Diffusion Policy treats visuomotor control as a generative diffusion process, producing smooth, multi-step action trajectories that excel at contact-rich manipulation. This policy has been trained and pushed to the Hub using LeRobot. See the full LeRobot documentation. The policy consumes these observation features and produces these action features. Inputs Outputs New to LeRobot? These guides cover the full workflow: - Install LeRobot — set up the lerobot package. - Hardware setup — assemble, wire, and calibrate your robot and cameras. - Record data & train a policy — the end-to-end imitation-learning walkthrough. - CLI cheat-sheet — quick reference for the lerobot- commands. The short…
Open-weight model · Robotics
diffusion_blocos_pote
by Victor Ivar van Halst victorvanhalst/diffusion_blocos_pote
diffusion_blocos_pote is an open-weight model for robotics from Victor Ivar van Halst, released under Apache License 2.0. It has 278M parameters. At 16-bit it needs about 0.7 GB of GPU memory, which fits on 1x MI300X from $1.85 an hour, at the lowest prices in the SAVRN Index.
Diffusion Policy treats visuomotor control as a generative diffusion process, producing smooth, multi-step action trajectories that excel at contact-rich manipulation. This policy has been trained and pushed to the Hub using LeRobot.
Parameters278M
Context—
Weights1.1 GB
Licenseapache-2.0
AccessOpen weights
Monthly Downloads—
Runs On
What it takes to serve diffusion_blocos_pote (278M parameters): the memory its weights need at each precision, and the cheapest way to rent enough data-center GPUs to hold them.
| Precision | Weights | Memory needed | Cheapest setup | Per hour | Also fits |
|---|---|---|---|---|---|
| 16-bit | 0.6 GB | 0.7 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 8-bit | 0.3 GB | 0.3 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 4-bit | 0.1 GB | 0.2 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
Memory is the weights at that precision plus 20% for the runtime and a short context; a long context needs more. Prices are the lowest on-demand hourly rates in the SAVRN Index, read Oct 18, 2026.
diffusion_blocos_pote on every accelerator the SAVRN Index prices, at every precision
Model Card
By Victor Ivar van Halst, published under apache-2.0, revision 2aa4c3c68420.
Diffusion Policy treats visuomotor control as a generative diffusion process, producing smooth, multi-step action trajectories that excel at contact-rich manipulation. This policy has been trained and pushed to the Hub using LeRobot. See the full LeRobot documentation. The policy consumes these observation features and produces these action features. Inputs Outputs New to LeRobot? These guides cover the full workflow: - Install LeRobot — set up the lerobot package. - Hardware setup — assemble, wire, and calibrate your robot and cameras. - Record data & train a policy — the end-to-end imitation-learning walkthrough. - CLI cheat-sheet — quick reference for the lerobot- commands. The short…
Read Victor Ivar van Halst's full model card
Model Card for diffusion
Diffusion Policy treats visuomotor control as a generative diffusion process, producing smooth, multi-step action trajectories that excel at contact-rich manipulation.
This policy has been trained and pushed to the Hub using LeRobot.
See the full LeRobot documentation.
Model Details
- License: apache-2.0
- Robot type:
so_follower - Cameras:
wrist,external
Inputs & Outputs
The policy consumes these observation features and produces these action features.
Inputs
| Feature | Type | Shape |
|---|---|---|
observation.state |
STATE | (6,) |
observation.images.wrist |
VISUAL | (3, 480, 640) |
observation.images.external |
VISUAL | (3, 480, 640) |
Outputs
| Feature | Type | Shape |
|---|---|---|
action |
ACTION | (6,) |
Training Dataset
- Repository: victorvanhalst/so101_blocos_pote_final_20261013_210550
- Episodes: 60
- Frames: 17787
- Frame rate: 25 FPS
- Task(s): "Pick the toy block and place it in the bowl"
Training Configuration
| Setting | Value |
|---|---|
| Training steps | 100000 |
| Batch size | 16 |
| Optimizer | adam |
| Learning rate | 0.0001 |
| Seed | 1000 |
| LeRobot version | 0.6.1 |
How to Get Started with the Model
New to LeRobot? These guides cover the full workflow:
- Install LeRobot — set up the
lerobotpackage. - Hardware setup — assemble, wire, and calibrate your robot and cameras.
