SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2310.06313 · ICLR · 2024

Advancing Pose-Guided Image Synthesis with Progressive Conditional Diffusion Models

Wei Yang, Cong Wang, Jun Zhang, Fei Shen, Hu Ye, Xiao Han

arXiv · PDF · Open in the Atlas

Code that ran

10 of 11 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; 3 honoured the contract we drafted, 1 violated it and 0 have no contract verdict; 6 failures of our instrument; 1 no recorded run), measured 2026-11-22; 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/2310.06313.json · badge: /api/ran/2310.06313.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
tencent-ailab/PCDMs canonical (classifier label)
classifier basis: census
10 ran · 1 no recorded run
FunctionStatusWhere it lives
compare_l1 Ran
ran, honoured the contract we drafted
tencent-ailab/PCDMs/metrics.py
code served (permissive licence) · get_code("f8eeae62669a07ad")
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 float32, 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 numpy as np

# Create two distinct small image arrays for comparison
img_true = np.random.randint(0, 256, size=(2, 4, 3), dtype=np.uint8)
img_test = np.random.randint(0, 256, size=(2, 4, 3), dtype=np.uint8)

ARGS = {
    "img_true": img_true,
    "img_test": img_test,
}
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 float32, 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
compare_mae Ran
ran, violated the contract we drafted
tencent-ailab/PCDMs/metrics.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from YeshengSu/EdgeConnect, is pointer only (licence: NOASSERTION) · get_code("85ce775a2ab90703")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from YeshengSu/EdgeConnect, and GitHub could not classify the licence of that repository (NOASSERTION). 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.

count_model_params Ran
ran, honoured the contract we drafted
tencent-ailab/PCDMs/stage1_train_prior_model.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from muzishen/rcdms, is pointer only (licence: NONE) · get_code("4b208faf97544161")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from muzishen/rcdms, 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_image_list Ran
ran; our contract draft was wrong, not the code
tencent-ailab/PCDMs/metrics.py
code served (permissive licence) · get_code("b7231ccec461621e")
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 list, ndim 1, 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 os
import numpy as np
import glob
import tempfile

# Create a temporary directory with some test image files
temp_dir = tempfile.mkdtemp()
test_jpg = os.path.join(temp_dir, "test1.jpg")
test_png = os.path.join(temp_dir, "test2.png")
open(test_jpg, 'a').close()
open(test_png, 'a').close()

# Test case 1: passing a list directly
test_list = ["image1.jpg", "image2.png", "image3.jpg"]

ARGS = {
    "flist": test_list
}
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 list, ndim 1, dtype family float — a list 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
image_grid Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
tencent-ailab/PCDMs/stage2_batchtest_inpaint_model.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from thomas-wyh/fuseanypart, is pointer only (licence: NONE) · get_code("d2b9faa80b2570e4")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from thomas-wyh/fuseanypart, 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.

read_coordinates_file Ran
ran, honoured the contract we drafted
tencent-ailab/PCDMs/stage1_batchtest_prior_model.py
code served (permissive licence) · get_code("82d0673e4138da7c")
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 2, dtype family float, shape (1, 4) 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 tempfile
import os

torch.manual_seed(0)

# Create a temporary file with coordinate data
temp_file = tempfile.NamedTemporaryFile(mode='w', delete=False, suffix='.txt')
temp_file.write("1.5 2.3\n")
temp_file.write("3.7 4.2\n")
temp_file.close()

ARGS = {
    'file_path': temp_file.name
}
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 2, dtype family float, shape (1, 4) — shape (1, 4) 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
rescale_noise_cfg Ran
ran; our contract draft was wrong, not the code
tencent-ailab/PCDMs/src/pipelines/PCDMs_pipeline.py
code served (permissive licence) · get_code("bea2d776a332f2b0")
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) and returned Tensor, ndim 4, dtype family float, shape (2, 4, 3, 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 torch

torch.manual_seed(0)

# Create small tensors with distinct dimensions
# noise_cfg: shape (batch=2, channels=4, height=3, width=3)
noise_cfg = torch.randn(2, 4, 3, 3)

# noise_pred_text: shape (batch=2, channels=4, height=3, width=3)
noise_pred_text = torch.randn(2, 4, 3, 3)

# guidance_rescale: float between 0 and 1
guidance_rescale = 0.7

ARGS = {
    "noise_cfg": noise_cfg,
    "noise_pred_text": noise_pred_text,
    "guidance_rescale": guidance_rescale,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
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 4, dtype family float, shape (2, 4, 3, 3) — shape (2, 4, 3, 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
retrieve_timesteps Ran
ran; our contract draft was wrong, not the code
tencent-ailab/PCDMs/src/pipelines/PCDMs_pipeline.py
code served (permissive licence) · get_code("3338a5b299ea25ec")
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) and returned tuple. The image it ran in was not recorded. If your copy returns the same type 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 inspect
from typing import List, Optional, Union

torch.manual_seed(0)

# Create a minimal scheduler mock that satisfies the function's requirements
class MockScheduler:
    def __init__(self, supports_custom_timesteps=True):
        self.supports_custom_timesteps = supports_custom_timesteps
        self.timesteps = torch.tensor([999, 500, 250, 100, 50, 0], dtype=torch.long)
    
    def set_timesteps(self, num_inference_steps: Optional[int] = None, device: Optional[Union[str, torch.device]] = None, timesteps: Optional[List[int]] = None, **kwargs):
        if timesteps is not None:
            self.timesteps = torch.tensor(timesteps, dtype=torch.long)
            if device is not None:
                self.timesteps = self.timesteps.to(device)
        else:
            # Generate timesteps based on num_inference_steps
            if num_inference_steps is not None:
                self.timesteps = torch.linspace(999, 0, num_inference_steps, dtype=torch.long)
            if device is not None:
                self.timesteps = self.timesteps.to(device)

