Papers › CtrLoRA: An Extensible and Efficient Framework for Controllable Image Generation

CtrLoRA: An Extensible and Efficient Framework for Controllable Image Generation

12 Oct 2024arXiv:2410.09400archive 2025-07-28

Yifeng Xu, Zhenliang He, Shiguang Shan, Xilin Chen

Recently, large-scale diffusion models have made impressive progress in text-to-image (T2I) generation. To further equip these T2I models with fine-grained spatial control, approaches like ControlNet introduce an extra network that learns to follow a condition image. However, for every single condition type, ControlNet requires independent training on millions of data pairs with hundreds of GPU hours, which is quite expensive and makes it challenging for ordinary users to explore and develop new types of conditions. To address this problem, we propose the CtrLoRA framework, which trains a Base ControlNet to learn the common knowledge of image-to-image generation from multiple base conditions, along with condition-specific LoRAs to capture distinct characteristics of each condition. Utilizing our pretrained Base ControlNet, users can easily adapt it to new conditions, requiring as few as 1,000 data pairs and less than one hour of single-GPU training to obtain satisfactory results in most scenarios. Moreover, our CtrLoRA reduces the learnable parameters by 90% compared to ControlNet, significantly lowering the threshold to distribute and deploy the model weights. Extensive experiments on various types of conditions demonstrate the efficiency and effectiveness of our method. Codes and model weights will be released at https://github.com/xyfJASON/ctrlora.

PaperPDFCodeCode Syntology ranMethod as code

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 22 code samples: 19 from 2 repositories linked to this paper, 3 identical to code harvested from another paper's repository. Across all 22: 13 ran (of which 6 constructed an object rather than computing a result; 10 with no instrument failure: 2 honoured, 1 violated, 7 with no contract checked; 3 where Syntology's instrument failed) · 9 unverified. Where Syntology's instrument failed: 3 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 16 samples from 1 repository, 9 ran (8 with no instrument failure; 1 where Syntology's instrument failed); community: 3 samples from 1 repository, 2 ran (1 with no instrument failure; 1 where Syntology's instrument failed); 3 identical to code first harvested elsewhere. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written between 2026-09-22 and 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 6 of the 13 samples that ran have no recorded date.

xyfjason/ctrlora officialmentioned in papermentioned on GitHubpytorchSyntology: 16 samples, 9 ran (1 instrument-failed) · 7 unverified report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

22 samples harvested: 13 ran (of which 6 constructed an object rather than computing a result; 10 with no instrument failure: 2 honoured, 1 violated, 7 with no contract checked; 3 where Syntology's instrument failed) · 9 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

2ran · honoured contract
1ran · violated contract
3ran · our draft was wrong
7ran
9unverified

Licence: 3 of the 22 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 2 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. 3 samples are listed last, in a group without a repository. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. For 4 samples that ran, the graph records a signature this page does not show: for a class the fixture built without calling, the harness called the object with inputs it made up itself, so the recorded signature is the harness's probe, not the fixture's arguments. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

