Upload 4 files

app.py

@@ -7,7 +7,8 @@ from dc import (infer, _infer, pass_result, get_diffusers_model_list, get_sample
     get_vaes, enable_model_recom_prompt, enable_diffusers_model_detail, extract_exif_data, esrgan_upscale, UPSCALER_KEYS,
     preset_quality, preset_styles, process_style_prompt, get_all_lora_tupled_list, update_loras, apply_lora_prompt,
     download_my_lora, search_civitai_lora, update_civitai_selection, select_civitai_lora, search_civitai_lora_json,
-    get_t2i_model_info, get_civitai_tag, CIVITAI_SORT, CIVITAI_PERIOD, CIVITAI_BASEMODEL)
+    get_t2i_model_info, get_civitai_tag, CIVITAI_SORT, CIVITAI_PERIOD, CIVITAI_BASEMODEL,
+    SCHEDULE_TYPE_OPTIONS, SCHEDULE_PREDICTION_TYPE_OPTIONS)
 # Translator
 from llmdolphin import (dolphin_respond_auto, dolphin_parse_simple,
     get_llm_formats, get_dolphin_model_format, get_dolphin_models,
@@ -92,6 +93,8 @@ with gr.Blocks(fill_width=True, elem_id="container", css=css, delete_cache=(60,
 
                 with gr.Row():
                     sampler = gr.Dropdown(label="Sampler", choices=get_samplers(), value="Euler")
+                    schedule_type = gr.Dropdown(label="Schedule type", choices=SCHEDULE_TYPE_OPTIONS, value=SCHEDULE_TYPE_OPTIONS[0])
+                    schedule_prediction_type = gr.Dropdown(label="Discrete Sampling Type", choices=SCHEDULE_PREDICTION_TYPE_OPTIONS, value=SCHEDULE_PREDICTION_TYPE_OPTIONS[0])
                     vae_model = gr.Dropdown(label="VAE Model", choices=get_vaes(), value=get_vaes()[0])
 
                 with gr.Accordion("LoRA", open=True, visible=True):
@@ -161,7 +164,7 @@ with gr.Blocks(fill_width=True, elem_id="container", css=css, delete_cache=(60,
                         with gr.Accordion("Select from Gallery", open=False):
                             lora_search_civitai_gallery = gr.Gallery([], label="Results", allow_preview=False, columns=5, show_share_button=False, interactive=False)
                         lora_search_civitai_result = gr.Dropdown(label="Search Results", choices=[("", "")], value="", allow_custom_value=True, visible=False)
-                        lora_download_url = gr.Textbox(label="LoRA URL", placeholder="https://civitai.com/api/download/models/28907", info="It has to be .safetensors files, and you can also download them from Hugging Face.", lines=1)
+                        lora_download_url = gr.Textbox(label="LoRA's download URL", placeholder="https://civitai.com/api/download/models/28907", info="It has to be .safetensors files, and you can also download them from Hugging Face.", lines=1)
                         lora_download = gr.Button("Get and set LoRA and apply to prompt")
 
                 with gr.Row():
@@ -200,7 +203,7 @@ 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],
+                sampler, vae_model, auto_trans, schedule_type, schedule_prediction_type],
         outputs=[result],
         queue=True,
         show_progress="full",
@@ -213,7 +216,7 @@ 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],
+                sampler, vae_model, auto_trans, schedule_type, schedule_prediction_type],
         outputs=[result],
         queue=False,
         show_api=True,
@@ -236,7 +239,7 @@ 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],
+                sampler, vae_model, auto_trans, schedule_type, schedule_prediction_type],
         outputs=[result],
         queue=True,
         show_progress="full",

dc.py

@@ -690,29 +690,29 @@ sd_gen = GuiSD()
 
 from pathlib import Path
 from PIL import Image
-import random, json
+import PIL
+import numpy as np
+import random
+import json
+import shutil
 from modutils import (safe_float, escape_lora_basename, to_lora_key, to_lora_path,
     get_local_model_list, get_private_lora_model_lists, get_valid_lora_name,
     get_valid_lora_path, get_valid_lora_wt, get_lora_info, CIVITAI_SORT, CIVITAI_PERIOD, CIVITAI_BASEMODEL,
     normalize_prompt_list, get_civitai_info, search_lora_on_civitai, translate_to_en, get_t2i_model_info, get_civitai_tag, save_image_history)
 
