# AI Video Generation

Generate videos using Stable Video Diffusion, AnimateDiff, and other models.

{% hint style="success" %}
All examples can be run on GPU servers rented through [CLORE.AI Marketplace](https://clore.ai/marketplace).
{% endhint %}

## Renting on CLORE.AI

1. Visit [CLORE.AI Marketplace](https://clore.ai/marketplace)
2. Filter by GPU type, VRAM, and price
3. Choose **On-Demand** (fixed rate) or **Spot** (bid price)
4. Configure your order:
   * Select Docker image
   * Set ports (TCP for SSH, HTTP for web UIs)
   * Add environment variables if needed
   * Enter startup command
5. Select payment: **CLORE**, **BTC**, or **USDT/USDC**
6. Create order and wait for deployment

### Access Your Server

* Find connection details in **My Orders**
* Web interfaces: Use the HTTP port URL
* SSH: `ssh -p <port> root@<proxy-address>`

## Available Models

| Model       | Type           | VRAM | Duration    |
| ----------- | -------------- | ---- | ----------- |
| SVD         | Image-to-Video | 16GB | 4 seconds   |
| SVD-XT      | Image-to-Video | 20GB | 4 seconds   |
| AnimateDiff | Text-to-Video  | 12GB | 2-4 seconds |
| CogVideoX   | Text-to-Video  | 24GB | 6 seconds   |

## Stable Video Diffusion (SVD)

### Quick Deploy

**Docker Image:**

```
pytorch/pytorch:2.5.1-cuda12.4-cudnn9-devel
```

**Ports:**

```
22/tcp
7860/http
```

**Command:**

```bash
pip install diffusers transformers accelerate gradio imageio && \
python svd_server.py
```

## Accessing Your Service

After deployment, find your `http_pub` URL in **My Orders**:

1. Go to **My Orders** page
2. Click on your order
3. Find the `http_pub` URL (e.g., `abc123.clorecloud.net`)

Use `https://YOUR_HTTP_PUB_URL` instead of `localhost` in examples below.

### SVD Script

```python
import torch
from diffusers import StableVideoDiffusionPipeline
from PIL import Image
import imageio

# Load model
pipe = StableVideoDiffusionPipeline.from_pretrained(
    "stabilityai/stable-video-diffusion-img2vid-xt",
    torch_dtype=torch.float16,
)
pipe.to("cuda")
pipe.enable_model_cpu_offload()

# Load and resize image
image = Image.open("input.png").resize((1024, 576))

# Generate video
frames = pipe(
    image,
    decode_chunk_size=8,
    num_frames=25,
    motion_bucket_id=127,
    noise_aug_strength=0.02
).frames[0]

# Save as GIF
imageio.mimsave("output.gif", frames, fps=6)

# Save as MP4
imageio.mimsave("output.mp4", frames, fps=6)
```

### SVD with Gradio UI

```python
import gradio as gr
import torch
from diffusers import StableVideoDiffusionPipeline
from PIL import Image
import imageio
import tempfile

pipe = StableVideoDiffusionPipeline.from_pretrained(
    "stabilityai/stable-video-diffusion-img2vid-xt",
    torch_dtype=torch.float16,
)
pipe.enable_model_cpu_offload()

def generate_video(image, motion_bucket, fps, num_frames):
    image = image.resize((1024, 576))

    frames = pipe(
        image,
        decode_chunk_size=4,
        num_frames=num_frames,
        motion_bucket_id=motion_bucket,
    ).frames[0]

    with tempfile.NamedTemporaryFile(suffix=".mp4", delete=False) as f:
        imageio.mimsave(f.name, frames, fps=fps)
        return f.name

demo = gr.Interface(
    fn=generate_video,
    inputs=[
        gr.Image(type="pil", label="Input Image"),
        gr.Slider(1, 255, value=127, label="Motion Amount"),
        gr.Slider(1, 30, value=6, label="FPS"),
        gr.Slider(14, 25, value=25, label="Frames")
    ],
    outputs=gr.Video(label="Generated Video"),
)

demo.launch(server_name="0.0.0.0", server_port=7860)
```

## AnimateDiff

### Installation

```bash
pip install diffusers transformers accelerate
```

### Generate Video from Text

```python
import torch
from diffusers import AnimateDiffPipeline, MotionAdapter, DDIMScheduler
import imageio

# Load motion adapter
adapter = MotionAdapter.from_pretrained("guoyww/animatediff-motion-adapter-v1-5-2")

# Load pipeline
pipe = AnimateDiffPipeline.from_pretrained(
    "runwayml/stable-diffusion-v1-5",
    motion_adapter=adapter,
    torch_dtype=torch.float16,
)
pipe.scheduler = DDIMScheduler.from_pretrained(
    "runwayml/stable-diffusion-v1-5",
    subfolder="scheduler",
    clip_sample=False,
    timestep_spacing="linspace",
    beta_schedule="linear",
    steps_offset=1,
)
pipe.to("cuda")
pipe.enable_model_cpu_offload()

# Generate
output = pipe(
    prompt="A cat walking through a garden, beautiful flowers, sunny day",
    negative_prompt="bad quality, blurry",
    num_frames=16,
    guidance_scale=7.5,
    num_inference_steps=25,
)

# Save
frames = output.frames[0]
imageio.mimsave("animatediff.gif", frames, fps=8)
```

### AnimateDiff with Custom Model

```python
from diffusers import AnimateDiffPipeline, MotionAdapter, EulerDiscreteScheduler

adapter = MotionAdapter.from_pretrained("guoyww/animatediff-motion-adapter-v1-5-2")

# Use a custom checkpoint (e.g., RealisticVision)
pipe = AnimateDiffPipeline.from_pretrained(
    "SG161222/Realistic_Vision_V5.1_noVAE",
    motion_adapter=adapter,
    torch_dtype=torch.float16,
)
```