xyfjason/ctrlora official repository 16 samples, 9 ran (1 instrument-failed) · 7 unverified
LoRACompatibleLinear cldm/cldm_ctrlora_inference.py ran Apache-2.0 (permissive) · 9da413a606c2fa21 · report fixture: returned LoRACompatibleLinear · level recorded 2026-09-22
LoRALinearLayer cldm/cldm_ctrlora_inference.py ran Apache-2.0 (permissive) · 902d1f89b0cf6904 · report fixture: returned LoRALinearLayer · level recorded 2026-09-22
MemoryEfficientCrossAttention in 7 papers cldm/cldm_ctrlora_inference.py ran Apache-2.0 (permissive) · f60e775a28631190 · report fixture: returned MemoryEfficientCrossAttention · level recorded 2026-09-22
QKVAttentionLegacy in 20 papers cldm/cldm_ctrlora_inference.py ran Apache-2.0 (permissive) · 0e10d815fe77258a · report fixture: signature qkv:Tensor/3/float · returned Tensor · level recorded 2026-09-24
SwitchableConv2d cldm/cldm_ctrlora_inference.py ran fingerprinted Apache-2.0 (permissive) · 1fc018a678b94a86 · report fixture: returned SwitchableConv2d · level recorded 2026-09-22
SwitchableGroupNorm cldm/cldm_ctrlora_inference.py ran fingerprinted Apache-2.0 (permissive) · 6be4fea6271b2108 · report fixture: returned SwitchableGroupNorm · level recorded 2026-09-22
SwitchableLayerNorm cldm/cldm_ctrlora_inference.py ran fingerprinted Apache-2.0 (permissive) · 2181071c92a4cce8 · report fixture: returned SwitchableLayerNorm · level recorded 2026-09-22
check_key app/gradio_ctrlora.py ran · violated contract Apache-2.0 (permissive) · 10ec89be27e3e44a · report fixture: signature k:str/0/str · returned bool · level recorded, date not recorded
get_config in 203 papers app/gradio_ctrlora.py ran · our draft was wrong Apache-2.0 (permissive) · 8450074c26c4e371 · report fixture: signature lora_ckpt:str/0/str, lora_num:int/0/int · returned str · level recorded, date not recorded
AttentionBlock in 69 papers cldm/cldm_ctrlora_inference.py unverified Apache-2.0 (permissive) · de2f868c40cb8ebe · report
BasicTransformerBlock in 22 papers cldm/cldm_ctrlora_inference.py unverified Apache-2.0 (permissive) · c02f4e63f9a3b275 · report
ControlNet cldm/cldm_ctrlora_inference.py unverified Apache-2.0 (permissive) · 9c1933018e1fe3c4 · report
ControlNetInference cldm/cldm_ctrlora_inference.py unverified Apache-2.0 (permissive) · 23aca6b588778459 · report
SpatialTransformer in 23 papers cldm/cldm_ctrlora_inference.py unverified Apache-2.0 (permissive) · df38578e601e8130 · report
TimestepEmbedSequential in 28 papers cldm/cldm_ctrlora_inference.py unverified Apache-2.0 (permissive) · b714f25e81b2ceff · report
cloneofsimo/lora community 3 samples, 2 ran (1 instrument-failed) · 1 unverified
inject_trainable_lora in 12 papers lora_diffusion/lora.py ran · our draft was wrong Apache-2.0 (permissive) · 4b4a8984a2737ae5 · report fixture: signature model:callable/0/?, target_replace_module:set/0/?, r:int/0/int, loras:NoneType/0/?, verbose:bool/0/bool, dropout_p:float/0/float, scale:float/0/float · returned tuple · level recorded, date not recorded
inject_trainable_lora_extended in 11 papers lora_diffusion/lora.py ran · honoured contract Apache-2.0 (permissive) · 3aec51ff694c19af · report fixture: signature model:callable/0/?, target_replace_module:set/0/?, r:int/0/int, loras:NoneType/0/? · returned tuple · level recorded, date not recorded
extract_lora_ups_down in 9 papers lora_diffusion/lora.py unverified Apache-2.0 (permissive) · 2f9880b526ff277e · report
Repository not located 3 samples, 2 ran (1 instrument-failed) · 1 unverified
3 samples are identical to code Syntology harvested from another paper's repository; this paper's own copy was not located, so no repository is named and no licence is recorded.
inject_trainable_lora in 12 papers repository not located ran · our draft was wrong licence of this copy not recorded · a1f6aab648f338b8 · report fixture: signature model:callable/0/?, target_replace_module:set/0/?, r:int/0/int, loras:NoneType/0/?, verbose:bool/0/bool, dropout_p:float/0/float, scale:float/0/float · returned tuple · level recorded, date not recorded
inject_trainable_lora_extended in 11 papers repository not located ran · honoured contract licence of this copy not recorded · 5ed08f9762be44ee · report fixture: signature model:callable/0/?, target_replace_module:set/0/?, r:int/0/int, loras:NoneType/0/? · returned tuple · level recorded, date not recorded
extract_lora_ups_down in 9 papers repository not located unverified licence of this copy not recorded · 33b1ae9f923ab3ec · report

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it.

