{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/kandinsky-3-0-technical-report","title":"Kandinsky 3.0 Technical Report","arxiv_id":"2312.03511","date":"2023-12-06","proceeding":null,"authors":["Vladimir Arkhipkin","Andrei Filatov","Viacheslav Vasilev","Anastasia Maltseva","Said Azizov","Igor Pavlov","Julia Agafonova","Andrey Kuznetsov","Denis Dimitrov"],"abstract":"We present Kandinsky 3.0, a large-scale text-to-image generation model based on latent diffusion, continuing the series of text-to-image Kandinsky models and reflecting our progress to achieve higher quality and realism of image generation. In this report we describe the architecture of the model, the data collection procedure, the training technique, and the production system for user interaction. We focus on the key components that, as we have identified as a result of a large number of experiments, had the most significant impact on improving the quality of our model compared to the others. We also describe extensions and applications of our model, including super resolution, inpainting, image editing, image-to-video generation, and a distilled version of Kandinsky 3.0 - Kandinsky 3.1, which does inference in 4 steps of the reverse process and 20 times faster without visual quality decrease. By side-by-side human preferences comparison, Kandinsky becomes better in text understanding and works better on specific domains. The code is available at https://github.com/ai-forever/Kandinsky-3","url_abs":"https://arxiv.org/abs/2312.03511v3","url_pdf":"https://arxiv.org/pdf/2312.03511v3.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"kandinsky-3-0-technical-report","repo_url":"https://github.com/ai-forever/kandinsky-3","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"image-generation","task_name":"Image Generation"},{"task_slug":"image-to-video","task_name":"Image to Video Generation"},{"task_slug":"super-resolution","task_name":"Super-Resolution"},{"task_slug":"text-to-image-generation-1","task_name":"Text to Image Generation"},{"task_slug":"text-to-image-generation","task_name":"Text-to-Image Generation"},{"task_slug":"video-generation","task_name":"Video Generation"}],"methods":[{"method_slug":"concatenated-skip-connection","method_name":"Concatenated Skip Connection"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"diffusion","method_name":"Diffusion"},{"method_slug":"focus","method_name":"Focus"},{"method_slug":"max-pooling","method_name":"Max Pooling"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"u-net","method_name":"U-Net"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2312.03511","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.03511"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ai-forever/kandinsky-3","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":6,"ran_draft_wrong":1,"unverified":7},"by_repo_kind":{"official":{"samples":14,"ran":7,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"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"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"2d8424245424b7c2","entry":"exist","repo":"ai-forever/kandinsky-3","repo_kind":"official","path":"kandinsky3/model/utils.py","file_url":"https://github.com/ai-forever/kandinsky-3/blob/HEAD/kandinsky3/model/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"2d8424245424b7c2"}},{"code_sha256_prefix":"ffd1b5056434604b","entry":"freeze","repo":"ai-forever/kandinsky-3","repo_kind":"official","path":"kandinsky3/utils.py","file_url":"https://github.com/ai-forever/kandinsky-3/blob/HEAD/kandinsky3/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"ffd1b5056434604b"}},{"code_sha256_prefix":"8e74c767e9680cb0","entry":"get_named_beta_schedule","repo":"ai-forever/kandinsky-3","repo_kind":"official","path":"kandinsky3/model/diffusion.py","file_url":"https://github.com/ai-forever/kandinsky-3/blob/HEAD/kandinsky3/model/diffusion.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"8e74c767e9680cb0"}},{"code_sha256_prefix":"388d5db2e1f7c3e9","entry":"load_conf","repo":"ai-forever/kandinsky-3","repo_kind":"official","path":"kandinsky3/utils.py","file_url":"https://github.com/ai-forever/kandinsky-3/blob/HEAD/kandinsky3/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"388d5db2e1f7c3e9"}},{"code_sha256_prefix":"3137073275f8c21a","entry":"nonlinearity","repo":"ai-forever/kandinsky-3","repo_kind":"official","path":"kandinsky3/movq.py","file_url":"https://github.com/ai-forever/kandinsky-3/blob/HEAD/kandinsky3/movq.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"3137073275f8c21a"}},{"code_sha256_prefix":"5da5a9e348708c11","entry":"set_default_item","repo":"ai-forever/kandinsky-3","repo_kind":"official","path":"kandinsky3/model/utils.py","file_url":"https://github.com/ai-forever/kandinsky-3/blob/HEAD/kandinsky3/model/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"5da5a9e348708c11"}},{"code_sha256_prefix":"7831948ab4cf9cc6","entry":"unfreeze","repo":"ai-forever/kandinsky-3","repo_kind":"official","path":"kandinsky3/utils.py","file_url":"https://github.com/ai-forever/kandinsky-3/blob/HEAD/kandinsky3/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"7831948ab4cf9cc6"}},{"code_sha256_prefix":"700c2e349b1df086","entry":"Normalize","repo":"ai-forever/kandinsky-3","repo_kind":"official","path":"kandinsky3/movq.py","file_url":"https://github.com/ai-forever/kandinsky-3/blob/HEAD/kandinsky3/movq.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"700c2e349b1df086"}},{"code_sha256_prefix":"ca4dfe224d9a4907","entry":"get_condition_encoder","repo":"ai-forever/kandinsky-3","repo_kind":"official","path":"kandinsky3/condition_encoders.py","file_url":"https://github.com/ai-forever/kandinsky-3/blob/HEAD/kandinsky3/condition_encoders.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"ca4dfe224d9a4907"}},{"code_sha256_prefix":"3dd69ee6189ede78","entry":"get_control_unet","repo":"ai-forever/kandinsky-3","repo_kind":"official","path":"kandinsky3/model/unet.py","file_url":"https://github.com/ai-forever/kandinsky-3/blob/HEAD/kandinsky3/model/unet.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"3dd69ee6189ede78"}},{"code_sha256_prefix":"6dbb9a57dd16e905","entry":"get_diffusion","repo":"ai-forever/kandinsky-3","repo_kind":"official","path":"kandinsky3/model/diffusion.py","file_url":"https://github.com/ai-forever/kandinsky-3/blob/HEAD/kandinsky3/model/diffusion.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"6dbb9a57dd16e905"}},{"code_sha256_prefix":"17e5d0d0f10ae79f","entry":"get_unet","repo":"ai-forever/kandinsky-3","repo_kind":"official","path":"kandinsky3/model/unet.py","file_url":"https://github.com/ai-forever/kandinsky-3/blob/HEAD/kandinsky3/model/unet.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"17e5d0d0f10ae79f"}},{"code_sha256_prefix":"82ce8afeb1eb6757","entry":"get_vae","repo":"ai-forever/kandinsky-3","repo_kind":"official","path":"kandinsky3/movq.py","file_url":"https://github.com/ai-forever/kandinsky-3/blob/HEAD/kandinsky3/movq.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"82ce8afeb1eb6757"}},{"code_sha256_prefix":"325f8f5ac2f1d3a6","entry":"set_default_layer","repo":"ai-forever/kandinsky-3","repo_kind":"official","path":"kandinsky3/model/utils.py","file_url":"https://github.com/ai-forever/kandinsky-3/blob/HEAD/kandinsky3/model/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"325f8f5ac2f1d3a6"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}