- Record data & train a policy — the end-to-end imitation-learning walkthrough.
- CLI cheat-sheet — quick reference for the
lerobot-*commands.
The short version to run and train this policy:
Run the policy on your robot
lerobot-rollout \
--strategy.type=base \
--robot.type=so_follower \
--robot.port=<your_robot_port> \
--robot.cameras="{ <camera_1>: {type: opencv, index_or_path: <index_or_path>, width: 640, height: 480, fps: 30}, <camera_2>: {type: opencv, index_or_path: <index_or_path>, width: 640, height: 480, fps: 30}}" \
--policy.path=victorvanhalst/diffusion_blocos_pote \
--task="Pick the toy block and place it in the bowl" \
--duration=60
Replace the remaining <...> placeholders with your own values: --robot.port and the camera names/indices are specific to your machine, and the camera names must match the observation keys this policy was trained on.
When --strategy.type=base is used the script doesn't record the episodes. Skipping duration will make the policy run indefinitely. For more information look at rollout documentation.
Train your own policy
lerobot-train \
--dataset.repo_id=${HF_USER}/<dataset> \
--policy.type=diffusion \
--output_dir=outputs/train/<policy_repo_id> \
--job_name=lerobot_training \
--policy.device=cuda \
--policy.repo_id=${HF_USER}/<policy_repo_id> \
--wandb.enable=true
Writes checkpoints to outputs/train/<policy_repo_id>/checkpoints/.
Evaluation
No evaluation results have been provided for this policy yet.
Citation
If you use this policy, please cite the method linked in the description above, along with LeRobot:
@misc{cadene2024lerobot,
author = {Cadene, Remi and Alibert, Simon and Soare, Alexander and Gallouedec, Quentin and Zouitine, Adil and Palma, Steven and Kooijmans, Pepijn and Aractingi, Michel and Shukor, Mustafa and Aubakirova, Dana and Russi, Martino and Capuano, Francesco and Pascal, Caroline and Choghari, Jade and Moss, Jess and Wolf, Thomas},
title = {LeRobot: State-of-the-art Machine Learning for Real-World Robotics in Pytorch},
howpublished = "\url{https://github.com/huggingface/lerobot}",
year = {2024}
}
Identity and Version
- Repository
- victorvanhalst/diffusion_blocos_pote
- Publisher
- Victor Ivar van Halst
- Task
- Robotics
- Modality
- Control
- Library
- lerobot
- Parameters
- 278M parameters
- Languages
- Not stated by the source
- Revision
- 2aa4c3c68420a789358d4e944b3502845f393a79
- First published
- 2026-10-15
- Last updated
- 2026-10-15
Files and Weights
9 files, 1.1 GB in total. The weights are 3 files totalling 1.1 GB in safetensors.
Weights3 files · 1.1 GB
Configuration4 files · 11.3 KB
Documentation1 file · 5.7 KB
Repository1 file · 1.5 KB
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| model.safetensors | Weights | 1.1 GB | 94a6dbda2f78 |
| policy_postprocessor_step_0_unnormalizer_processor.safetensors | Weights | 7.6 KB | b65c30c509d5 |
| policy_preprocessor_step_3_normalizer_processor.safetensors | Weights | 7.6 KB | 80e938a0723d |
| config.json | Configuration | 2.4 KB | — |
| policy_postprocessor.json | Configuration | 658 B | — |
| policy_preprocessor.json | Configuration | 1.3 KB | — |
| train_config.json | Configuration | 7.0 KB | — |
| README.md | Documentation | 5.7 KB | — |
| .gitattributes | Repository | 1.5 KB | — |
License and Download
- License
- apache-2.0
- Access
- Open weights, no gate
- Download size
- 1.1 GB
Download from Victor Ivar van Halst
Released by Victor Ivar van Halst through its official repository on Hugging Face. Read the license.