1 assembly on this paper: 1 harvested, 0 generated.

harvested Assembly for CTRLORA (graph method: CTRLORA). 35 bricks; individually on a fixture: 23 ran (of which 13 constructed an object rather than computing a result; 17 with no instrument failure: 0 honoured, 2 violated, 15 with no contract checked; 6 where Syntology's instrument failed) · 12 unverified. The assembly has not been run end-to-end.

  1. ControlNetInference entry · level 0 · unverified · 23aca6b588778459
  2. ControlNet helper · level 0 · unverified · 9c1933018e1fe3c4
  3. LoRACompatibleLinear model · level 1 · ran · 9da413a606c2fa21
  4. LoRALinearLayer model · level 1 · ran · 902d1f89b0cf6904
  5. SwitchableConv2d helper · level 1 · ran · 1fc018a678b94a86
  6. SwitchableGroupNorm helper · level 1 · ran · 6be4fea6271b2108
  7. SwitchableLayerNorm helper · level 1 · ran · 2181071c92a4cce8
  8. timestep_embedding helper · level 1 · ran; the contract check could not run · 9df115707ad18735
  9. AttentionBlock helper · level 0 · unverified · de2f868c40cb8ebe
  10. Downsample helper · level 1 · ran · 0feab49c606075bb
  11. ResBlock helper · level 0 · unverified · dd3dd6c4cfa9bb05
  12. SpatialTransformer helper · level 0 · unverified · df38578e601e8130
  13. TimestepEmbedSequential helper · level 0 · unverified · b714f25e81b2ceff
  14. conv_nd helper · level 0 · unverified · fe4eb545bbb728e0
  15. exists helper · level 1 · ran · violated contract · aa5486a3650902d8
  16. linear helper · level 1 · ran · our draft was wrong · 0e30585f04efffbe
  17. zero_module helper · level 1 · ran · our draft was wrong · 129b804760b3115f
  18. QKVAttention helper · level 1 · ran · 941d1452fb38ca5e
  19. QKVAttentionLegacy helper · level 1 · ran · 0e10d815fe77258a
  20. checkpoint helper · level 0 · unverified · c596e50230fd9ed8
  21. normalization helper · level 1 · ran · our draft was wrong · daafc1c89511b8be
  22. avg_pool_nd helper · level 0 · unverified · ecd0fc28815b65ae
  23. TimestepBlock helper · level 0 · unverified · 7958a01675377ce4
  24. Upsample helper · level 1 · ran · 1b4579fe4aec5257
  25. BasicTransformerBlock helper · level 0 · unverified · c02f4e63f9a3b275
  26. Normalize helper · level 1 · ran · our draft was wrong · c3a6b977022957cb
  27. count_flops_attn helper · level 0 · unverified · 6e9c81a619f204c5
  28. CheckpointFunction helper · level 1 · ran · 70ec8e3dd3981b5e
  29. GroupNorm32 helper · level 1 · ran · 426c2385fa431d9a
  30. CrossAttention helper · level 1 · ran · 87dcf207c5c9187c
  31. FeedForward helper · level 1 · ran · 3abfca8077fe9d76
  32. MemoryEfficientCrossAttention helper · level 1 · ran · f60e775a28631190
  33. default helper · level 1 · ran · violated contract · 424012cb37b31172
  34. max_neg_value helper · level 1 · ran · our draft was wrong · f2fe51a4a5646c6f
  35. GEGLU helper · level 1 · ran · 387673fa5780bf50

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2410.09400") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Conditional Image GenerationImage Generation

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

BASEDiffusion

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections