SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2401.05252 · 2024

PIXART-δ: Fast and Controllable Image Generation with Latent Consistency Models

arXiv · PDF · Open in the Atlas

Code that ran

5 of 5 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; 0 honoured the contract we drafted, 1 violated it and 0 have no contract verdict; 4 failures of our instrument; 0 no recorded run); 1 of them was also run on the host, not in the jail, by the peer-agreement lane that set its level, 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/2401.05252.json · badge: /api/ran/2401.05252.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
PixArt-alpha/PixArt-alpha canonical (classifier label)
classifier basis not recorded on the link
5 ran · 0 no recorded run
FunctionStatusWhere it lives
append_dims Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
PixArt-alpha/PixArt-alpha/train_scripts/train_pixart_lcm.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from layer6ai-labs/direct-cms, is pointer only (licence: NONE) · get_code("30befb7e4327e615")
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 layer6ai-labs/direct-cms, 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.

extract_into_tensor Ran
ran; our contract draft was wrong, not the code
PixArt-alpha/PixArt-alpha/train_scripts/train_pixart_lcm.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from Luo-Yihong/YOSO, is pointer only (licence: NONE) · get_code("a15cfd7932844ef9")
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 Luo-Yihong/YOSO, 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.

filter_keys Ran
ran; our contract draft was wrong, not the code
PixArt-alpha/PixArt-alpha/train_scripts/train_pixart_lcm_lora.py
code served (permissive licence) · get_code("d81c3ca69afe5db9")
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 function. 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

torch.manual_seed(0)

# Analyze the function:
# filter_keys takes a key_set parameter
# It returns a function _f that filters a dictionary
# key_set is used in: if k in key_set
# So key_set should be a set-like object (set, list, tuple, etc.)

# Create a simple key_set with some string keys
key_set = {'name', 'age', 'email'}

ARGS = {
    'key_set': key_set
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type function — a function output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a function output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not 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
scalings_for_boundary_conditions Ran
ran, violated the contract we drafted
PixArt-alpha/PixArt-alpha/train_scripts/train_pixart_lcm.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from Luo-Yihong/YOSO, is pointer only (licence: NONE) · get_code("bf8e9418920783fb")
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 Luo-Yihong/YOSO, 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.

text_encoder_lora_state_dict Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
PixArt-alpha/PixArt-alpha/train_scripts/train_pixart_lora_hf.py
code served (permissive licence) · get_code("4ed40bc152475f67")
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 dict. 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 torch.nn as nn
from transformers import CLIPTextModel

torch.manual_seed(0)

class LoRALinearLayer(nn.Module):
    def __init__(self, in_features, out_features):
        super().__init__()
        self.linear = nn.Linear(in_features, out_features)
    
    def state_dict(self, destination=None, prefix='', keep_vars=False):
        state = super().state_dict(destination, prefix, keep_vars)
        return state

class MockAttention(nn.Module):
    def __init__(self, hidden_size):
        super().__init__()
        self.q_proj = nn.Linear(hidden_size, hidden_size)
        self.k_proj = nn.Linear(hidden_size, hidden_size)
        self.v_proj = nn.Linear(hidden_size, hidden_size)
        self.out_proj = nn.Linear(hidden_size, hidden_size)
        
        # Add lora_linear_layer to each projection
        self.q_proj.lora_linear_layer = LoRALinearLayer(hidden_size, hidden_size)
        self.k_proj.lora_linear_layer = LoRALinearLayer(hidden_size, hidden_size)
        self.v_proj.lora_linear_layer = LoRALinearLayer(hidden_size, hidden_size)
        self.out_proj.lora_linear_layer = LoRALinearLayer(hidden_size, hidden_size)

class MockEncoderLayer(nn.Module):
    def __init__(self, hidden_size):
        super().__init__()
        self.self_attn = MockAttention(hidden_size)

class MockEncoder(nn.Module):
    def __init__(self, num_layers, hidden_size):
        super().__init__()
        self.layers = nn.ModuleList([
            MockEncoderLayer(hidden_size) for _ in range(num_layers)
        ])

class MockTextModel(nn.Module):
    def __init__(self, num_layers, hidden_size):
        super().__init__()
        self.encoder = MockEncoder(num_layers, hidden_size)

class MockCLIPTextEncoder(CLIPTextModel):
    def __init__(self, num_layers=2, hidden_size=4):
        # Initialize with minimal config
        from transformers import CLIPTextConfig
        config = CLIPTextConfig(
            vocab_size=1000,
            hidden_size=hidden_size,
            num_hidden_layers=num_layers,
            num_attention_heads=2,
            intermediate_size=8,
            max_position_embeddings=77,
        )
        super().__init__(config)
        # Replace text_model with our mock
        self.text_model = MockTextModel(num_layers, hidden_size)

text_encoder = MockCLIPTextEncoder(num_layers=2, hidden_size=4)

