John Pope

johndpope's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted a paper 1 day ago

Tri-Prompting: Video Diffusion with Unified Control over Scene, Subject, and Motion

Paper • 2603.15614 • Published Mar 16 • 7

liked 2 models 3 days ago

wpydcr/NanoAvatar

Updated about 21 hours ago • 3

DANNY621/H3-World

Image-to-Video • Updated 4 days ago • • 88

New activity in alibaba-pai/MiniMax-H3-Fun-Controlnet-Union 3 days ago

Requests for comfyui example workflow for this Controlnet

👍 23

2

#2 opened 21 days ago by

Fleinstein

liked a model 3 days ago

alibaba-pai/MiniMax-H3-Fun-Controlnet-Union

Text-to-Video • Updated 22 days ago • 11.4k • 177

upvoted a paper 7 days ago

BDH-CQ: In-Context Learning with Recurrent Latent Reasoning

Paper • 2608.09888 • Published Aug 10 • 780

liked a model 9 days ago

lightx2v/Minimax-h3-Turbo

Image-to-Video • Updated 5 days ago • 1.45M • 937

liked a model 10 days ago

smskk/114kk

Updated Aug 5 • 1

liked a Space 11 days ago

Running on Zero

MCP

Featured

36

H3-World

🎮

36

Drive a world model with WASD and camera keys

liked 2 models 11 days ago

PoopMan333/H3_Character_Sheet_Generator

Image-to-Image • Updated 5 days ago • 177

smhfacct/Minimax-H3-fl2va-ref2va-hybrid-models

Text-to-Video • Updated 29 days ago • 257

upvoted a collection 11 days ago

SolarWM

Collection

Family-specific checkpoints, released data, and paper for SolarWM long-horizon interactive video world models. • 7 items • Updated 5 days ago • 7

liked 2 models 11 days ago

junchaoh-cs/SolarWM

Updated 12 days ago • 3

rzgar/minimax-h3_fl2v_8Step_motion_enhancer

Image-to-Video • Updated 10 days ago • 7.01k • • 43

liked a model 20 days ago

thomsonreuters/Thomson-1.0-Small

Image-Text-to-Text • 35B • Updated 18 days ago • 2.43k • 194

reacted to AtAndDev's post with 🔥 20 days ago

view post

Post

2118

FIRST SPECK MODEL RELEASED:
specklabs/Speck1-140M

new models coming very soon (both instruct and much better models), with much much higher training scale as i am getting marenostrum5 access soon!
we will be looking at 100b-2t token budgets :)

See translation

• 
• 
• 
• 4 replies

·

🔥

9

9

❤️

2

2

+

Reply

upvoted a paper 20 days ago

FreeToken: Efficient Edge-Native MoE Serving with Bandwidth-Adaptive Execution

Paper • 2608.16157 • Published 29 days ago • 109

New activity in SimpleTuner/open-rvq-encoder-minimax-music3 20 days ago

How to help?

3

#1 opened 22 days ago by

johndpope

updated a model 20 days ago

johndpope/open-rvq-encoder-minimax-music3

Updated 20 days ago

published a model 20 days ago

johndpope/open-rvq-encoder-minimax-music3

Updated 20 days ago