Skip to page content
SAVRN
Search Plan a project

Open-weight model · Image to video

cosmos-predict2.5-2b-agibot-mv-robocasa-pressbutton

by SeongyoungMoon Gom-sy/cosmos-predict2.5-2b-agibot-mv-robocasa-pressbutton

cosmos-predict2.5-2b-agibot-mv-robocasa-pressbutton is a model for image to video from SeongyoungMoon, released under other (access requested at publisher). Its published files total 34.4 GB.

Private research checkpoints — Cosmos-Predict2.5-2B robot/multiview-agibot (frameinit) post-trained on RoboCasa CoffeePressButton 3-view renders (55 human demos, 704² → trained at 480², 81 frames/view @20 fps). 2026-10.

Parameters—
Context—
Weights12.9 GB
Licenseother
AccessAccess requested at publisher
Monthly Downloads—

Model Card

Private research checkpoints — Cosmos-Predict2.5-2B robot/multiview-agibot (frameinit) post-trained on RoboCasa CoffeePressButton 3-view renders (55 human demos, 704² → trained at 480², 81 frames/view @20 fps). 2026-10. iterXXXXXX/modelemabf16.pt — EMA weights (bf16) for inference with experiment 2brobocasacoffeeagibotframeinit (code/ holds the dataset/experiment files and mvinfer.py needed to reproduce; see code/HANDOFF.md). Research only (world-model video generation for IDM labelling / policy training). Round 1 (iter004000/, identity extrinsics) showed view collapse at t≥20 frames (3 views converging to one), seed-dependent. Round 2 restarts from the agibot base with real MuJoCo camera…

Excerpt from the card by SeongyoungMoon, licensed other.

Identity and Version

Repository
Gom-sy/cosmos-predict2.5-2b-agibot-mv-robocasa-pressbutton
Publisher
SeongyoungMoon
Task
Image to video
Modality
Other
Library
Not stated by the source
Parameters
Not stated by the source
Languages
Not stated by the source
Revision
efc18397f8c338b020455d800dd53cc9fe3cc72a
First published
2026-10-04
Last updated
2026-10-09

Files and Weights

46 files, 34.4 GB in total. The weights are 3 files totalling 12.9 GB in pt.

Weights3 files · 12.9 GB
Configuration15 files · 62.5 KB
Documentation4 files · 18.6 KB
Other19 files · 21.5 GB
Repository5 files · 4.3 MB
Every file
FileTypeSizeSHA-256
iter_004000/model_ema_bf16.ptWeights4.3 GB —
realcam/iter_004000/model_ema_bf16.ptWeights4.3 GB —
realcam/iter_008000/model_ema_bf16.ptWeights4.3 GB —
calib_toolkit/make_cameras_real.pyConfiguration2.8 KB —
calib_toolkit/selftest_synthetic.pyConfiguration2.0 KB —
calib_toolkit/solve_calib.pyConfiguration4.9 KB —
calib_toolkit/verify_projection.pyConfiguration1.5 KB —
code/cameras.jsonConfiguration680 B —
code/data.pyConfiguration2.6 KB —
code/experiment/robocasa.pyConfiguration3.1 KB —
code/extract_cam_poses.pyConfiguration2.6 KB —
code/mv_infer.pyConfiguration6.3 KB —
code/precompute_mv_text.pyConfiguration1.7 KB —
code/robocasa_dataset.pyConfiguration8.5 KB —
code_round2/detect_collapse.pyConfiguration2.0 KB —
code_round2/extract_cam_poses.pyConfiguration3.9 KB —
code_round2/mv_infer.pyConfiguration8.4 KB —
code_round2/robocasa_data.pyConfiguration11.6 KB —
README.mdDocumentation2.2 KB —
calib_toolkit/README_CALIB.mdDocumentation3.2 KB —
code/HANDOFF.mdDocumentation7.5 KB —
code_round2/RESUME.mdDocumentation5.7 KB —
code/mv_train.shOther1.5 KB —
code_round2/run_agibot_robocasa.shOther2.5 KB —
code_round2/run_mv_infer.shOther1.4 KB —
round2_3task/iter_000004893/model/__0_0.distcpOther3.2 GB —
round2_3task/iter_000004893/model/__1_0.distcpOther3.2 GB —
round2_3task/iter_000004893/model/__2_0.distcpOther3.2 GB —
round2_3task/iter_000004893/model/__3_0.distcpOther3.2 GB —
round2_3task/iter_000004893/optim/__0_0.distcpOther2.2 GB —
round2_3task/iter_000004893/optim/__1_0.distcpOther2.1 GB —
round2_3task/iter_000004893/optim/__2_0.distcpOther2.1 GB —
round2_3task/iter_000004893/optim/__3_0.distcpOther2.1 GB —
round2_3task/iter_000004893/scheduler/__0_0.distcpOther7.7 KB —
round2_3task/iter_000004893/scheduler/__1_0.distcpOther —
round2_3task/iter_000004893/scheduler/__2_0.distcpOther —
round2_3task/iter_000004893/scheduler/__3_0.distcpOther —
round2_3task/iter_000004893/trainer/__0_0.distcpOther1.3 KB —
round2_3task/iter_000004893/trainer/__1_0.distcpOther —
round2_3task/iter_000004893/trainer/__2_0.distcpOther —
round2_3task/iter_000004893/trainer/__3_0.distcpOther —
.gitattributesRepository2.3 KB —
round2_3task/iter_000004893/model/.metadataRepository1.1 MB —
round2_3task/iter_000004893/optim/.metadataRepository3.2 MB —
round2_3task/iter_000004893/scheduler/.metadataRepository1.2 KB —
round2_3task/iter_000004893/trainer/.metadataRepository761 B —

License and Download

License
other
Access
Access requested at publisher
Download size
12.9 GB
Request access from SeongyoungMoon

SeongyoungMoon grants access through its official repository on Hugging Face.

