diff --git a/.gitignore b/.gitignore
index 9bc6d5a24..3bb999538 100644
--- a/.gitignore
+++ b/.gitignore
@@ -41,6 +41,7 @@ tunableop_results*.csv
 /*.txt
 /*.mp3
 /*.lnk
+/*.swp
 !webui.bat
 !webui.sh
 !package.json
diff --git a/CHANGELOG.md b/CHANGELOG.md
index c60c6f3da..ae551af28 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -21,6 +21,7 @@
   - fix `wan-2.2-a14b` stage selection  
   - fix `wan-2.2-5b` vae decode  
   - disabling live preview should not disable progress updates  
+  - video tab create `params.txt` with metadata  
 
 ## Update for 2025-10-18
 
diff --git a/modules/framepack/framepack_worker.py b/modules/framepack/framepack_worker.py
index cda5677f8..6558c0765 100644
--- a/modules/framepack/framepack_worker.py
+++ b/modules/framepack/framepack_worker.py
@@ -308,12 +308,26 @@ def worker(
                 if is_last_section:
                     break
 
-            total_generated_frames, _video_filename = save_video(history_pixels, mp4_fps, mp4_codec, mp4_opt, mp4_ext, mp4_sf, mp4_video, mp4_frames, mp4_interpolate, pbar=pbar, stream=stream, metadata=metadata)
+            total_generated_frames, _video_filename = save_video(
+                None,
+                history_pixels,
+                mp4_fps,
+                mp4_codec,
+                mp4_opt,
+                mp4_ext,
+                mp4_sf,
+                mp4_video,
+                mp4_frames,
+                mp4_interpolate,
+                pbar=pbar,
+                stream=stream,
+                metadata=metadata,
+            )
 
     except AssertionError:
         shared.log.info('FramePack: interrupted')
         if shared.opts.keep_incomplete:
-            save_video(history_pixels, mp4_fps, mp4_codec, mp4_opt, mp4_ext, mp4_sf, mp4_video, mp4_frames, mp4_interpolate=0, stream=stream, metadata=metadata)
+            save_video(None, history_pixels, mp4_fps, mp4_codec, mp4_opt, mp4_ext, mp4_sf, mp4_video, mp4_frames, mp4_interpolate=0, stream=stream, metadata=metadata)
     except Exception as e:
         shared.log.error(f'FramePack: {e}')
         errors.display(e, 'FramePack')
diff --git a/modules/generation_parameters_copypaste.py b/modules/generation_parameters_copypaste.py
index 1427e53cc..df0ea1643 100644
--- a/modules/generation_parameters_copypaste.py
+++ b/modules/generation_parameters_copypaste.py
@@ -3,7 +3,6 @@ import io
 import os
 from PIL import Image
 import gradio as gr
-from modules.paths import params_path
 from modules import shared, gr_tempdir, script_callbacks, images
 from modules.infotext import parse, mapping, quote, unquote # pylint: disable=unused-import
 
@@ -204,6 +203,7 @@ def create_override_settings_dict(text_pairs):
 def connect_paste(button, local_paste_fields, input_comp, override_settings_component, tabname):
 
     def paste_func(prompt):
+        from modules.paths import params_path
         if prompt is None or len(prompt.strip()) == 0:
             if os.path.exists(params_path):
                 with open(params_path, "r", encoding="utf8") as file:
diff --git a/modules/images_namegen.py b/modules/images_namegen.py
index 849450d5b..f81a6447d 100644
--- a/modules/images_namegen.py
+++ b/modules/images_namegen.py
@@ -23,8 +23,8 @@ NOTHING = object()
 
