diff --git a/CHANGELOG.md b/CHANGELOG.md
index 1931bd2b5..13b831797 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -2,6 +2,31 @@
 
 ## Update for 2024-12-18
 
+### Highlights
+
+*What's new?*
+
+While we have several new supported models, workflows and tools, this release is primarily about *quality-of-life improvements*:  
+- New memory management engine: list of changes that went into this one is too long for here,  
+  but main goal is enabling modern large models to run on standard consumer GPUs  
+  without performance hits typically associated with aggressive memory swapping and needs for constant manual tweaks  
+- New [documentation website](https://vladmandic.github.io/sdnext-docs/)  
+  with full search and tons of new documentation  
+- New settings panel with simplified and streamlined configuration  
+
+We've also added support for several new models (see [supported models](https://vladmandic.github.io/sdnext-docs/Model-Support/) for full list):  
+- [NVLabs Sana](https://huggingface.co/Efficient-Large-Model/Sana_1600M_1024px)  
+- [Lightricks LTX-Video](https://huggingface.co/Lightricks/LTX-Video)  
+
+And a lot of Control goodies and related goodies  
+- for SDXL there is new [ProMax](https://huggingface.co/xinsir/controlnet-union-sdxl-1.0), improved *Union* and *Tiling*  
+- for FLUX.1 there are [Flux Tools](https://blackforestlabs.ai/flux-1-tools/) as well as official *Canny* and *Depth* models and a cool [Redux](https://huggingface.co/black-forest-labs/FLUX.1-Redux-dev) model  
+- for SD 3.5 there are official *Canny*, *Blur* and *Depth* in addition to existing 3rd party models  
+
+Plus couple of new integrated workflows such as [FreeScale](https://github.com/ali-vilab/FreeScale) and [Style Aligned Image Generation](https://style-aligned-gen.github.io/)  
+
+[README](https://github.com/vladmandic/automatic/blob/master/README.md) | [CHANGELOG](https://github.com/vladmandic/automatic/blob/master/CHANGELOG.md) | [Docs](https://vladmandic.github.io/sdnext-docs/) | [WiKi](https://github.com/vladmandic/automatic/wiki) | [Discord](https://discord.com/invite/sd-next-federal-batch-inspectors-1101998836328697867)
+
 ### New models and integrations
 
 - [NVLabs Sana](https://huggingface.co/Efficient-Large-Model/Sana_1600M_1024px)
@@ -13,6 +38,13 @@
   *reference values*: sampler: default (or any flow-match variant), width/height: 1024, guidance scale: 4.5  
   *note* like other LLM-based text-encoders, sana prefers long and descriptive prompts  
   any short prompt below 300 characters will be auto-expanded using built in Gemma LLM before encoding while long prompts will be passed as-is  
+- **ControlNet**
+  - improved support for **Union** controlnets with granular control mode type
+  - added support for latest [Xinsir ProMax](https://huggingface.co/xinsir/controlnet-union-sdxl-1.0) all-in-one controlnet  
+  - added support for multiple **Tiling** controlnets, for example [Xinsir Tile](https://huggingface.co/xinsir/controlnet-tile-sdxl-1.0)  
+    *note*: when selecting tiles in control settings, you can also specify non-square ratios  
+    in which case it will use context-aware image resize to maintain overall composition  
+    *note*: available tiling options can be set in settings -> control  
 - [Flux Tools](https://blackforestlabs.ai/flux-1-tools/)  
   **Redux** is actually a tool, **Fill** is inpaint/outpaint optimized version of *Flux-dev*  
   **Canny** & **Depth** are optimized versions of *Flux-dev* for their respective tasks: they are *not* ControlNets that work on top of a model  
@@ -36,6 +68,11 @@
   both **Depth** and **Canny** LoRAs are available in standard control menus  
 - [StabilityAI SD35 ControlNets](https://huggingface.co/stabilityai/stable-diffusion-3.5-controlnets)
   - In addition to previously released `InstantX` and `Alimama`, we now have *official* ones from StabilityAI  
+- [Lightricks LTX-Video](https://huggingface.co/Lightricks/LTX-Video)
+  basic support for LTX-Video for text-to-video and image-to-video  
+  to use, select in *scripts -> ltx-video*  
+  *note* you may need to enable sequential offload for maximum gpu memory savings  
+  *note* ltx-video requires very long and descriptive prompt, see original link for examples  
 - [Style Aligned Image Generation](https://style-aligned-gen.github.io/)  
   enable in scripts, compatible with sd-xl  
   enter multiple prompts in prompt field separated by new line  
@@ -47,13 +84,6 @@
   run iterative generation of images at different scales to achieve better results  
   can render 4k sdxl images  
   *note*: disable live preview to avoid memory issues when generating large images  
-- **ControlNet**
-  - improved support for **Union** controlnets with granular control mode type
-  - added support for latest [Xinsir ProMax](https://huggingface.co/xinsir/controlnet-union-sdxl-1.0) all-in-one controlnet  
-  - added support for multiple **Tiling** controlnets, for example [Xinsir Tile](https://huggingface.co/xinsir/controlnet-tile-sdxl-1.0)  
-    *note*: when selecting tiles in control settings, you can also specify non-square ratios  
-    in which case it will use context-aware image resize to maintain overall composition  
-    *note*: available tiling options can be set in settings -> control  
 
 ### UI and workflow improvements
 
diff --git a/modules/processing_diffusers.py b/modules/processing_diffusers.py
index 581589262..d43660ca8 100644
--- a/modules/processing_diffusers.py
+++ b/modules/processing_diffusers.py
@@ -355,6 +355,8 @@ def process_decode(p: processing.StableDiffusionProcessing, output):
         if not hasattr(output, 'images') and hasattr(output, 'frames'):
             shared.log.debug(f'Generated: frames={len(output.frames[0])}')
             output.images = output.frames[0]
+        if output.images is not None and len(output.images) > 0 and isinstance(output.images[0], Image.Image):
+            return output.images
         model = shared.sd_model if not is_refiner_enabled(p) else shared.sd_refiner
         if not hasattr(model, 'vae'):
             if hasattr(model, 'pipe') and hasattr(model.pipe, 'vae'):
diff --git a/scripts/ltxvideo.py b/scripts/ltxvideo.py
new file mode 100644
index 000000000..54e2685a8
--- /dev/null
+++ b/scripts/ltxvideo.py
@@ -0,0 +1,130 @@
+import time
+import torch
+import gradio as gr
+import diffusers
+from modules import scripts, processing, shared, images, devices, sd_models, sd_checkpoint
+
+
+repo_id = 'a-r-r-o-w/LTX-Video-diffusers'
+presets = [
+    {"label": "custom", "width": 0, "height": 0, "num_frames": 0},
+    {"label": "1216x704, 41 frames", "width": 1216, "height": 704, "num_frames": 41},
+    {"label": "1088x704, 49 frames", "width": 1088, "height": 704, "num_frames": 49},
+    {"label": "1056x640, 57 frames", "width": 1056, "height": 640, "num_frames": 57},
+    {"label": "992x608, 65 frames", "width": 992, "height": 608, "num_frames": 65},
+    {"label": "896x608, 73 frames", "width": 896, "height": 608, "num_frames": 73},
+    {"label": "896x544, 81 frames", "width": 896, "height": 544, "num_frames": 81},
+    {"label": "832x544, 89 frames", "width": 832, "height": 544, "num_frames": 89},
+    {"label": "800x512, 97 frames", "width": 800, "height": 512, "num_frames": 97},
+    {"label": "768x512, 97 frames", "width": 768, "height": 512, "num_frames": 97},
+    {"label": "800x480, 105 frames", "width": 800, "height": 480, "num_frames": 105},
+    {"label": "736x480, 113 frames", "width": 736, "height": 480, "num_frames": 113},
+    {"label": "704x480, 121 frames", "width": 704, "height": 480, "num_frames": 121},
+    {"label": "704x448, 129 frames", "width": 704, "height": 448, "num_frames": 129},
+    {"label": "672x448, 137 frames", "width": 672, "height": 448, "num_frames": 137},
+    {"label": "640x416, 153 frames", "width": 640, "height": 416, "num_frames": 153},
+    {"label": "672x384, 161 frames", "width": 672, "height": 384, "num_frames": 161},
+    {"label": "640x384, 169 frames", "width": 640, "height": 384, "num_frames": 169},
+    {"label": "608x384, 177 frames", "width": 608, "height": 384, "num_frames": 177},
+    {"label": "576x384, 185 frames", "width": 576, "height": 384, "num_frames": 185},
+    {"label": "608x352, 193 frames", "width": 608, "height": 352, "num_frames": 193},
+    {"label": "576x352, 201 frames", "width": 576, "height": 352, "num_frames": 201},
+    {"label": "544x352, 209 frames", "width": 544, "height": 352, "num_frames": 209},
+    {"label": "512x352, 225 frames", "width": 512, "height": 352, "num_frames": 225},
+    {"label": "512x352, 233 frames", "width": 512, "height": 352, "num_frames": 233},
+    {"label": "544x320, 241 frames", "width": 544, "height": 320, "num_frames": 241},
+    {"label": "512x320, 249 frames", "width": 512, "height": 320, "num_frames": 249},
+    {"label": "512x320, 257 frames", "width": 512, "height": 320, "num_frames": 257},
+]
+
+
+class Script(scripts.Script):
+    def title(self):
+        return 'Video: LTX Video'
+
+    def show(self, is_img2img):
+        return shared.native
+
+    # return signature is array of gradio components
+    def ui(self, _is_img2img):
+        def video_type_change(video_type):
+            return [
+                gr.update(visible=video_type != 'None'),
+                gr.update(visible=video_type == 'GIF' or video_type == 'PNG'),
+                gr.update(visible=video_type == 'MP4'),
+                gr.update(visible=video_type == 'MP4'),
+            ]
+        def preset_change(preset):
+            return gr.update(visible=preset == 'custom')
+
+        with gr.Row():
+            gr.HTML('<a href="https://www.ltxvideo.org/">&nbsp LTX Video</a><br>')
+        with gr.Row():
+            preset_name = gr.Dropdown(label='Preset', choices=[p['label'] for p in presets], value='custom')
+            num_frames = gr.Slider(label='Frames', minimum=9, maximum=257, step=1, value=9)
+        with gr.Row():
+            video_type = gr.Dropdown(label='Video file', choices=['None', 'GIF', 'PNG', 'MP4'], value='None')
+            duration = gr.Slider(label='Duration', minimum=0.25, maximum=10, step=0.25, value=2, visible=False)
+        with gr.Row():
+            gif_loop = gr.Checkbox(label='Loop', value=True, visible=False)
+            mp4_pad = gr.Slider(label='Pad frames', minimum=0, maximum=24, step=1, value=1, visible=False)
+            mp4_interpolate = gr.Slider(label='Interpolate frames', minimum=0, maximum=24, step=1, value=0, visible=False)
+        preset_name.change(fn=preset_change, inputs=[preset_name], outputs=num_frames)
+        video_type.change(fn=video_type_change, inputs=[video_type], outputs=[duration, gif_loop, mp4_pad, mp4_interpolate])
+        return [preset_name, num_frames, video_type, duration, gif_loop, mp4_pad, mp4_interpolate]
+
+    def run(self, p: processing.StableDiffusionProcessing, preset_name, num_frames, video_type, duration, gif_loop, mp4_pad, mp4_interpolate): # pylint: disable=arguments-differ, unused-argument
+        # set params
+        preset = [p for p in presets if p['label'] == preset_name][0]
+        image = getattr(p, 'init_images', None)
+        image = None if image is None or len(image) == 0 else image[0]
+        if p.width == 0 or p.height == 0 and image is not None:
+            p.width = image.width
+            p.height = image.height
+        if preset['label'] != 'custom':
+            num_frames = preset['num_frames']
+            p.width = preset['width']
+            p.height = preset['height']
+        else:
+            num_frames = 8 * int(num_frames // 8) + 1
+            p.width = 32 * int(p.width // 32)
+            p.height = 32 * int(p.height // 32)
+        if image:
+            image = images.resize_image(resize_mode=2, im=image, width=p.width, height=p.height, upscaler_name=None, output_type='pil')
+            p.task_args['image'] = image
+        p.task_args['output_type'] = 'pil'
+        p.task_args['generator'] = torch.manual_seed(p.seed)
+        p.task_args['num_frames'] = num_frames
+        p.sampler_name = 'Default'
+        p.do_not_save_grid = True
+        p.ops.append('ltx')
+
+        # load model
+        cls = diffusers.LTXPipeline if image is None else diffusers.LTXImageToVideoPipeline
+        diffusers.LTXTransformer3DModel = diffusers.LTXVideoTransformer3DModel
+        diffusers.AutoencoderKLLTX = diffusers.AutoencoderKLLTXVideo
+        if shared.sd_model.__class__ != cls:
+            sd_models.unload_model_weights()
+            shared.sd_model = cls.from_pretrained(
+                repo_id,
+                cache_dir = shared.opts.hfcache_dir,
+                torch_dtype=devices.dtype,
+            )
+            sd_models.set_diffuser_options(shared.sd_model)
+            shared.sd_model.sd_checkpoint_info = sd_checkpoint.CheckpointInfo(repo_id)
+            shared.sd_model.sd_model_hash = None
+        shared.sd_model = sd_models.apply_balanced_offload(shared.sd_model)
+        shared.sd_model.vae.enable_slicing()
+        shared.sd_model.vae.enable_tiling()
+        devices.torch_gc(force=True)
+        shared.log.debug(f'LTX: cls={shared.sd_model.__class__.__name__} preset={preset_name} args={p.task_args}')
+
+        # run processing
+        t0 = time.time()
+        processed = processing.process_images(p)
+        t1 = time.time()
+        if processed is not None and len(processed.images) > 0:
+            shared.log.info(f'LTX: frames={len(processed.images)} time={t1-t0:.2f}')
+            if video_type != 'None':
+                images.save_video(p, filename=None, images=processed.images, video_type=video_type, duration=duration, loop=gif_loop, pad=mp4_pad, interpolate=mp4_interpolate)
+        return processed
diff --git a/wiki b/wiki
index 470e75f0c..34ba1df45 160000
--- a/wiki
+++ b/wiki
@@ -1 +1 @@
-Subproject commit 470e75f0c70a22ed3d65187c70f04c131400b35d
+Subproject commit 34ba1df45d17da4ee09a2e5278e384bc1929dd8b