Model reference · open weights
psi0_5 is an open-weight video model from StanfordNeuroAILab. AxForge deploys and operates it for you on dedicated EU-owned hardware — with the licence handled where one is required.
Available as managed deployment — configured and operated for you on dedicated EU hardware, quoted per deployment.
What it is
| Released by | StanfordNeuroAILab |
|---|---|
| Type | Video models |
| Task | Image→video |
| Runs with | transformers |
| Released | 2026-05-17 |
| Popularity | 998 downloads / month |
| Licence | Commercial licence needed |
About
Prompt PSI with images, motion, depth, camera pose, or partial future states, and ask it to complete the missing pieces of a physical scene.
PSI treats visual prediction as a promptable modeling problem. A prompt can be
as simple as rgb0->rgb1, or it can include explicit control handles such as
optical flow, depth, camera motion, and partially specified future frames. The
same predictor handles all of these notations.
| Prompt | What PSI Does |
|---|---|
rgb0->rgb1 | continue a scene one frame forward |
rgb0->f01,rgb1 | imagine motion and render the next frame |
rgb0,f01->f01,rgb1 | densify a sparse flow prompt, then render |
rgb0,d0,f01->f01,d1,rgb1 | use depth and motion to predict flow, depth, and RGB |
rgb0,c01->rgb1 | synthesize a new camera view |
from PIL import Image
from transformers import AutoModel
predictor = AutoModel.from_pretrained(
"StanfordNeuroAILab/psi0_5",
trust_remote_code=True,
device="cuda:0",
)
rgb1 = predictor.generate("rgb0->rgb1", rgb0=Image.open("scene.png"))
rgb1.save("scene_next.png")
f01 = predictor.sparse_flow_prompt([((70, 221), (168, 221))], rgb0.size)
dense_flow, rgb1 = predictor.generate(
"rgb0,f01->f01,rgb1",
rgb0=rgb0,
f01=f01,
num_seq_patches=256,
)
camera = {
"fov_x": 60.0,
"fov_y": 60.0,
"euler_angles": [0.0, -0.12, 0.0],
"translation": [0.10, 0.0, 0.04],
}
rgb1 = predictor.generate(
"rgb0,c01->rgb1",
rgb0=Image.open("coffee_mug_000.png"),
c01=camera,
)
The full usage guide includes sparse flow construction, depth/flow prompting, camera-conditioned NVS, visual statistics, and scriptable demos:
docs/usage.md
The release gallery shows many prompt patterns in action:
https://neuroailab.github.io/psi-website/blog/psi-generations.html
PSIv0.5 is a modestly sized model that has not undergone any post-training yet.
Some of its rollouts diverge. We recommend unrestricted sampling for flow
prediction and top_p=0.9, top_k=1000 for RGB rendering. Correct prompting
can significantly improve generations, and simple harnesses such as those in the
provided Gradio app can be used to steer the model much more effectively. We
believe this direction has great potential for scaling to create even more
comprehensive models of the world while maintaining this highly controllable
API.
From the published model card. Full card on the HuggingFace links in the sidebar.
Using it via the API
Once AxForge deploys psi0-5 for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (psi0-5 below is illustrative; you get the exact model name on deployment.)
$ curl -sS https://api.axforge.ai/v1/videos/generations \
-H "Authorization: Bearer $AXFORGE_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"psi0-5","prompt":"a drone shot over a forest"}'
Create an account — your API key is available in the console. 3M free tokens every 30 days with every new account.