SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2410.07718 · 2024

Hallo2: Long-Duration and High-Resolution Audio-Driven Portrait Image Animation

arXiv · PDF · Open in the Atlas

Code that ran

8 of 10 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 2 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 6 failures of our instrument; 2 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2410.07718.json · badge: /api/ran/2410.07718.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
fudan-generative-vision/hallo2 canonical (classifier label)
classifier basis: census
8 ran · 2 no recorded run
FunctionStatusWhere it lives
findNonreflectiveSimilarity Ran
ran, honoured the contract we drafted
fudan-generative-vision/hallo2/facelib/detection/matlab_cp2tform.py
code served (permissive licence) · get_code("6f685b41161dd908")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned tuple, ndim 3, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import numpy as np

# Create small test data for the function
# uv and xy should be 2D arrays with shape (M, 2) where M is number of points
# We need at least K=2 unique points, so let's use 3 points to be safe

uv = np.array([
    [1.0, 2.0],
    [3.0, 4.0],
    [5.0, 6.0]
], dtype=np.float64)

xy = np.array([
    [0.5, 1.0],
    [1.5, 2.0],
    [2.5, 3.0]
], dtype=np.float64)

options = {'K': 2}

ARGS = {
    'uv': uv,
    'xy': xy,
    'options': options
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple, ndim 3, dtype family float — a tuple output has no array shape of its own; none is stated
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
get_affine_transform_matrix Ran
ran, honoured the contract we drafted
fudan-generative-vision/hallo2/facelib/detection/align_trans.py
code served (permissive licence) · get_code("b7f364dbce963974")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned ndarray, ndim 2, dtype family float, shape (2, 3) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import numpy as np

# Create source points (4 points with x, y coordinates)
src_pts = np.array([
    [10.0, 20.0],
    [30.0, 40.0],
    [50.0, 60.0],
    [70.0, 80.0]
], dtype=np.float32)

# Create destination points (4 points with x, y coordinates)
# These represent where the source points should map to
dst_pts = np.array([
    [15.0, 25.0],
    [35.0, 45.0],
    [55.0, 65.0],
    [75.0, 85.0]
], dtype=np.float32)

ARGS = {
    'src_pts': src_pts,
    'dst_pts': dst_pts
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 2, dtype family float, shape (2, 3) — shape (2, 3) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
get_position_from_periods Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
fudan-generative-vision/hallo2/basicsr/models/lr_scheduler.py
pointer only (licence: MIT); the stored copy get_code serves, from AlifAshrafee/Restoring-Without-Forgetting, is pointer only (licence: NONE) · get_code("cd569444547de84f")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from AlifAshrafee/Restoring-Without-Forgetting, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

get_reference_facial_points Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
fudan-generative-vision/hallo2/facelib/detection/align_trans.py
code served (permissive licence) · get_code("7089edc02820bcfe")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned ndarray, ndim 2, dtype family float, shape (5, 2) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import numpy as np

ARGS = {
    "output_size": None,
    "inner_padding_factor": 0.0,
    "outer_padding": (0, 0),
    "default_square": False,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 2, dtype family float, shape (5, 2) — shape (5, 2) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
reduce_loss Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
fudan-generative-vision/hallo2/basicsr/losses/loss_util.py
code served (permissive licence) · get_code("a648a03a952822c0")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned Tensor, ndim 0, dtype family float, shape () as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn.functional as F

torch.manual_seed(0)

# Create a small elementwise loss tensor (batch=2, elements=4)
loss = torch.tensor([[0.5, 1.2, 0.3, 0.8], [0.9, 0.4, 1.1, 0.6]], dtype=torch.float32)

# Test with 'mean' reduction
reduction = 'mean'

ARGS = {
    'loss': loss,
    'reduction': reduction,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 0, dtype family float, shape () — shape () as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
tformfwd Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
fudan-generative-vision/hallo2/facelib/detection/matlab_cp2tform.py
code served (permissive licence) · get_code("b4e2f92e3ce5abc6")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned ndarray, ndim 2, dtype family float, shape (4, 2) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import numpy as np