Memory Requirements

PrecisionWeights in memory
As published12.9 GB

Weights only, from the published parameter count; the key-value cache and runtime add to this.

Questions About cosmos-predict2.5-2b-agibot-mv-robocasa-pressbutton

What license is cosmos-predict2.5-2b-agibot-mv-robocasa-pressbutton released under?

other, as its publisher declares it. Read the license text before commercial use.

Similar Models

Model · Image to video

Wan_2.2_ComfyUI_Repackaged

Comfy Org

Repackaged model files for ComfyUI. - https://huggingface.co/nvidia/ChronoEdit-14B-Diffusers - https://huggingface.co/Wan-AI/Wan2.2-Animate-14B - https://huggingface.co/alibaba-pai/Wan2.2-Fun-A14B-Control-Camera - https://huggingface.co/alibaba-pai/Wan2.2-Fun-A14B-Control - https://huggingface.co/alibaba-pai/Wan2.2-Fun-5B-Control - https://huggingface.co/alibaba-pai/Wan2.2-Fun-5B-InP - https://huggingface.co/alibaba-pai/Wan2.2-Fun-A14B-InP - https://huggingface.co/alibaba-pai/Wan2.2-VACE-Fun-A14B - https://huggingface.co/Wan-AI/Wan2.2-I2V-A14B - https://huggingface.co/Wan-AI/Wan2.2-S2V-14B - https://huggingface.co/Wan-AI/Wan2.2-T2V-A14B - https://huggingface.co/Wan-AI/Wan2.2-TI2V-5B…

Open weights apache-2.0 diffusion-single-file
View model

Model · Image to video

LTX-2.5

LTX.io

LTX-2.5 is an open world model with open weights, built for local execution and fine-tuning. Its established use is generating synchronized, high-fidelity video and audio from text, image, and video inputs; applicability to emerging domains such as robotics and physical AI is developing. Full control and customization — self-host on your own infrastructure. No per-generation billing, no per-seat lock-in, no forced API dependency. Revenue is measured across the whole entity, including subsidiaries and affiliates under common control. The full, binding terms live in LICENSE. - Native multishot generation — generate connected scenes in a single pass: multiple shots that hold character…

Access requested at publisher other diffusion-single-file
View model

Model · Image to video

LTX-2.5

Comfyicu

LTX-2.5 is an open world model with open weights, built for local execution and fine-tuning. Its established use is generating synchronized, high-fidelity video and audio from text, image, and video inputs; applicability to emerging domains such as robotics and physical AI is developing. Full control and customization — self-host on your own infrastructure. No per-generation billing, no per-seat lock-in, no forced API dependency. Revenue is measured across the whole entity, including subsidiaries and affiliates under common control. The full, binding terms live in LICENSE. - Native multishot generation — generate connected scenes in a single pass: multiple shots that hold character…

Open weights other diffusion-single-file
View model

Model · Image to video

Minimax-h3-Turbo

Lightx2v

Please check our repository or the LightX2V MiniMax-H3 examples to reproduce the results. Please check the model specifications for more details. Try the MiniMax-H3 Turbo LoRA directly in LightX2V Studio: The Studio currently uses the FL2V 8-step v1.0 768p LoRA, which provides improved video and audio generation quality with 8-step inference. Integrate MiniMax-H3 Turbo into your application through the LightX2V API

Open weights apache-2.0 diffusers
View model

Model · Image to video

MiniMax-H3-GGUF

Jay

This repository (Abiray/MiniMax-H3-GGUF) provides GGUF quantized versions and necessary component files for the MiniMax H3 model. MiniMax H3 is a general-purpose, omni-modal generative system that supports unified understanding of multimodal contexts composed of text, images, video, and audio. It can generate video with native stereo audio at resolutions up to 2K and durations of up to 15 seconds. If you are looking for a smaller model with the same great quality that fits better on consumer-tier GPUs, please check out the MiniMax-H3-Pruned-GGUF repository. The pruned architecture is compressed down to 8.9 GB – 21.6 GB, bringing MiniMax H3 execution directly to consumer hardware. This…

Open weights other
View model

Model · Image to video

LTX-2.3

LTX.io

This model card focuses on the LTX-2.3 model, which is a significant update to the LTX-2 model with improved audio and visual quality as well as enhanced prompt adherence. LTX-2 was presented in the paper LTX-2: Efficient Joint Audio-Visual Foundation Model. If you want to dive in right to the code - it is available here. LTX-2.3 is a DiT-based audio-video foundation model designed to generate synchronized video and audio within a single model. It brings together the core building blocks of modern video generation, with open weights and a focus on practical, local execution. LTX-2.3 is accessible right away via the API Playground. You can use the models - full, distilled, upscalers and any…

Open weights other diffusers
View model