, True, False, 4, 4, 32,
-        True, None, None, "plus_face", "original", 0.7, None, None, "base", "style", 0.7, 0.0,
+        True, None, None, "plus_face", "original", 0.7, None, None, "base", "style", 0.7, pag_scale,
         load_lora_cpu, verbose_info, gpu_duration
     ):
         images = stream_images if isinstance(stream_images, list) else images
@@ -787,10 +785,10 @@ def infer(prompt, negative_prompt, seed, randomize_seed, width, height, guidance
 
 #@spaces.GPU
 def _infer(prompt, negative_prompt, seed, randomize_seed, width, height, guidance_scale, num_inference_steps,
-            model_name = load_diffusers_format_model[0], lora1 = None, lora1_wt = 1.0, lora2 = None, lora2_wt = 1.0,
-            lora3 = None, lora3_wt = 1.0, lora4 = None, lora4_wt = 1.0, lora5 = None, lora5_wt = 1.0,
-            sampler = "Euler", vae = None, translate = True, schedule_type=SCHEDULE_TYPE_OPTIONS[0], schedule_prediction_type=SCHEDULE_PREDICTION_TYPE_OPTIONS[0],
-            recom_prompt = True, progress=gr.Progress(track_tqdm=True)):
+           model_name=load_diffusers_format_model[0], lora1=None, lora1_wt=1.0, lora2=None, lora2_wt=1.0,
+           lora3=None, lora3_wt=1.0, lora4=None, lora4_wt=1.0, lora5=None, lora5_wt=1.0,
+           sampler="Euler", vae=None, translate=False, schedule_type=SCHEDULE_TYPE_OPTIONS[0], schedule_prediction_type=SCHEDULE_PREDICTION_TYPE_OPTIONS[0],
+           clip_skip=True, pag_scale=0.0, free_u=False, gpu_duration=59, recom_prompt=True, progress=gr.Progress(track_tqdm=True)):
     return gr.update()