Papers › Ingredients: Blending Custom Photos with Video Diffusion Transformers

Ingredients: Blending Custom Photos with Video Diffusion Transformers

3 Jan 2025arXiv:2501.01790archive 2025-07-28

Zhengcong Fei, Debang Li, Di Qiu, Changqian Yu, Mingyuan Fan

This paper presents a powerful framework to customize video creations by incorporating multiple specific identity (ID) photos, with video diffusion Transformers, referred to as \texttt{Ingredients}. Generally, our method consists of three primary modules: (\textbf{i}) a facial extractor that captures versatile and precise facial features for each human ID from both global and local perspectives; (\textbf{ii}) a multi-scale projector that maps face embeddings into the contextual space of image query in video diffusion transformers; (\textbf{iii}) an ID router that dynamically combines and allocates multiple ID embedding to the corresponding space-time regions. Leveraging a meticulously curated text-video dataset and a multi-stage training protocol, \texttt{Ingredients} demonstrates superior performance in turning custom photos into dynamic and personalized video content. Qualitative evaluations highlight the advantages of proposed method, positioning it as a significant advancement toward more effective generative video control tools in Transformer-based architecture, compared to existing methods. The data, code, and model weights are publicly available at: \url{https://github.com/feizc/Ingredients}.

PaperPDFCodeCode Syntology ran

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

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2501.01790")

Code

Syntology Ran 7 of 22 code samples harvested from 1 repository linked to this paper; 15 have no recorded run. Of those that ran: 2 ran · honoured contract; 2 ran · our draft was wrong; 1 ran · fixture could not drive it; 2 ran with no contract checked.

By repository: official repository: 22 samples from 1 repository, 7 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

feizc/ingredients officialmentioned in papermentioned on GitHubpytorchApache-2.0 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; 7 ran; 2 honoured the contract we drafted; 15 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

2ran · honoured contract
2ran · our draft was wrong
1ran · fixture could not drive it
2ran
15unverified

Licence: 0 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 feizc/ingredients. “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. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (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 from a repository marked official are listed first. 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 four 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; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). 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.

FeedForward feizc/ingredients/models/local_facial_extractor.py official repository ran · our draft was wrong Apache-2.0 (permissive) · 5105747c2711b1cb · report
conv1x1 feizc/ingredients/metric/curricularface/model_resnet.py official repository ran Apache-2.0 (permissive) · 85a6d411e524efe4 · report
conv3x3 feizc/ingredients/metric/curricularface/model_resnet.py official repository ran Apache-2.0 (permissive) · 6ccc5338f47a440c · report
get_block feizc/ingredients/metric/curricularface/model_irse.py official repository ran · honoured contract fingerprinted Apache-2.0 (permissive) · ad5dbf57f3ea2633 · report
get_blocks feizc/ingredients/metric/curricularface/model_irse.py official repository ran · honoured contract Apache-2.0 (permissive) · e82dfb7d2386721b · report
get_resize_crop_region_for_grid feizc/ingredients/models/pipeline_ingredients.py official repository ran · fixture could not drive it fingerprinted Apache-2.0 (permissive) · 734fd43f6aaef115 · report
retrieve_timesteps feizc/ingredients/models/pipeline_cogvideox.py official repository ran · our draft was wrong Apache-2.0 (permissive) · 22b1f260da28f6a5 · report
IR_18 feizc/ingredients/metric/curricularface/model_irse.py official repository unverified Apache-2.0 (permissive) · 42efa8d0cbd120d8 · report
ResNet_50 feizc/ingredients/metric/curricularface/model_resnet.py official repository unverified Apache-2.0 (permissive) · d6583b15d8a7722f · report
compute_clip_score feizc/ingredients/metric/clip_score.py official repository unverified Apache-2.0 (permissive) · 7b654be5a00e575f · report
compute_prompt_embeddings feizc/ingredients/models/utils.py official repository unverified Apache-2.0 (permissive) · 025423ed7b216773 · report
draw_kps feizc/ingredients/models/pipeline_ingredients.py official repository unverified Apache-2.0 (permissive) · 4ccfaec71f6cfcc8 · report
encode_prompt feizc/ingredients/models/utils.py official repository unverified Apache-2.0 (permissive) · 9ca4e9fb5eb8034d · report
get_face_keypoints feizc/ingredients/metric/face_sim_fid.py official repository unverified Apache-2.0 (permissive) · e185497b8158057e · report
get_model_config feizc/ingredients/models/eva_clip/factory.py official repository unverified Apache-2.0 (permissive) · 5c7cf820e99443ff · report
get_tokenizer feizc/ingredients/models/eva_clip/factory.py official repository unverified Apache-2.0 (permissive) · 9b7c99fcbb58f26f · report
load_image feizc/ingredients/metric/face_sim_fid.py official repository unverified Apache-2.0 (permissive) · 18703ab999a62c3e · report
load_state_dict feizc/ingredients/models/eva_clip/factory.py official repository unverified Apache-2.0 (permissive) · ab854bdad372c33e · report
process_image feizc/ingredients/models/pipeline_ingredients.py official repository unverified Apache-2.0 (permissive) · c17ad34b7b0cba0e · report
reshape_tensor feizc/ingredients/models/local_facial_extractor.py official repository unverified Apache-2.0 (permissive) · 4cb2e2a2ca0bec9f · report
sample_video_frames feizc/ingredients/metric/face_sim_fid.py official repository unverified Apache-2.0 (permissive) · 8d3e6b254561c7ec · report
tensor_to_pil feizc/ingredients/models/utils.py official repository unverified Apache-2.0 (permissive) · aabdf33f95d21edf · report

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Diffusion

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