docs: SEO improvements 0819 #1451
There are no files selected for viewing
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
|
|
@@ -6,6 +6,10 @@ sidebarTitle: "Wan2.1 Fun Control" | |
|
|
||
| import UpdateReminder from "/snippets/tutorials/update-reminder.mdx"; | ||
|
|
||
| Wan2.1-Fun-Control is an open-source video generation model from Alibaba's VideoX-Fun project that follows preset control conditions instead of relying on prompt text alone. You can guide the output with Canny edge maps, depth maps, OpenPose skeletons, MLSD geometric edges, or point trajectories. | ||
|
|
||
| The model ships in two sizes: the 1.3B version (about 19 GB) for lightweight local deployment with lower VRAM requirements, and the 14B version (about 47 GB) for higher-quality results. Both support multi-resolution video prediction at 512, 768, and 1024 pixels, generate up to 81 frames (about 5 seconds) at 16 frames per second, and accept multilingual prompts. ComfyUI supports Wan2.1-Fun-Control natively. | ||
|
Comment on lines
+9
to
+11
There was a problem hiding this comment. 🎯 Functional Correctness | 🟡 Minor | ⚡ Quick win 🧩 Analysis chain🏁 Script executed: #!/bin/bash
set -eu
for f in tutorials/video/wan/fun-control.mdx ko/tutorials/video/wan/fun-control.mdx zh/tutorials/video/wan/fun-control.mdx; do
echo "===== $f ====="
sed -n '1,80p' "$f"
done
echo "===== size references ====="
rg -n -i 'fun.control|47(\.0)? ?GB|32(\.8)? ?GB|19 ?GB|14B|1\.3B' tutorials/video/wan ko/tutorials/video/wan zh/tutorials/video/wanRepository: Comfy-Org/docs Length of output: 50371 🏁 Script executed: #!/bin/bash
set -eu
python3 - <<'PY'
import json
import urllib.request
urls = {
"VideoX-Fun README": "https://raw.githubusercontent.com/aigc-apps/VideoX-Fun/main/README.md",
"14B model metadata": "https://huggingface.co/api/models/alibaba-pai/Wan2.1-Fun-14B-Control",
"1.3B model metadata": "https://huggingface.co/api/models/alibaba-pai/Wan2.1-Fun-1.3B-Control",
}
for label, url in urls.items():
print(f"===== {label} =====")
try:
with urllib.request.urlopen(url, timeout=20) as response:
data = response.read().decode("utf-8")
if label == "VideoX-Fun README":
lines = data.splitlines()
for i, line in enumerate(lines, 1):
if any(term in line.lower() for term in ("47", "32", "1.3b", "14b", "model size", "gb")):
start = max(1, i - 2)
end = min(len(lines), i + 2)
print("\n".join(f"{n}: {lines[n-1]}" for n in range(start, end + 1)))
else:
model = json.loads(data)
for sibling in model.get("siblings", []):
name = sibling.get("rfilename", "")
if name.endswith((".safetensors", ".bin", ".pth")):
print(name, sibling.get("size"))
except Exception as exc:
print(type(exc).__name__, exc)
PYRepository: Comfy-Org/docs Length of output: 677 🌐 Web query:
💡 Result: The file name diffusion_pytorch_model.safetensors is a standard naming convention for model weights in Hugging Face repositories [1][2][3]. For the Wan2.1-Fun-14B-Control model, this specific file typically has a size of 32.8 GB [3][4]. The mention of 47.0 GB in technical documentation refers to the total storage space required for the entire model repository or the deployment environment, rather than the size of the single diffusion_pytorch_model.safetensors weight file [5][6][7][8]. Key details regarding the Wan2.1-Fun-14B-Control model: - The 14B Control model is a high-performance variant designed for video control tasks, including support for Canny, Depth, Pose, MLSD, and trajectory control [5][9][8]. - It is designed for multi-resolution video prediction (512, 768, 1024) and was trained to generate videos up to 81 frames at 16 frames per second [5][6][8]. - Due to its 14B parameter scale and high-performance requirements, it demands significant VRAM, with the actual model weight file (diffusion_pytorch_model.safetensors) occupying approximately 32.8 GB [8][3][4]. - When setting up this model in environments like ComfyUI, users are typically advised that the 14B model requires renaming the downloaded file to Wan2.1-Fun-14B-Control.safetensors for proper loading [8]. Citations:
🏁 Script executed: #!/bin/bash
set -eu
echo "===== VideoX-Fun size references ====="
curl -ksSfL https://raw.githubusercontent.com/aigc-apps/VideoX-Fun/main/README.md |
grep -Ein -C 3 '47(\.0)?[[:space:]]*GB|32(\.8)?[[:space:]]*GB|model size|1\.3B|14B' | head -80
echo "===== Hugging Face 14B file sizes ====="
curl -ksSfL https://huggingface.co/api/models/alibaba-pai/Wan2.1-Fun-14B-Control |
jq -r '.siblings[] | select(.rfilename | test("\\.(safetensors|bin|pth)$")) | "\(.rfilename)\t\(.size // "size unavailable")"'
echo "===== Hugging Face 14B README size references ====="
curl -ksSfL https://huggingface.co/alibaba-pai/Wan2.1-Fun-14B-Control/raw/main/README_en.md |
grep -Ein -C 3 '47(\.0)?[[:space:]]*GB|32(\.8)?[[:space:]]*GB|model size|1\.3B|14B' | head -80Repository: Comfy-Org/docs Length of output: 6747 Label the 14B size figures consistently. The upstream 47.0 GB value is total model storage space. The 📍 Affects 3 files
🤖 Prompt for AI AgentsSource: MCP tools |
||
|
|
||
| ## About Wan2.1-Fun-Control | ||
|
|
||
| **Wan2.1-Fun-Control** is an open-source video generation and control project developed by Alibaba team. | ||
|
|
||
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Oops, something went wrong.
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
🎯 Functional Correctness | 🟡 Minor | ⚡ Quick win
🧩 Analysis chain
🏁 Script executed:
Repository: Comfy-Org/docs
Length of output: 1840
「画像生成動画」を画像から動画への生成を示す表現に置き換えてください。
画像生成動画は意味が曖昧です。画像から動画を高精度に生成できますなどに変更してください。🤖 Prompt for AI Agents