# Create a 3x3 affine transformation matrix
trans = np.array([
    [1.0, 0.0, 2.0],
    [0.0, 1.0, 3.0],
    [0.0, 0.0, 1.0]
], dtype=np.float32)

# Create a Kx2 array of coordinates (K=4 points)
uv = np.array([
    [0.0, 0.0],
    [1.0, 1.0],
    [2.0, 3.0],
    [4.0, 5.0]
], dtype=np.float32)

ARGS = {
    "trans": trans,
    "uv": uv
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 2, dtype family float, shape (4, 2) — shape (4, 2) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
tforminv Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
fudan-generative-vision/hallo2/facelib/detection/matlab_cp2tform.py
code served (permissive licence) · get_code("9d62a8188b0ad97a")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned ndarray, ndim 2, dtype family float, shape (5, 2) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import numpy as np

# Create a valid 3x3 affine transformation matrix
# Using a simple rotation + translation matrix
trans = np.array([
    [0.866, -0.5, 10.0],      # rotation + translation x
    [0.5, 0.866, 20.0],        # rotation + translation y
    [0.0, 0.0, 1.0]            # homogeneous coordinate
], dtype=np.float64)

# Create sample coordinates (K x 2 array)
# K=5 points with (x, y) coordinates
uv = np.array([
    [0.0, 0.0],
    [1.0, 0.0],
    [0.0, 1.0],
    [1.0, 1.0],
    [2.0, 3.0]
], dtype=np.float64)

ARGS = {
    "trans": trans,
    "uv": uv
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 2, dtype family float, shape (5, 2) — shape (5, 2) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
weight_reduce_loss Ran
ran; our contract draft was wrong, not the code
fudan-generative-vision/hallo2/basicsr/losses/loss_util.py
code served (permissive licence) · get_code("1ba39317ea81871a")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned Tensor, ndim 0, dtype family float, shape () as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn.functional as F

torch.manual_seed(0)

# Create a small loss tensor (batch_size=2, num_elements=4)
loss = torch.rand(2, 4)

# Create a weight tensor with matching dimensions
# weight.dim() == loss.dim() and weight.size(1) == loss.size(1)
weight = torch.rand(2, 4)

# Test different reduction modes
reduction = 'mean'

ARGS = {
    'loss': loss,
    'weight': weight,
    'reduction': reduction
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 0, dtype family float, shape () — shape () as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
warp_and_crop_face Not yet run
unverified (harvested, no recorded run)
fudan-generative-vision/hallo2/facelib/detection/align_trans.py
code served (permissive licence) · get_code("66ff1bbab2b2a672")
How it ran

no invocation recorded.

weighted_loss Not yet run
unverified (harvested, no recorded run)
fudan-generative-vision/hallo2/basicsr/losses/loss_util.py
code served (permissive licence) · get_code("cf63f8afc13f62a7")
How it ran

no invocation recorded.

