SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1605.05396 · 2016

Generative Adversarial Text to Image Synthesis

arXiv · PDF · Open in the Atlas

Code that ran

15 of 19 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; 1 honoured the contract we drafted, 0 violated it and 6 have no contract verdict; 8 failures of our instrument; 4 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/1605.05396.json · badge: /api/ran/1605.05396.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
Abhis-123/TextToImage community (classifier label)
classifier basis: plan_row
7 ran · 0 no recorded run
DanielLongo/cGANs reimplementation (classifier label)
classifier basis: classifier_2025
4 ran · 0 no recorded run
dongdongdong666/CPGAN reimplementation (classifier label)
classifier basis: classifier_2025
2 ran · 0 no recorded run
priscillalui/StackGAN-Stories reimplementation (classifier label)
classifier basis: classifier_2025
1 ran · 0 no recorded run
copy not recorded community
not in the paper's declared repositories
1 ran · 0 no recorded run
itsayushthada/Text-To-Image community (classifier label)
classifier basis not recorded on the link
0 ran · 3 no recorded run
hanzhanggit/StackGAN-inception-model reimplementation (classifier label)
classifier basis: classifier_2025
0 ran · 1 no recorded run
FunctionStatusWhere it lives
Block3x3_relu Ran
ran; our contract draft was wrong, not the code
priscillalui/StackGAN-Stories/code/model.py
code served (permissive licence) · get_code("90b28e5e76aecfad")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Sonnet 4.5, prompt python_fixture_v1) and returned Sequential. 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
import torch.nn.functional as F

torch.manual_seed(0)

class GLU(nn.Module):
    def __init__(self):
        super(GLU, self).__init__()

    def forward(self, x):
        nc = x.size(1)
        assert nc % 2 == 0, 'channels dont divide 2!'
        nc = int(nc / 2)
        return x[:, :nc] * F.sigmoid(x[:, nc:])

def conv3x3(in_planes, out_planes):
    """3x3 convolution with padding"""
    return nn.Conv2d(in_planes, out_planes, kernel_size=3, stride=1, padding=1, bias=False)

def Block3x3_relu(in_planes, out_planes):
    block = nn.Sequential(conv3x3(in_planes, out_planes * 2), nn.BatchNorm2d(out_planes * 2), GLU())
    return block

ARGS = {
    'in_planes': 3,
    'out_planes': 5
}
Setup block drafted by
a language model, Claude Sonnet 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 Sequential — a Sequential output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Sequential output the recorded ndim 1 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
Block3x3_relu Ran
ran on a synthesized input
Abhis-123/TextToImage/stackgan/utils/from_original.py
code served (permissive licence) · get_code("2bbce63d639e9cfe")
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 Sequential. 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

torch.manual_seed(0)

ARGS = {
    'in_planes': 3,
    'out_planes': 4,
}
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 Sequential — a Sequential output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Sequential output the recorded ndim 1 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
Conv2dCongruent Ran
ran on a synthesized input
Abhis-123/TextToImage/stackgan/utils/blocks.py
code served (permissive licence) · get_code("0b7e6680747be066")
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 Conv2d. 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

torch.manual_seed(0)

ARGS = {
    'in_channels': 3,
    'out_channels': 16,
    'kernel_size': 3,
    'bias': False
}
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 Conv2d — a Conv2d output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Conv2d 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
JoinBlock Ran
ran on a synthesized input
Abhis-123/TextToImage/stackgan/utils/blocks.py
code served (permissive licence) · get_code("aa85d37a12bbf4cd")
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 Sequential. 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

torch.manual_seed(0)

ARGS = {
    "in_channels": 16,
    "cond_dim": 8,
}
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 Sequential — a Sequential output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Sequential output the recorded ndim 1 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
UpsamplingBlock Ran
ran on a synthesized input
Abhis-123/TextToImage/stackgan/utils/blocks.py
code served (permissive licence) · get_code("6887d29e55f2f670")
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 Sequential. 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

torch.manual_seed(0)

ARGS = {
    'in_channels': 3,
    'out_channels': 64,
    'kernel_size': 3,
}
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 Sequential — a Sequential output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Sequential output the recorded ndim 1 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
conv1x1 Ran
ran; our contract draft was wrong, not the code
this paper's copy was not recorded; identical code first harvested from alexmotogna/attngan
pointer only · get_code("19379807ba70daaa")
How it ran

The body of this sample is withheld: this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it. 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.