 class FilenameGenerator:
     replacements = {
-        'width': lambda self: self.image.width,
-        'height': lambda self: self.image.height,
+        'width': lambda self: self.width,
+        'height': lambda self: self.height,
         'batch_number': lambda self: self.batch_number,
         'iter_number': lambda self: self.iter_number,
         'num': lambda self: NOTHING if self.p.n_iter == 1 and self.p.batch_size == 1 else self.p.iteration * self.p.batch_size + self.p.batch_index + 1,
@@ -32,8 +32,8 @@ class FilenameGenerator:
         'date': lambda self: datetime.datetime.now().strftime('%Y-%m-%d'),
         'datetime': lambda self, *args: self.datetime(*args),  # accepts formats: [datetime], [datetime<Format>], [datetime<Format><Time Zone>]
         'hasprompt': lambda self, *args: self.hasprompt(*args),  # accepts formats:[hasprompt<prompt1|default><prompt2>..]
-        'hash': lambda self: self.image_hash(),
-        'image_hash': lambda self: self.image_hash(),
+        'hash': lambda self: self.image_hash() if self.image is not None else '',
+        'image_hash': lambda self: self.image_hash() if self.image is not None else '',
         'timestamp': lambda self: getattr(self.p, "job_timestamp", shared.state.job_timestamp),
         'epoch': lambda self: int(time.time()),
         'job_timestamp': lambda self: getattr(self.p, "job_timestamp", shared.state.job_timestamp),
@@ -61,7 +61,7 @@ class FilenameGenerator:
     }
     default_time_format = '%Y%m%d%H%M%S'
 
-    def __init__(self, p, seed, prompt, image, grid=False):
+    def __init__(self, p, seed, prompt, image=None, grid=False, width=None, height=None):
         if p is None:
             debug('Filename generator init skip')
         else:
@@ -82,6 +82,8 @@ class FilenameGenerator:
         if isinstance(self.prompt, list):
             self.prompt = ' '.join(self.prompt)
         self.image = image
+        self.width = width if width is not None else (image.width if image is not None else (p.width if p is not None else 0))
+        self.height = height if height is not None else (image.height if image is not None else (p.height if p is not None else 0))
         if not grid:
             self.batch_number = NOTHING if self.p is None or getattr(self.p, 'batch_size', 1) == 1 else (self.p.batch_index + 1 if hasattr(self.p, 'batch_index') else NOTHING)
             self.iter_number = NOTHING if self.p is None or getattr(self.p, 'n_iter', 1) == 1 else (self.p.iteration + 1 if hasattr(self.p, 'iteration') else NOTHING)
diff --git a/modules/ltx/ltx_process.py b/modules/ltx/ltx_process.py
index b45298854..8b429a593 100644
--- a/modules/ltx/ltx_process.py
+++ b/modules/ltx/ltx_process.py
@@ -89,6 +89,8 @@ def run_ltx(task_id,
         shared.state.job_count = 1
 
         p = processing.StableDiffusionProcessingVideo(
+            video_engine=engine,
+            video_model=model,
             prompt=prompt,
             negative_prompt=negative,
             styles=styles,
@@ -247,6 +249,7 @@ def run_ltx(task_id,
         timer.process.add('offload', t11 - t10)
 
         num_frames, video_file = save_video(
+            p=p,
             pixels=frames,
             mp4_fps=mp4_fps,
             mp4_codec=mp4_codec,
diff --git a/modules/processing_class.py b/modules/processing_class.py
index 8ac7286fc..29990e4b4 100644
--- a/modules/processing_class.py
+++ b/modules/processing_class.py
@@ -428,9 +428,11 @@ class StableDiffusionProcessing:
 class StableDiffusionProcessingVideo(StableDiffusionProcessing):
     def __init__(self, **kwargs):
         self.prompt_template: str = None
-        self.frames: int = 1
+        self.frames: int = kwargs.pop('frames', 1)
+        self.vae_tile_frames: int = kwargs.pop('vae_tile_frames', 0)
+        self.video_engine: str = kwargs.pop('video_engine', None)
+        self.video_model: str = kwargs.pop('video_model', None)
         self.scheduler_shift: float = 0.0
-        self.vae_tile_frames: int = 0
         debug(f'Process init: mode={self.__class__.__name__} kwargs={kwargs}') # pylint: disable=protected-access
         super().__init__(**kwargs)
 
diff --git a/modules/ui_video.py b/modules/ui_video.py
index dfe6c2018..77fda42c7 100644
--- a/modules/ui_video.py
+++ b/modules/ui_video.py
@@ -38,7 +38,7 @@ def create_ui():
                     mp4_fps, mp4_interpolate, mp4_codec, mp4_ext, mp4_opt, mp4_video, mp4_frames, mp4_sf = video_ui.create_ui_outputs()
                 with gr.Tab('Models', id='video-core-tab') as video_core_tab:
                     from modules.video_models import video_ui
-                    video_ui.create_ui(prompt, negative, styles, overrides, init_image, init_strength, last_image, mp4_fps, mp4_interpolate, mp4_codec, mp4_ext, mp4_opt, mp4_video, mp4_frames, mp4_sf, width, height, frames, seed, reuse_seed)
+                    engine, model, steps, sampler_index = video_ui.create_ui(prompt, negative, styles, overrides, init_image, init_strength, last_image, mp4_fps, mp4_interpolate, mp4_codec, mp4_ext, mp4_opt, mp4_video, mp4_frames, mp4_sf, width, height, frames, seed, reuse_seed)
                 with gr.Tab('FramePack', id='framepack-tab') as framepack_tab:
                     from modules.framepack import framepack_ui
                     framepack_ui.create_ui(prompt, negative, styles, overrides, init_image, last_image, mp4_fps, mp4_interpolate, mp4_codec, mp4_ext, mp4_opt, mp4_video, mp4_frames, mp4_sf)
@@ -48,8 +48,18 @@ def create_ui():
 
         paste_fields = [
             (prompt, "Prompt"), # cannot add more fields as they are not defined yet
+            (negative, "Negative prompt"),
+            (width, "Width"),
+            (height, "Height"),
+            (frames, "Frames"),
+            (seed, "Seed"),
+            (styles, "Styles"),
+            (steps, "Steps"),
+            (sampler_index, "Sampler"),
+            (engine, "Engine"),
+            (model, "Model"),
         ]
-        generation_parameters_copypaste.add_paste_fields("video", None, paste_fields, overrides)
+        generation_parameters_copypaste.add_paste_fields("video", None, paste_fields)
         bindings = generation_parameters_copypaste.ParamBinding(paste_button=paste, tabname="video", source_text_component=prompt, source_image_component=None)
         generation_parameters_copypaste.register_paste_params_button(bindings)
 
diff --git a/modules/video_models/video_run.py b/modules/video_models/video_run.py
index 2a2f1ab39..5ef65e3b0 100644
--- a/modules/video_models/video_run.py
+++ b/modules/video_models/video_run.py
@@ -28,6 +28,8 @@ def generate(*args, **kwargs):
 
     p = processing.StableDiffusionProcessingVideo(
         sd_model=shared.sd_model,
+        video_engine=engine,
+        video_model=model,
         prompt=prompt,
         negative_prompt=negative,
         styles=styles,
@@ -138,6 +140,7 @@ def generate(*args, **kwargs):
     # video_file = images.save_video(p, filename=None, images=processed.images, video_type=video_type, duration=video_duration, loop=video_loop, pad=video_pad, interpolate=video_interpolate) # legacy video save from list of images
     pixels = video_save.images_to_tensor(processed.images)
     _num_frames, video_file = video_save.save_video(
+        p=p,
         pixels=pixels,
         mp4_fps=mp4_fps,
         mp4_codec=mp4_codec,
diff --git a/modules/video_models/video_save.py b/modules/video_models/video_save.py
index 24775c5a1..9453dc96f 100644
--- a/modules/video_models/video_save.py
+++ b/modules/video_models/video_save.py
@@ -1,18 +1,52 @@
 import os
 import time
-import datetime
 import cv2
 import numpy as np
 import torch
 import einops
-from modules import shared, errors ,timer, rife
+from modules import shared, errors ,timer, rife, processing
 from modules.video_models.video_utils import check_av
 
 
-def get_video_filename(frames:int, codec:str):
-    timestamp = datetime.datetime.now().strftime('%Y%m%d-%H%M%S')
-    output_filename = os.path.join(shared.opts.outdir_video, f'{timestamp}-{codec}-f{frames}')
-    return output_filename
+def get_video_filename(p:processing.StableDiffusionProcessingVideo):
+    from modules.images_namegen import FilenameGenerator
+    namegen = FilenameGenerator(p, seed=p.seed if p is not None else 0, prompt=p.prompt if p is not None else '')
+    filename = namegen.apply(shared.opts.samples_filename_pattern if shared.opts.samples_filename_pattern and len(shared.opts.samples_filename_pattern) > 0 else "[seq]-[prompt_words]")
+    if shared.opts.save_to_dirs:
+        dirname = namegen.apply(shared.opts.directories_filename_pattern or "[prompt_words]")
+        dirname = os.path.join(shared.opts.outdir_video, dirname, filename)
+    else:
+        dirname = shared.opts.outdir_video
+    if not os.path.exists(dirname):
+        os.makedirs(dirname, exist_ok=True)
+    filename = os.path.join(dirname, filename)
+    filename = namegen.sequence(filename)
+    filename = namegen.sanitize(filename)
+    return filename
+
+
+def save_params(p, filename: str = None):
+    from modules.paths import params_path
+    if p is None:
+        dct = {}
+    else:
+        # sampler_index, sampler_shift, dynamic_shift, guidance_scale, guidance_true, init_image, init_strength, last_image, vae_type, vae_tile_frames, mp4_fps, mp4_interpolate, mp4_codec, mp4_ext, mp4_opt, mp4_video, mp4_frames, mp4_sf, vlm_enhance, vlm_model, vlm_system_prompt, override_settings = args
+        dct = {
+            "Prompt": p.prompt,
+            "Negative prompt": p.negative_prompt,
+            "Steps": p.steps,
+            "Sampler": p.sampler_name,
+            "Seed": p.seed,
+            "Engine": p.video_engine,
+            "Model": p.video_model,
+            "Frames": p.frames,
+            "Size": f"{p.width}x{p.height}",
+            "Styles": ','.join(p.styles) if isinstance(p.styles, list) else p.styles,
+        }
+    params = ', '.join([f'{k}: {v}' for k, v in dct.items() if v is not None and v != ''])
+    fn = filename if filename is not None else params_path
+    with open(fn, "w", encoding="utf8") as file:
+        file.write(params)
 
 
 def images_to_tensor(images):
@@ -71,6 +105,7 @@ def atomic_save_video(filename, tensor:torch.Tensor, fps:float=24, codec:str='li
 
 
 def save_video(
+        p:processing.StableDiffusionProcessingVideo,
         pixels:torch.Tensor,
         mp4_fps:int=24,
         mp4_codec:str='libx264',
@@ -111,7 +146,10 @@ def save_video(
         x = einops.rearrange(x, '(m n) c t h w -> t (m h) (n w) c', n=n)
         x = x.contiguous()
 
-        output_filename = get_video_filename(t, mp4_codec)
+        output_filename = get_video_filename(p)
+        if shared.opts.save_txt:
+            save_params(p, f'{output_filename}.txt')
+        save_params(p)
 
         if mp4_sf:
             fn = f'{output_filename}.safetensors'
diff --git a/modules/video_models/video_ui.py b/modules/video_models/video_ui.py
index 5215055d7..1dee95e60 100644
--- a/modules/video_models/video_ui.py
+++ b/modules/video_models/video_ui.py
@@ -127,7 +127,7 @@ def create_ui(prompt, negative, styles, overrides, init_image, init_strength, la
                 generate = gr.Button('Generate', elem_id="video_generate_btn", variant='primary', visible=False)
             with gr.Row():
                 engine = gr.Dropdown(label='Engine', choices=list(models_def.models), value='None', elem_id="video_engine")
-                model = gr.Dropdown(label='Model', choices=[''], value=None, elem_id="video_model")
+                model = gr.Dropdown(label='Model', choices=[''], value='None', elem_id="video_model")
                 btn_load = ToolButton(ui_symbols.loading, elem_id="video_model_load")
             with gr.Row():
                 url = gr.HTML(label='Model URL', elem_id='video_model_url', value='<br><br>')
@@ -197,3 +197,4 @@ def create_ui(prompt, negative, styles, overrides, init_image, init_strength, la
         show_progress=False,
     )
     generate.click(**video_dict)
+    return [engine, model, steps, sampler_index]