Also present in other papers' code

Of 10 samples lifted from this paper's linked repositories, 10 carry a function identity and 0 do not. Of the 10 distinct functions with an identity, 7 are also present in other papers whose code we hold (7 with at least one paper dated earlier, 4 the same month, 4 later) and 3 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
get_position_from_periods 55 other papers
42 dated earlier, 2 the same month, 8 later, 3 same year, order not determinable
2110.04627 (2021-10)
Vector-quantized Image Modeling with Improved VQGAN
136790177 (2022 (year only))
Frequency and Spatial Dual Guidance for Image Dehazing
2204.04676 (2022-04)
Simple Baselines for Image Restoration
and 52 more not named here
weighted_loss 44 other papers
28 dated earlier, 2 the same month, 11 later, 3 same year, order not determinable
136790177 (2022 (year only))
Frequency and Spatial Dual Guidance for Image Dehazing
2203.14216 (2022-03)
Efficient and Degradation-Adaptive Network for Real-World Image Super-Resolution
2205.05996 (2022-05)
Blueprint Separable Residual Network for Efficient Image Super-Resolution
and 41 more not named here
reduce_loss 43 other papers
27 dated earlier, 2 the same month, 11 later, 3 same year, order not determinable
136790177 (2022 (year only))
Frequency and Spatial Dual Guidance for Image Dehazing
2203.14216 (2022-03)
Efficient and Degradation-Adaptive Network for Real-World Image Super-Resolution
2205.05996 (2022-05)
Blueprint Separable Residual Network for Efficient Image Super-Resolution
and 40 more not named here
weight_reduce_loss 43 other papers
28 dated earlier, 2 the same month, 10 later, 3 same year, order not determinable
136790177 (2022 (year only))
Frequency and Spatial Dual Guidance for Image Dehazing
2203.14216 (2022-03)
Efficient and Degradation-Adaptive Network for Real-World Image Super-Resolution
2205.05996 (2022-05)
Blueprint Separable Residual Network for Efficient Image Super-Resolution
and 40 more not named here
get_affine_transform_matrix 4 other papers
4 dated earlier
1804.07573 (2018-04)
MobileFaceNets: Efficient CNNs for Accurate Real-Time Face Verification on Mobile Devices
1908.09124 (2019-08)
SeesawFaceNets: sparse and robust face verification model for mobile platform
2008.00951 (2020-08)
Encoding in Style: a StyleGAN Encoder for Image-to-Image Translation
and 1 more not named here
tformfwd 4 other papers
4 dated earlier
1411.7923 (2014-11)
Learning Face Representation from Scratch
1804.07573 (2018-04)
MobileFaceNets: Efficient CNNs for Accurate Real-Time Face Verification on Mobile Devices
1908.09124 (2019-08)
SeesawFaceNets: sparse and robust face verification model for mobile platform
and 1 more not named here
tforminv 4 other papers
4 dated earlier
1411.7923 (2014-11)
Learning Face Representation from Scratch
1804.07573 (2018-04)
MobileFaceNets: Efficient CNNs for Accurate Real-Time Face Verification on Mobile Devices
1908.09124 (2019-08)
SeesawFaceNets: sparse and robust face verification model for mobile platform
and 1 more not named here

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Recent advances in latent diffusion-based generative models for portrait image animation, such as Hallo, have achieved impressive results in short-duration video synthesis. In this paper, we present updates to Hallo, introducing several design enhancements to extend its capabilities. First, we extend the method to produce long-duration videos. To address substantial challenges such as appearance drift and temporal artifacts, we investigate augmentation strategies within the image space of conditional motion frames. Specifically, we introduce a patch-drop technique augmented with Gaussian noise to enhance visual consistency and temporal coherence over long duration. Second, we achieve 4K resolution portrait video generation. To accomplish this, we implement vector quantization of latent codes and apply temporal alignment techniques to maintain coherence across the temporal dimension. By integrating a high-quality decoder, we realize visual synthesis at 4K resolution. Third, we incorporate adjustable semantic textual labels for portrait expressions as conditional inputs. This extends beyond traditional audio cues to improve controllability and increase the diversity of the generated content. To the best of our knowledge, Hallo2, proposed in this paper, is the first method to achieve 4K resolution and generate hour-long, audio-driven portrait image animations enhanced with textual prompts. We have conducted extensive experiments to evaluate our method on publicly available datasets, including HDTF, CelebV, and our introduced "Wild" dataset. The experimental results demonstrate that our approach achieves state-of-the-art performance in long-duration portrait video animation, successfully generating rich and controllable content at 4K resolution for duration extending up to tens of minutes. Project page https://fudan-generative-vision.github.io/hallo2

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2410.07718")
get_code_for_paper("2410.07718")
have("2410.07718")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2410.07718.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2410.07718.svg)](https://syntology.ai/paper/2410.07718)

Connect an agent — have() is free.