conv3x3 Ran
ran; our contract draft was wrong, not the code
Abhis-123/TextToImage/stackgan/utils/from_original.py
code served (permissive licence) · get_code("ea864de5c552bc4a")
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 Conv2d. 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

torch.manual_seed(0)

ARGS = {
    "in_planes": 3,
    "out_planes": 64,
}
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 Conv2d — a Conv2d output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Conv2d 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
cosine_similarity Ran
ran; our contract draft was wrong, not the code
dongdongdong666/CPGAN/evaluation/caculate_R_precison.py
code served (permissive licence) · get_code("e0c14774d8283a63")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Sonnet 4.5, prompt python_fixture_v1) and returned Tensor, ndim 1, dtype family float, shape (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 torch

torch.manual_seed(0)

# Create two tensors with distinct shapes for testing cosine similarity
# x1 and x2 should have the same shape for element-wise multiplication
# Using batch size 2, feature dimension 4
x1 = torch.randn(2, 4)
x2 = torch.randn(2, 4)

# dim=1 means we compute similarity along dimension 1 (the feature dimension)
# eps is a small value to prevent division by zero

ARGS = {
    'x1': x1,
    'x2': x2,
    'dim': 1,
    'eps': 1e-08
}
Setup block drafted by
a language model, Claude Sonnet 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 1, dtype family float, shape (2,) — shape (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
create_optimizer Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
DanielLongo/cGANs/DCGAN.py
pointer only (licence: NONE) · get_code("1260620e5bfe1614")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, DanielLongo/cGANs 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.

discriminator_loss Ran
ran; our contract draft was wrong, not the code
DanielLongo/cGANs/cDCGAN.py
pointer only (licence: NONE) · get_code("8d99aaa30d71b315")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, DanielLongo/cGANs 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.

generate_nosie Ran
ran, honoured the contract we drafted
DanielLongo/cGANs/DCGAN.py
pointer only (licence: NONE) · get_code("edd684c8d7918d6a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, DanielLongo/cGANs 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.

process_text Ran
ran on a synthesized input
Abhis-123/TextToImage/datasets.py
code served (permissive licence) · get_code("ca07d7ef0a1b5440")
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 (70, 201) 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)

# The function takes a single parameter: text
# Looking at the function body:
# - text is iterated over with "for tok in text"
# - each tok is used with alphabet.index(tok)
# - text length is checked with len(text)
# So text should be a string or sequence of characters from the alphabet

alphabet = 'abcdefghijklmnopqrstuvwxyz0123456789-,;.!?:\'"/\\|_@#$%^&*~`+-=<>()[]{} '

# Create a valid text string using characters from the alphabet
text = "hello world!"

ARGS = {
    "text": text
}
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 (70, 201) — shape (70, 201) 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
train_gan Ran
ran on a synthesized input
DanielLongo/cGANs/DCGAN.py
pointer only (licence: NONE) · get_code("2fb479c48e65d7b4")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, DanielLongo/cGANs 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.

upBlock Ran
ran; our contract draft was wrong, not the code
dongdongdong666/CPGAN/code/model.py
code served (permissive licence) · get_code("c96308e17ab1e7ae")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Sonnet 4.5, prompt python_fixture_v1) and returned Sequential. 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

torch.manual_seed(0)

# upBlock takes in_planes and out_planes as parameters
# It creates a sequential block with:
# 1. Upsample (scale_factor=2)
# 2. conv3x3 (in_planes -> out_planes * 2)
# 3. BatchNorm2d (out_planes * 2)
# 4. GLU (which divides channels by 2, so out_planes * 2 -> out_planes)

in_planes = 8
out_planes = 4

ARGS = {
    'in_planes': in_planes,
    'out_planes': out_planes
}
Setup block drafted by
a language model, Claude Sonnet 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 Sequential — a Sequential output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Sequential output the recorded ndim 1 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
upBlock Ran
ran; our contract draft was wrong, not the code
Abhis-123/TextToImage/stackgan/utils/from_original.py
code served (permissive licence) · get_code("6467935a6cd80074")
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 Sequential. 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

torch.manual_seed(0)

# upBlock takes in_planes and out_planes as parameters
# in_planes: number of input channels
# out_planes: number of output channels

# The function creates a Sequential module with:
# 1. Upsample layer
# 2. conv3x3 layer: takes in_planes input channels, outputs out_planes * 2 channels
# 3. BatchNorm2d layer: normalizes out_planes * 2 channels
# 4. GLU layer: expects even number of channels (out_planes * 2), outputs out_planes channels