# Create scheduler instance
scheduler = MockScheduler(supports_custom_timesteps=True)

# Define arguments for the function
ARGS = {
    "scheduler": scheduler,
    "num_inference_steps": 6,
    "device": "cpu",
    "timesteps": None,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple — a tuple output has no array shape of its own; none is stated
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
split_list_into_chunks Ran
ran; our contract draft was wrong, not the code
tencent-ailab/PCDMs/stage1_batchtest_prior_model.py
code served (permissive licence) · get_code("652f1c8927e235d3")
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 list. The image it ran in was not recorded. If your copy returns the same type 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 numpy as np

# Analyze the function:
# - lst: needs to be a list-like object that supports len(), slicing with [i:i+chunk_size]
# - n: integer representing number of chunks
# The function splits a list into n chunks and handles remainder by extending last chunk

# Create a simple list for testing
test_list = [1, 2, 3, 4, 5, 6, 7, 8, 9, 10]
n_chunks = 3

ARGS = {
    "lst": test_list,
    "n": n_chunks
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type list — a list output has no array shape of its own; none is stated
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
zero_module Ran
ran; our contract draft was wrong, not the code
tencent-ailab/PCDMs/stage3_batchtest_refined_model.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from iguoyanjun/Memorize-When-Needed, is pointer only (licence: NONE) · get_code("d81381b327c76edd")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from iguoyanjun/Memorize-When-Needed, 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.

load_training_checkpoint Not yet run
unverified (harvested, no recorded run)
tencent-ailab/PCDMs/stage1_train_prior_model.py
code served (permissive licence) · get_code("d3e6b5403c89389e")
How it ran

no invocation recorded.

Also present in other papers' code

Of 11 samples lifted from this paper's linked repositories, 11 carry a function identity and 0 do not. Of the 11 distinct functions with an identity, 6 are also present in other papers whose code we hold (4 with at least one paper dated earlier, 2 the same month, 5 later) and 5 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
rescale_noise_cfg 62 other papers
3 dated earlier, 59 later
2206.02779 (2022-06)
Blended Latent Diffusion
2304.06720 (2023-04)
Expressive Text-to-Image Generation with Rich Text
2309.06380 (2023-09)
InstaFlow: One Step is Enough for High-Quality Diffusion-Based Text-to-Image Generation
and 59 more not named here
zero_module 40 other papers
3 dated earlier, 1 the same month, 36 later
2305.13077 (2023-05)
ControlVideo: Training-free Controllable Text-to-Video Generation
2305.17098 (2023-05)
ControlVideo: Conditional Control for One-shot Text-driven Video Editing and Beyond
2308.03448 (2023-08)
Make Explicit Calibration Implicit: Calibrate Denoiser Instead of the Noise Model
and 37 more not named here
retrieve_timesteps 21 other papers
21 later
2401.11708 (2024-01)
Mastering Text-to-Image Diffusion: Recaptioning, Planning, and Generating with Multimodal LLMs
2403.06976 (2024-03)
BrushNet: A Plug-and-Play Image Inpainting Model with Decomposed Dual-Branch Diffusion
2403.17924 (2024-03)
Attention Interpolation for Text-to-Image Diffusion
and 18 more not named here
image_grid 10 other papers
1 dated earlier, 2 the same month, 7 later
2303.17870 (2023-03)
GlyphDraw: Seamlessly Rendering Text with Intricate Spatial Structures in Text-to-Image Generation
2310.04816 (2023-10)
Hacking Generative Models with Differentiable Network Bending
2310.08129 (2023-10)
Tailored Visions: Enhancing Text-to-Image Generation with Personalized Prompt Rewriting
and 7 more not named here
compare_mae 1 other paper
1 dated earlier
1901.00212 (2019-01)
EdgeConnect: Generative Image Inpainting with Adversarial Edge Learning
count_model_params 1 other paper
1 later
2407.02482 (2024-07)
Boosting Consistency in Story Visualization with Rich-Contextual Conditional Diffusion Models

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 work has showcased the significant potential of diffusion models in poseguided person image synthesis. However, owing to the inconsistency in pose between the source and target images, synthesizing an image with a distinct pose, relying exclusively on the source image and target pose information, remains a formidable challenge. This paper presents Progressive Conditional Diffusion Models (PCDMs) that incrementally bridge the gap between person images under the target and source poses through three stages. Specifically, in the first stage, we design a simple prior conditional diffusion model that predicts the global features of the target image by mining the global alignment relationship between pose coordinates and image appearance. Then, the second stage establishes a dense correspondence between the source and target images using the global features from the previous stage, and an inpainting conditional diffusion model is proposed to further align and enhance the contextual features, generating a coarse-grained person image. In the third stage, we propose a refining conditional diffusion model to utilize the coarsely generated image from the previous stage as a condition, achieving texture restoration and enhancing fine-detail consistency. The three-stage PCDMs work progressively to generate the final high-quality and high-fidelity synthesized image. Both qualitative and quantitative results demonstrate the consistency and photorealism of our proposed PCDMs under challenging scenarios. The code and model will be available at https://github.com/tencent-ailab/PCDMs.

For agents

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

get_harvested_code_for_paper("2310.06313")
get_code_for_paper("2310.06313")
have("2310.06313")

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

curl https://syntology.ai/api/ran/2310.06313.json

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

[![Syntology run record](https://syntology.ai/api/ran/2310.06313.svg)](https://syntology.ai/paper/2310.06313)

Connect an agent — have() is free.