ARGS = {
    'text_encoder': text_encoder
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch, transformers — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not 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

Also present in other papers' code

Of 5 samples lifted from this paper's linked repositories, 5 carry a function identity and 0 do not. Of the 5 distinct functions with an identity, 5 are also present in other papers whose code we hold (4 with at least one paper dated earlier, 1 the same month, 5 later) and 0 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
extract_into_tensor 32 other papers
12 dated earlier, 1 the same month, 19 later · 7 only as an assembly brick
2006.11239 (2020-06)
Denoising Diffusion Probabilistic Models
2010.02502 (2020-10)
Denoising Diffusion Implicit Models
2112.02815 (2021-12)
Make It Move: Controllable Image-to-Video Generation with Text Descriptions
and 29 more not named here
append_dims 27 other papers
6 dated earlier, 19 later, 2 same year, order not determinable · 2 only as an assembly brick
2204.06125 (2022-04)
Hierarchical Text-Conditional Image Generation with CLIP Latents
2304.09787 (2023-04)
NeuralField-LDM: Scene Generation with Hierarchical Latent Diffusion Models
2307.12493 (2023-07)
TF-ICON: Diffusion-Based Training-Free Cross-Domain Image Composition
and 24 more not named here
filter_keys 4 other papers
2 dated earlier, 1 later, 1 same year, order not determinable
2310.04378 (2023-10)
Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inference
2311.05556 (2023-11)
LCM-LoRA: A Universal Stable-Diffusion Acceleration Module
01705 (2024 (year only))
Pixel-Aware Stable Diffusion for Realistic Image Super-Resolution and Personalized Stylization
and 1 more not named here
text_encoder_lora_state_dict 3 other papers
1 dated earlier, 2 later
2311.13600 (2023-11)
ZipLoRA: Any Subject in Any Style by Effectively Merging LoRAs
2403.14572 (2024-03)
Implicit Style-Content Separation using B-LoRA
2407.04604 (2024-07)
PartCraft: Crafting Creative Objects by Parts
scalings_for_boundary_conditions 2 other papers
2 later
2403.04692 (2024-03)
PixArt-Σ: Weak-to-Strong Training of Diffusion Transformer for 4K Text-to-Image Generation
2403.12931 (2024-03)
You Only Sample Once: Taming One-Step Text-To-Image Synthesis by Self-Cooperative Diffusion GANs

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

This technical report introduces PIXART-δ, a text-to-image synthesis framework that integrates the Latent Consistency Model (LCM) and ControlNet into the advanced PIXART-α model. PIXART-α is recognized for its ability to generate high-quality images of 1024px resolution through a remarkably efficient training process. The integration of LCM in PIXART-δ significantly accelerates the inference speed, enabling the production of high-quality images in just 2-4 steps. Notably, PIXART-δ achieves a breakthrough 0.5 seconds for generating 1024x1024 pixel images, marking a 7x improvement over the PIXART-α. Additionally, PIXART-δ is designed to be efficiently trainable on 32GB V100 GPUs within a single day. With its 8-bit inference capability (von Platen et al., 2023), PIXART-δ can synthesize 1024px images within 8GB GPU memory constraints, greatly enhancing its usability and accessibility. Furthermore, incorporating a ControlNet-like module enables fine-grained control over text-to-image diffusion models. We introduce a novel ControlNet-Transformer architecture, specifically tailored for Transformers, achieving explicit controllability alongside high-quality image generation. As a state-of-the-art, open-source image generation model, PIXART-δ offers a promising alternative to the Stable Diffusion family of models, contributing significantly to text-to-image synthesis.

For agents

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

get_harvested_code_for_paper("2401.05252")
get_code_for_paper("2401.05252")
have("2401.05252")

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

curl https://syntology.ai/api/ran/2401.05252.json

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

[![Syntology run record](https://syntology.ai/api/ran/2401.05252.svg)](https://syntology.ai/paper/2401.05252)

Connect an agent — have() is free.