ARGS = {
    "in_planes": 4,
    "out_planes": 3,
}
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 Sequential — a Sequential output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Sequential output the recorded ndim 1 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
encode Not yet run
unverified (harvested, no recorded run)
itsayushthada/Text-To-Image/skipthoughts.py
code served (permissive licence) · get_code("2d06283b04889970")
How it ran

no invocation recorded.

preprocess Not yet run
unverified (harvested, no recorded run)
hanzhanggit/StackGAN-inception-model/inception_score.py
pointer only (licence: NONE) · get_code("b85a728ed7aaaade")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, hanzhanggit/StackGAN-inception-model 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. No invocation recorded.

preprocess Not yet run
unverified (harvested, no recorded run)
itsayushthada/Text-To-Image/skipthoughts.py
code served (permissive licence) · get_code("6f1052a5fada2e72")
How it ran

no invocation recorded.

word_features Not yet run
unverified (harvested, no recorded run)
itsayushthada/Text-To-Image/skipthoughts.py
code served (permissive licence) · get_code("fca1315be1d730a4")
How it ran

no invocation recorded.

Also present in other papers' code

Of 19 samples lifted from this paper's linked repositories, 19 carry a function identity and 0 do not. Of the 17 distinct functions with an identity, 10 are also present in other papers whose code we hold (3 with at least one paper dated earlier, 0 the same month, 10 later) and 7 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
conv1x1 8 other papers
1 dated earlier, 7 later · 3 only as an assembly brick
1511.06434 (2015-11)
Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
1711.10485 (2017-11)
AttnGAN: Fine-Grained Text to Image Generation with Attentional Generative Adversarial Networks
1802.06474 (2018-02)
A Closed-form Solution to Photorealistic Image Stylization
and 5 more not named here
conv3x3 6 other papers
1 dated earlier, 5 later · 1 only as an assembly brick
1511.06434 (2015-11)
Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
1710.10916 (2017-10)
StackGAN++: Realistic Image Synthesis with Stacked Generative Adversarial Networks
1711.10485 (2017-11)
AttnGAN: Fine-Grained Text to Image Generation with Attentional Generative Adversarial Networks
and 3 more not named here
upBlock 6 other papers
1 dated earlier, 5 later
1511.06434 (2015-11)
Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
1710.10916 (2017-10)
StackGAN++: Realistic Image Synthesis with Stacked Generative Adversarial Networks
1711.10485 (2017-11)
AttnGAN: Fine-Grained Text to Image Generation with Attentional Generative Adversarial Networks
and 3 more not named here
cosine_similarity 2 other papers
2 later
1802.06474 (2018-02)
A Closed-form Solution to Photorealistic Image Stylization
1910.13321 (2019-10)
Semantic Object Accuracy for Generative Text-to-Image Synthesis
preprocess 2 other papers
2 later
1612.03242 (2016-12)
StackGAN: Text to Photo-realistic Image Synthesis with Stacked Generative Adversarial Networks
1904.01310 (2019-04)
DM-GAN: Dynamic Memory Generative Adversarial Networks for Text-to-Image Synthesis
Block3x3_relu 1 other paper
1 later
1710.10916 (2017-10)
StackGAN++: Realistic Image Synthesis with Stacked Generative Adversarial Networks
create_optimizer 1 other paper
1 later
1802.05637 (2018-02)
cGANs with Projection Discriminator
discriminator_loss 1 other paper
1 later
1802.05637 (2018-02)
cGANs with Projection Discriminator
generate_nosie 1 other paper
1 later
1802.05637 (2018-02)
cGANs with Projection Discriminator
train_gan 1 other paper
1 later
1802.05637 (2018-02)
cGANs with Projection Discriminator

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

More are linked than shown here.

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

Abstract

Automatic synthesis of realistic images from text would be interesting and useful, but current AI systems are still far from this goal. However, in recent years generic and powerful recurrent neural network architectures have been developed to learn discriminative text feature representations. Meanwhile, deep convolutional generative adversarial networks (GANs) have begun to generate highly compelling images of specific categories, such as faces, album covers, and room interiors. In this work, we develop a novel deep architecture and GAN formulation to effectively bridge these advances in text and image model- ing, translating visual concepts from characters to pixels. We demonstrate the capability of our model to generate plausible images of birds and flowers from detailed text descriptions.

For agents

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

get_harvested_code_for_paper("1605.05396")
get_code_for_paper("1605.05396")
have("1605.05396")

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

curl https://syntology.ai/api/ran/1605.05396.json

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

[![Syntology run record](https://syntology.ai/api/ran/1605.05396.svg)](https://syntology.ai/paper/1605.05396)

Connect an agent — have() is free.