## AnimateDiff in ComfyUI

### Install Nodes

```bash
cd /workspace/ComfyUI/custom_nodes
git clone https://github.com/Kosinkadink/ComfyUI-AnimateDiff-Evolved.git
git clone https://github.com/Kosinkadink/ComfyUI-VideoHelperSuite.git
```

### Download Motion Models

```bash
cd /workspace/ComfyUI/custom_nodes/ComfyUI-AnimateDiff-Evolved/models
wget https://huggingface.co/guoyww/animatediff/resolve/main/mm_sd_v15_v2.ckpt
```

## CogVideoX

### Text-to-Video

```python
import torch
from diffusers import CogVideoXPipeline
import imageio

pipe = CogVideoXPipeline.from_pretrained(
    "THUDM/CogVideoX-2b",
    torch_dtype=torch.float16
)
pipe.to("cuda")
pipe.enable_model_cpu_offload()

prompt = "A drone flying over a beautiful mountain landscape at sunset"

video = pipe(
    prompt=prompt,
    num_videos_per_prompt=1,
    num_inference_steps=50,
    num_frames=49,
    guidance_scale=6,
).frames[0]

imageio.mimsave("cogvideo.mp4", video, fps=8)
```

## Video Upscaling

### Real-ESRGAN for Video

```python
import cv2
import torch
from basicsr.archs.rrdbnet_arch import RRDBNet
from realesrgan import RealESRGANer

model = RRDBNet(num_in_ch=3, num_out_ch=3, num_feat=64, num_block=23, num_grow_ch=32, scale=4)
upsampler = RealESRGANer(
    scale=4,
    model_path='RealESRGAN_x4plus.pth',
    model=model,
    tile=400,
    tile_pad=10,
    pre_pad=0,
    half=True
)

# Process video frame by frame
cap = cv2.VideoCapture("input.mp4")

# ... upscale each frame
```

## Interpolation (Smooth Videos)

### FILM Frame Interpolation

```python

# Install
pip install tensorflow tensorflow_hub

import tensorflow as tf
import tensorflow_hub as hub

model = hub.load("https://tfhub.dev/google/film/1")

def interpolate(frame1, frame2, num_interpolations=3):
    # Returns interpolated frames between frame1 and frame2
    ...
```

### RIFE (Real-Time)

```bash
pip install rife-ncnn-vulkan-python

from rife_ncnn_vulkan import Rife
rife = Rife(gpu_id=0)

# Interpolate frames
```

## Batch Video Generation

```python
prompts = [
    "A rocket launching into space",
    "Ocean waves crashing on rocks",
    "A butterfly flying through flowers",
]

for i, prompt in enumerate(prompts):
    print(f"Generating {i+1}/{len(prompts)}")
    output = pipe(prompt, num_frames=16)
    imageio.mimsave(f"video_{i:03d}.mp4", output.frames[0], fps=8)
```

## Memory Tips

### For Limited VRAM

```python

# Enable CPU offload
pipe.enable_model_cpu_offload()

# Enable VAE slicing
pipe.enable_vae_slicing()

# Enable attention slicing
pipe.enable_attention_slicing()

# Reduce frame count
num_frames = 14  # Instead of 25
```

### Chunked Decoding

```python
frames = pipe(
    image,
    decode_chunk_size=2,  # Decode 2 frames at a time
    num_frames=25,
).frames[0]
```

## Converting Output

### GIF to MP4

```bash
ffmpeg -i input.gif -movflags faststart -pix_fmt yuv420p -vf "scale=trunc(iw/2)*2:trunc(ih/2)*2" output.mp4
```

### Frame Sequence to Video

```bash
ffmpeg -framerate 8 -i frame_%04d.png -c:v libx264 -pix_fmt yuv420p output.mp4
```

### Add Audio

```bash
ffmpeg -i video.mp4 -i audio.mp3 -c:v copy -c:a aac -shortest output_with_audio.mp4
```

## Performance

| Model       | GPU      | Frames | Time   |
| ----------- | -------- | ------ | ------ |
| SVD-XT      | RTX 3090 | 25     | \~120s |
| SVD-XT      | RTX 4090 | 25     | \~80s  |
| SVD-XT      | A100     | 25     | \~50s  |
| AnimateDiff | RTX 3090 | 16     | \~30s  |
| CogVideoX   | A100     | 49     | \~180s |

## Cost Estimate

Typical CLORE.AI marketplace rates (as of 2024):

| GPU       | Hourly Rate | Daily Rate | 4-Hour Session |
| --------- | ----------- | ---------- | -------------- |
| RTX 3060  | \~$0.03     | \~$0.70    | \~$0.12        |
| RTX 3090  | \~$0.06     | \~$1.50    | \~$0.25        |
| RTX 4090  | \~$0.10     | \~$2.30    | \~$0.40        |
| A100 40GB | \~$0.17     | \~$4.00    | \~$0.70        |
| A100 80GB | \~$0.25     | \~$6.00    | \~$1.00        |

*Prices vary by provider and demand. Check* [*CLORE.AI Marketplace*](https://clore.ai/marketplace) *for current rates.*

**Save money:**

* Use **Spot** market for flexible workloads (often 30-50% cheaper)
* Pay with **CLORE** tokens
* Compare prices across different providers

## Troubleshooting

### OOM Error

* Reduce num\_frames
* Enable CPU offload
* Use smaller decode\_chunk\_size

### Flickering Video

* Increase num\_inference\_steps
* Try different motion\_bucket\_id
* Use frame interpolation

### Poor Quality

* Use higher resolution input (SVD)
* Better prompts (AnimateDiff)
* Increase guidance\_scale