Built From
- Described by arXiv:2303.04137
- Trained on (disclosed) victorvanhalst/so101_blocos_pote_final_20261013_210550
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 1.1 GB |
| 16-bit | 0.6 GB |
| 8-bit | 0.3 GB |
| 4-bit | 0.1 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Questions About diffusion_blocos_pote
How much GPU memory does diffusion_blocos_pote need?
About 0.7 GB at 16-bit and 0.2 GB at 4-bit: the weights (278M parameters) plus a working margin. A long context needs more.
What is the cheapest GPU to run diffusion_blocos_pote on?
At 16-bit, 1x MI300X from $1.85 an hour; at 4-bit, 1x MI300X from $1.85 an hour, at the lowest on-demand prices the SAVRN Index lists.
Can I use diffusion_blocos_pote commercially?
Yes. diffusion_blocos_pote is released under Apache License 2.0. The Apache License 2.0 is a permissive open-source license. It permits commercial use, modification and redistribution. It requires keeping the license and copyright notices and any NOTICE file, stating significant changes, and it includes an express patent grant from contributors.
Similar Models
Diffusion Policy treats visuomotor control as a generative diffusion process, producing smooth, multi-step action trajectories that excel at contact-rich manipulation. This policy has been trained and pushed to the Hub using LeRobot. See the full LeRobot documentation. The policy consumes these observation features and produces these action features. Inputs Outputs New to LeRobot? These guides cover the full workflow: - Install LeRobot — set up the lerobot package. - Hardware setup — assemble, wire, and calibrate your robot and cameras. - Record data & train a policy — the end-to-end imitation-learning walkthrough. - CLI cheat-sheet — quick reference for the lerobot- commands. The short…
Diffusion Policy treats visuomotor control as a generative diffusion process, producing smooth, multi-step action trajectories that excel at contact-rich manipulation. This policy has been trained and pushed to the Hub using LeRobot. See the full LeRobot documentation. The policy consumes these observation features and produces these action features. Inputs Outputs New to LeRobot? These guides cover the full workflow: - Install LeRobot — set up the lerobot package. - Hardware setup — assemble, wire, and calibrate your robot and cameras. - Record data & train a policy — the end-to-end imitation-learning walkthrough. - CLI cheat-sheet — quick reference for the lerobot- commands. The short…
Diffusion Policy treats visuomotor control as a generative diffusion process, producing smooth, multi-step action trajectories that excel at contact-rich manipulation. This policy has been trained and pushed to the Hub using LeRobot. See the full LeRobot documentation. The policy consumes these observation features and produces these action features. Inputs Outputs New to LeRobot? These guides cover the full workflow: - Install LeRobot — set up the lerobot package. - Hardware setup — assemble, wire, and calibrate your robot and cameras. - Record data & train a policy — the end-to-end imitation-learning walkthrough. - CLI cheat-sheet — quick reference for the lerobot- commands. The short…
Diffusion Policy treats visuomotor control as a generative diffusion process, producing smooth, multi-step action trajectories that excel at contact-rich manipulation. This policy has been trained and pushed to the Hub using LeRobot. See the full LeRobot documentation. The policy consumes these observation features and produces these action features. Inputs Outputs New to LeRobot? These guides cover the full workflow: - Install LeRobot — set up the lerobot package. - Hardware setup — assemble, wire, and calibrate your robot and cameras. - Record data & train a policy — the end-to-end imitation-learning walkthrough. - CLI cheat-sheet — quick reference for the lerobot- commands. The short…
Diffusion Policy treats visuomotor control as a generative diffusion process, producing smooth, multi-step action trajectories that excel at contact-rich manipulation. This policy has been trained and pushed to the Hub using LeRobot. See the full documentation at LeRobot Docs. For a complete walkthrough, see the training guide. Below is the short version on how to train and run inference/eval: Writes checkpoints to outputs/train/ /checkpoints/. Prefix the dataset repo with eval\ and supply --policy.path pointing to a local or hub checkpoint.