 
-
 #@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, progress=gr.Progress(track_tqdm=True)):
-    import PIL
-    import numpy as np
+           sampler = "Euler", vae = None, translate=True, schedule_type=SCHEDULE_TYPE_OPTIONS[0], schedule_prediction_type=SCHEDULE_PREDICTION_TYPE_OPTIONS[0],
+           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
-    schedule_type = SCHEDULE_TYPE_OPTIONS[0]
-    schedule_prediction_type = SCHEDULE_PREDICTION_TYPE_OPTIONS[0]
     filename_pattern = "model,seed"
 
     images: list[tuple[PIL.Image.Image, str | None]] = []
@@ -766,8 +766,6 @@ def __infer(prompt, negative_prompt, seed, randomize_seed, width, height, guidan
            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 a", vae = None, translate=True, progress=gr.Progress(track_tqdm=True)):
-    import PIL
-    import numpy as np
     MAX_SEED = np.iinfo(np.int32).max
 
     load_lora_cpu = False
@@ -824,7 +822,8 @@ def __infer(prompt, negative_prompt, seed, randomize_seed, width, height, guidan
 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 a", vae = None, translate = True, progress=gr.Progress(track_tqdm=True)):
+            sampler = "Euler", vae = None, translate = True, schedule_type=SCHEDULE_TYPE_OPTIONS[0], schedule_prediction_type=SCHEDULE_PREDICTION_TYPE_OPTIONS[0],
+            progress=gr.Progress(track_tqdm=True)):
     return gr.update(visible=True)
 
 
@@ -868,7 +867,6 @@ def enable_diffusers_model_detail(is_enable: bool = False, model_name: str = "")
 
 
 def load_model_prompt_dict():
-    import json
     dict = {}
     try:
         with open('model_dict.json', encoding='utf-8') as f:
@@ -1005,7 +1003,6 @@ def download_lora(dl_urls: str):
 
 
 def copy_lora(path: str, new_path: str):
-    import shutil
     if path == new_path: return new_path
     cpath = Path(path)
     npath = Path(new_path)

modutils.py

@@ -960,7 +960,7 @@ def move_file_lora(filepaths):
 
 CIVITAI_SORT = ["Highest Rated", "Most Downloaded", "Newest"]
 CIVITAI_PERIOD = ["AllTime", "Year", "Month", "Week", "Day"]
-CIVITAI_BASEMODEL = ["Pony", "SD 1.5", "SDXL 1.0", "Flux.1 D", "Flux.1 S"]
+CIVITAI_BASEMODEL = ["Pony", "Illustrious", "SDXL 1.0", "SD 1.5", "Flux.1 D", "Flux.1 S"]
 
 
 def get_civitai_info(path):
@@ -1320,10 +1320,10 @@ style_list = [
 
 
 optimization_list = {
-    "None": [28, 7., 'Euler a', False, 'None', 1.],
-    "Default": [28, 7., 'Euler a', False, 'None', 1.],
-    "SPO": [28, 7., 'Euler a', True, 'loras/spo_sdxl_10ep_4k-data_lora_diffusers.safetensors', 1.],
-    "DPO": [28, 7., 'Euler a', True, 'loras/sdxl-DPO-LoRA.safetensors', 1.],
+    "None": [28, 7., 'Euler', False, 'None', 1.],
+    "Default": [28, 7., 'Euler', False, 'None', 1.],
+    "SPO": [28, 7., 'Euler', True, 'loras/spo_sdxl_10ep_4k-data_lora_diffusers.safetensors', 1.],
+    "DPO": [28, 7., 'Euler', True, 'loras/sdxl-DPO-LoRA.safetensors', 1.],
     "DPO Turbo": [8, 2.5, 'LCM', True, 'loras/sd_xl_dpo_turbo_lora_v1-128dim.safetensors', 1.],
     "SDXL Turbo": [8, 2.5, 'LCM', True, 'loras/sd_xl_turbo_lora_v1.safetensors', 1.],
     "Hyper-SDXL 12step": [12, 5., 'TCD', True, 'loras/Hyper-SDXL-12steps-CFG-lora.safetensors', 1.],
@@ -1331,10 +1331,10 @@ optimization_list = {
     "Hyper-SDXL 4step": [4, 0, 'TCD', True, 'loras/Hyper-SDXL-4steps-lora.safetensors', 1.],
     "Hyper-SDXL 2step": [2, 0, 'TCD', True, 'loras/Hyper-SDXL-2steps-lora.safetensors', 1.],
     "Hyper-SDXL 1step": [1, 0, 'TCD', True, 'loras/Hyper-SDXL-1steps-lora.safetensors', 1.],
-    "PCM 16step": [16, 4., 'Euler a trailing', True, 'loras/pcm_sdxl_normalcfg_16step_converted.safetensors', 1.],
-    "PCM 8step": [8, 4., 'Euler a trailing', True, 'loras/pcm_sdxl_normalcfg_8step_converted.safetensors', 1.],
-    "PCM 4step": [4, 2., 'Euler a trailing', True, 'loras/pcm_sdxl_smallcfg_4step_converted.safetensors', 1.],
-    "PCM 2step": [2, 1., 'Euler a trailing', True, 'loras/pcm_sdxl_smallcfg_2step_converted.safetensors', 1.],
+    "PCM 16step": [16, 4., 'Euler trailing', True, 'loras/pcm_sdxl_normalcfg_16step_converted.safetensors', 1.],
+    "PCM 8step": [8, 4., 'Euler trailing', True, 'loras/pcm_sdxl_normalcfg_8step_converted.safetensors', 1.],
+    "PCM 4step": [4, 2., 'Euler trailing', True, 'loras/pcm_sdxl_smallcfg_4step_converted.safetensors', 1.],
+    "PCM 2step": [2, 1., 'Euler trailing', True, 'loras/pcm_sdxl_smallcfg_2step_converted.safetensors', 1.],
 }
 
 
@@ -1362,13 +1362,13 @@ def set_optimization(opt, steps_gui, cfg_gui, sampler_gui, clip_skip_gui, lora_g
 
 # [sampler_gui, steps_gui, cfg_gui, clip_skip_gui, img_width_gui, img_height_gui, optimization_gui]
 preset_sampler_setting = {
-    "None": ["Euler a", 28, 7., True, 1024, 1024, "None"],
+    "None": ["Euler", 28, 7., True, 1024, 1024, "None"],
     "Anime 3:4 Fast": ["LCM", 8, 2.5, True, 896, 1152, "DPO Turbo"],
-    "Anime 3:4 Standard": ["Euler a", 28, 7., True, 896, 1152, "None"],
-    "Anime 3:4 Heavy": ["Euler a", 40, 7., True, 896, 1152, "None"],
+    "Anime 3:4 Standard": ["Euler", 28, 7., True, 896, 1152, "None"],
+    "Anime 3:4 Heavy": ["Euler", 40, 7., True, 896, 1152, "None"],
     "Anime 1:1 Fast": ["LCM", 8, 2.5, True, 1024, 1024, "DPO Turbo"],
-    "Anime 1:1 Standard": ["Euler a", 28, 7., True, 1024, 1024, "None"],
-    "Anime 1:1 Heavy": ["Euler a", 40, 7., True, 1024, 1024, "None"],
+    "Anime 1:1 Standard": ["Euler", 28, 7., True, 1024, 1024, "None"],
+    "Anime 1:1 Heavy": ["Euler", 40, 7., True, 1024, 1024, "None"],
     "Photo 3:4 Fast": ["LCM", 8, 2.5, False, 896, 1152, "DPO Turbo"],
     "Photo 3:4 Standard": ["DPM++ 2M Karras", 28, 7., False, 896, 1152, "None"],
     "Photo 3:4 Heavy": ["DPM++ 2M Karras", 40, 7., False, 896, 1152, "None"],
@@ -1380,9 +1380,9 @@ preset_sampler_setting = {
 
 def set_sampler_settings(sampler_setting):
     if not sampler_setting in list(preset_sampler_setting.keys()) or sampler_setting == "None":
-        return gr.update(value="Euler a"), gr.update(value=28), gr.update(value=7.), gr.update(value=True),\
+        return gr.update(value="Euler"), gr.update(value=28), gr.update(value=7.), gr.update(value=True),\
               gr.update(value=1024), gr.update(value=1024), gr.update(value="None")
-    v = preset_sampler_setting.get(sampler_setting, ["Euler a", 28, 7., True, 1024, 1024])
+    v = preset_sampler_setting.get(sampler_setting, ["Euler", 28, 7., True, 1024, 1024])
     # sampler, steps, cfg, clip_skip, width, height, optimization
     return gr.update(value=v[0]), gr.update(value=v[1]), gr.update(value=v[2]), gr.update(value=v[3]),\
           gr.update(value=v[4]), gr.update(value=v[5]), gr.update(value=v[6])
@@ -1573,7 +1573,7 @@ EXAMPLES_GUI = [
         7.5,
         True,
         -1,
-        "Euler a",
+        "Euler",
         1152,
         896,
         "votepurchase/animagine-xl-3.1",
@@ -1586,7 +1586,7 @@ EXAMPLES_GUI = [
         5.,
         True,
         -1,
-        "Euler a",
+        "Euler",
         1024,
         1024,
         "votepurchase/ponyDiffusionV6XL",
@@ -1599,7 +1599,7 @@ EXAMPLES_GUI = [
         7.0,
         True,
         -1,
-        "Euler a",
+        "Euler",
         1024,
         1024,
         "Raelina/Rae-Diffusion-XL-V2",
@@ -1612,7 +1612,7 @@ EXAMPLES_GUI = [
         7.0,
         True,
         -1,
-        "Euler a",
+        "Euler",
         1024,
         1024,
         "Raelina/Raemu-XL-V4",
@@ -1625,7 +1625,7 @@ EXAMPLES_GUI = [
         7.,
         True,
         -1,
-        "Euler a",
+        "Euler",
         1024,
         1024,
         "cagliostrolab/animagine-xl-3.1",