DeepSeek-R1-GGUF
unsloth · Kit
GGUF copies of the 671B DeepSeek-R1 reasoning model, with 1.58-bit and 2-bit dynamic quants, for running it in llama.cpp on a local machine with enough memory.
Smooths stop-motion footage and the gaps between generated images, using the RIFE and Adetailer models. For animators and image-generation users who want steadier motion between frames.
Smooth Gen is a kit in the Productivity category, listed by Mindket. It is free. This is version 1, last updated on . Download it on this page, a zip of its files. Nothing in it runs by itself.
pip install -U huggingface_hub hf download alrobles/smooth_gen --repo-type space --local-dir smooth_gen cd smooth_gen
Smooth Gen evens out stop-motion animation and the jumps between generated images. It is a small Gradio app that names two models, RIFE and Adetailer, in its setup. The README is a single line, so the exact controls are not described there.
It suits animators and AI-image users whose sequences look jumpy from one frame to the next. It also suits developers who want a compact example of a Gradio app that runs on a GPU Space.
| Industry | Who uses it | How they use it | Example |
|---|---|---|---|
| Animation | Stop-motion artists | Soften the jumps between photographed frames | Load a short clip and compare it with the original |
| Creative AI | Image-generation users | Link generated images into a steadier sequence | Smooth a run of images that share one subject |
| Social media | Short-video makers | Make quick clips look less choppy | Prepare a loop for posting |
| Software | Gradio developers | Read a compact app built on two named models | Copy the folder and run it locally |
Anyone who wants to generate new images from a prompt can skip it, since this app works on frames you already have.
The app runs in two places.
| Use case | Who | What they get back |
|---|---|---|
| Stop-motion smoothing | Animators | A steadier sequence from choppy frames |
| Generation gaps | Image-generation users | A smoother link between generated images |
| App study | Developers | A short repository with the app file and its packages |
The online page needs nothing installed. A local copy needs the following.
pip install -U huggingface_hub hf download alrobles/smooth_gen --repo-type space --local-dir smooth_gen cd smooth_gen pip install gradio==6.31.0 pip install -r requirements.txt python app.py
Open the page in a browser, load the frames or images you want smoothed, and run it. On a local copy, this command starts the page.
python app.py
| Tool | What it does |
|---|---|
| RIFE | A model the Space names, used to fill the gaps between frames |
| Adetailer | A second model the Space names, used to refine the images |
| app.py | Holds the Gradio page |
| requirements.txt | Lists the Python packages the app needs |
You have a stop-motion clip with visible jumps between frames. You load it into the page and run it, and you get back a smoother sequence to compare with the original.
If you are new to this, start with a short clip of only a few frames. Run it once and watch the motion, then judge whether the gaps look softer.
If you know the field, the Space names two models, r3gm/RIFE and Bingsu/adetailer, and runs on a ZeroGPU Space with A10G hardware. The repository has only the app file, the requirements and the README, so the pipeline order and settings are best read from app.py itself.
The Space page gives one line of description and no usage guide. Read app.py to see what each control does.
Smooths stop-motion footage and the gaps between generated images, using the RIFE and Adetailer models. For animators and image-generation users who want steadier motion between frames.
Made by alrobles on Hugging Face. These notes are Mindket's, written from its Space page and README; the app's own files and license are on Hugging Face.
What it is: Smooth Gen evens out stop-motion animation and the jumps between generated images. It is a small Gradio app that names two models, RIFE and Adetailer, in its setup. The README is a single line, so the exact controls are not described there.
Who it suits: It suits animators and AI-image users whose sequences look jumpy from one frame to the next. It also suits developers who want a compact example of a Gradio app that runs on a GPU Space.
Industry | Who uses it | How they use it | Example
Animation | Stop-motion artists | Soften the jumps between photographed frames | Load a short clip and compare it with the original
Creative AI | Image-generation users | Link generated images into a steadier sequence | Smooth a run of images that share one subject
Social media | Short-video makers | Make quick clips look less choppy | Prepare a loop for posting
Software | Gradio developers | Read a compact app built on two named models | Copy the folder and run it locally
Anyone who wants to generate new images from a prompt can skip it, since this app works on frames you already have.
Where to use it: The app runs in two places.
Use case | Who | What they get back
Stop-motion smoothing | Animators | A steadier sequence from choppy frames
Generation gaps | Image-generation users | A smoother link between generated images
App study | Developers | A short repository with the app file and its packages
How to set it up: The online page needs nothing installed. A local copy needs the following.
pip install -U huggingface_hub
hf download alrobles/smooth_gen --repo-type space --local-dir smooth_gen
cd smooth_gen
pip install gradio==6.31.0
pip install -r requirements.txt
python app.py
How to use it: Open the page in a browser, load the frames or images you want smoothed, and run it. On a local copy, this command starts the page.
python app.py
Tool | What it does
RIFE | A model the Space names, used to fill the gaps between frames
Adetailer | A second model the Space names, used to refine the images
app.py | Holds the Gradio page
requirements.txt | Lists the Python packages the app needs
Example: You have a stop-motion clip with visible jumps between frames. You load it into the page and run it, and you get back a smoother sequence to compare with the original.
For newcomers and experts: If you are new to this, start with a short clip of only a few frames. Run it once and watch the motion, then judge whether the gaps look softer.
If you know the field, the Space names two models, r3gm/RIFE and Bingsu/adetailer, and runs on a ZeroGPU Space with A10G hardware. The repository has only the app file, the requirements and the README, so the pipeline order and settings are best read from app.py itself.
Load frames or images
RIFE fills the gaps between them
Adetailer refines the images
A smoother sequence comes back
Good to know: The Space page gives one line of description and no usage guide. Read app.py to see what each control does.
Open the Space in your browser, or copy it to your own Hugging Face account from its page. Nothing in this kit runs by itself.
README.md 4 KB
Listed Hugging Face Spaces in the same category that share the most tags with this one.
| Product | Likes | Built with | License | Last change |
|---|---|---|---|---|
| Smooth Gen This page | 1 | gradio | mit | |
| MusicGenShares gradio | 5,116 | gradio | cc-by-nc-4.0 | |
| Kokoro TTSShares gradio | 3,556 | gradio | apache-2.0 | |
| Background RemovalShares gradio | 2,988 | gradio | mit | |
| Omni Image EditorShares gradio | 2,922 | gradio | mit | |
| Diffusers Image OutpaintShares gradio | 2,565 | gradio | apache-2.0 |
unsloth · Kit
GGUF copies of the 671B DeepSeek-R1 reasoning model, with 1.58-bit and 2-bit dynamic quants, for running it in llama.cpp on a local machine with enough memory.
prithivMLmods · Kit
Provides GGUF files of Axion-1.0-35B, a 35B mixture-of-experts model with about 3B active parameters aimed at scientific reasoning, information seeking and too…
Phips · Kit
Upscales low-resolution images with a super-resolution network that trains on one consumer GPU and exports to ONNX. For people who train or run image upscalers.
ACE-Step · Kit
Generates music from text with a 4B diffusion decoder, 50 steps and guidance control, aiming for higher audio quality than the base. For creators with a GPU of…
op7418 · Skill
Skill that makes single-file HTML slide decks, slide illustrations and platform covers in two visual styles, with a presenter mode for rehearsal. For speakers…
zarazhangrui · Skill
Builds HTML presentations from scratch or from a PowerPoint file and shows visual style previews to pick from, for people who want web slides with no CSS or Ja…