5
DeepSeek-R1-Distill-Qwen-32B-Japanese-AWQ
💬
Akihito Miyazaki PRO
Akjava
AI & ML interests
I'm developing a user-friendly, browser-based platform that allows users to connect various AI services like ChatGPT, Gemini, local LLMs, Hugging Face models, and more. Our goal is to empower users to build custom AI tools by seamlessly combining these services, similar to Langchain or ComfyUI.
Recent Activity
liked
a Space
11 days ago
Aratako/DeepSeek-R1-Distill-Qwen-32B-Japanese-AWQ
updated
a Space
12 days ago
Akjava/chat-phi-4-deepseek-R1K-RL-EZO
published
a Space
12 days ago
Akjava/chat-phi-4-deepseek-R1K-RL-EZO
Organizations
None yet
Akjava's activity
liked
a
Space
11 days ago
updated
a
Space
12 days ago
published
a
Space
12 days ago
liked
a
dataset
19 days ago
reacted to
nyuuzyou's
post with ❤️
23 days ago
Post
1685
🎨 Artfol Dataset -
nyuuzyou/artfol
A collection of 1,892,816 artwork posts featuring:
- High-quality art pieces with various styles and techniques
- Complete metadata including artist IDs, titles, and moderation flags
- Content from Artfol social media platform
The dataset contains:
- Public domain artwork posts
- Artist attribution and identifiers
- Direct image URLs and web page links
- Content safety flags (NSFW, gore)
- Post titles and descriptions
All content is available under CC0 license, allowing unrestricted use including commercial applications.
A collection of 1,892,816 artwork posts featuring:
- High-quality art pieces with various styles and techniques
- Complete metadata including artist IDs, titles, and moderation flags
- Content from Artfol social media platform
The dataset contains:
- Public domain artwork posts
- Artist attribution and identifiers
- Direct image URLs and web page links
- Content safety flags (NSFW, gore)
- Post titles and descriptions
All content is available under CC0 license, allowing unrestricted use including commercial applications.
posted
an
update
about 1 month ago
Post
630
I've released some spaces that demonstrates more advanced uses of MediaPipe-landmarks.
Head-pose-estimate
original mediapipe’s detection is good on short angles,trained-model seems work and there are more improve space
Akjava/mediapipe-head-pose-estimation
generate-3d-head:gltf
this is simple and initial
Akjava/mediapipe-face-mesh-3d
Akjava/mediapipe-head-2d-spinning
prototype-faceswap
color adjust and transform soso work,need find a way to keep face features.
Akjava/mediapipe-face-skin-transform
Head-pose-estimate
original mediapipe’s detection is good on short angles,trained-model seems work and there are more improve space
Akjava/mediapipe-head-pose-estimation
generate-3d-head:gltf
this is simple and initial
Akjava/mediapipe-face-mesh-3d
Akjava/mediapipe-head-2d-spinning
prototype-faceswap
color adjust and transform soso work,need find a way to keep face features.
Akjava/mediapipe-face-skin-transform
updated
a
collection
about 1 month ago
updated
a
Space
about 1 month ago
updated
a
collection
about 1 month ago
updated
9
Spaces
about 1 month ago
1
Mediapipe Face Landmark/Skin Transform
💻
Transform face landmark/skin,half of FaceSwap
4
Mediapipe Face Mesh 3d
👀
create 3d-gltf face-mesh from image with mediapipe
2
Mediapipe Head 2d Spinning
🐠
spining mediapipe 468 points
1
Mediapipe Face Landmark/Skin Transform
💻
Transform face landmark/skin,half of FaceSwap
4
Mediapipe Face Mesh 3d
👀
create 3d-gltf face-mesh from image with mediapipe
2
Mediapipe Head 2d Spinning
🐠
spining mediapipe 468 points
3
Mediapipe Head Pose Estimation
👁
2 head pose estimation with mediapipe and trained-model
3
Mediapipe Head Pose Estimation
👁
2 head pose estimation with mediapipe and trained-model
2
Mediapipe Head 2d Spinning
🐠
spining mediapipe 468 points