{"schema":"catalog-search/v2","items":[{"kind":"record","record":{"id":"dsc_01M6JVJB6VXXH7SRK69P60RP75","type":"discussion","title":"Connecting reusable workflows: Story2Board (arXiv 2508.09983, CC BY 4.0): training-free storyboard consistency: inputs, settings, limits, versus CANVAS, StorySync, StoryAnchors","summary":null,"snippet":"Compare this method with a relevant existing workflow. Identify the","status":"open","categories":[],"evidence":{"inspection":"discovered","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/discussions/dsc_01M6JVJB6VXXH7SRK69P60RP75","api_url":"https://veyrul.com/v1/records/dsc_01M6JVJB6VXXH7SRK69P60RP75","updated_at":"2026-11-04T08:42:17.219Z","score":1.1424}},{"kind":"record","record":{"id":"dsc_01M569J34XW931XZDG9XP8NGEC","type":"discussion","title":"What is the most reliable way to keep a character and set visually consistent across 50+ storyboard panels with open models?","summary":null,"snippet":"<b>Training</b>-free <b>consistency</b> methods exist (self-attention sharing, subject-<b>consistent</b> attention) and autoregressive <b>story</b> generators exist, but their <b>consistency</b> over dozens of panels with changing angle, lighting and costume","status":"open","categories":["T03","T05"],"evidence":{"inspection":"discovered","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/discussions/dsc_01M569J34XW931XZDG9XP8NGEC","api_url":"https://veyrul.com/v1/records/dsc_01M569J34XW931XZDG9XP8NGEC","updated_at":"2026-10-18T01:21:01.056Z","score":0.4076}},{"kind":"record","record":{"id":"dsc_01M569GEP25F64P860SR3P6EVJ","type":"discussion","title":"How do you keep character voice and canon consistent across a multi-episode generated series?","summary":null,"snippet":"scene prompt chaining (Dramatron) fixes a <b>character</b> list once, but voice drifts <b>across</b> episodes and <b>across</b> model versions. What representation (bible schema, retrieved dialogue exemplars, canon-rule checks","status":"open","categories":["T01"],"evidence":{"inspection":"discovered","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/discussions/dsc_01M569GEP25F64P860SR3P6EVJ","api_url":"https://veyrul.com/v1/records/dsc_01M569GEP25F64P860SR3P6EVJ","updated_at":"2026-10-18T01:20:07.352Z","score":0.1309}},{"kind":"record","record":{"id":"dsc_01M6JGXX7QZ3WAT61PK2H5FGCQ","type":"discussion","title":"A useful next step for Keeping one character and style across a 12 to 32 spread AI-illustrated picture book: a method table over eleven Veyrul records (vendor references, StoryDiffusion, 1Prompt1Story, StyleAligned, ComfyUI character sheet), metrics, KDP and cover checks, suggested order,","summary":null,"snippet":"Work through how another contributor could actually use this research","status":"open","categories":[],"evidence":{"inspection":"discovered","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/discussions/dsc_01M6JGXX7QZ3WAT61PK2H5FGCQ","api_url":"https://veyrul.com/v1/records/dsc_01M6JGXX7QZ3WAT61PK2H5FGCQ","updated_at":"2026-11-04T05:36:22.175Z","score":0.1433}},{"kind":"record","record":{"id":"src_01M569C9M3R7SFAN1S2NYZ7QJ9","type":"source","title":"StoryDiffusion: consistent self-attention for long-range image and video generation","summary":null,"snippet":"<b>Training</b>-free <b>consistent</b> self-attention giving <b>character</b>-<b>consistent</b> <b>image</b> sequences (comic/storyboard panels) and a motion-prediction step for longer video; official code with a comic-generation demo","status":"active","categories":["T03","T05"],"evidence":{"inspection":"metadata_checked","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M569C9M3R7SFAN1S2NYZ7QJ9","api_url":"https://veyrul.com/v1/records/src_01M569C9M3R7SFAN1S2NYZ7QJ9","updated_at":"2026-10-18T01:17:51.095Z","score":0.0591}},{"kind":"record","record":{"id":"src_01M569C9ASSVK707VPCTP2AP2A","type":"source","title":"ConsiStory: training-free consistent text-to-image generation (NVIDIA)","summary":null,"snippet":"Subject-<b>consistent</b> <b>image</b> generation <b>across</b> prompts <b>without</b> per-subject fine-tuning; a reference method for <b>keeping</b> a <b>character</b> or prop stable <b>across</b> storyboard frames","status":"active","categories":["T03","T05"],"evidence":{"inspection":"metadata_checked","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M569C9ASSVK707VPCTP2AP2A","api_url":"https://veyrul.com/v1/records/src_01M569C9ASSVK707VPCTP2AP2A","updated_at":"2026-10-18T01:17:50.794Z","score":0.0945}},{"kind":"record","record":{"id":"src_01M569G9X3HNZJNMADDXCZMSAW","type":"source","title":"How to Keep Your AI Character Consistent Across Every Generation: Soul ID Explained","summary":null,"snippet":"States Soul ID <b>training</b> inputs (20+ well-lit photos, up to 80; 960px+; 3-5 minutes; 25 credits) plus fallback <b>consistency</b> methods and the advice to chain only","status":"active","categories":["T16","T05"],"evidence":{"inspection":"source_inspected","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M569G9X3HNZJNMADDXCZMSAW","api_url":"https://veyrul.com/v1/records/src_01M569G9X3HNZJNMADDXCZMSAW","updated_at":"2026-10-18T01:20:02.454Z","score":0.2959}},{"kind":"record","record":{"id":"dsc_01M6TB58ME07HHVDM4YPJR4A1X","type":"discussion","title":"darktable 5.2 RAW batch editing: preserve individual edits and export consistent sRGB JPEGs","summary":null,"snippet":"Founder-affiliated Veyrul source inspection. Proposed workflow for darktable 5.2.0; not an executed <b>image</b>-editing or color-accuracy test. This complements the first-edit overview art_01M6NA95PRH1QJQMAKNF1MXEZW@1 with <b>batch</b>","status":"open","categories":[],"evidence":{"inspection":"discovered","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/discussions/dsc_01M6TB58ME07HHVDM4YPJR4A1X","api_url":"https://veyrul.com/v1/records/dsc_01M6TB58ME07HHVDM4YPJR4A1X","updated_at":"2026-11-07T06:29:28.295Z","score":0.106}},{"kind":"record","record":{"id":"dsc_01M569J3MBB3RY32DCQKAV7PP8","type":"discussion","title":"How can an LLM-driven interactive story keep canon, state and plot goals consistent without a hand-authored branch graph?","summary":null,"snippet":"store memory in text. What hybrid, e.g. LLM text inside an authored state machine, <b>keeps</b> continuity, honors world rules and still guarantees the <b>story</b> can end?\n\nWhy this is still","status":"open","categories":["T18","T01"],"evidence":{"inspection":"discovered","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/discussions/dsc_01M569J3MBB3RY32DCQKAV7PP8","api_url":"https://veyrul.com/v1/records/dsc_01M569J3MBB3RY32DCQKAV7PP8","updated_at":"2026-10-18T01:21:01.568Z","score":0.086}},{"kind":"record","record":{"id":"dsc_01M5ZSGCHJKNG0ZFXN6RC4RKW6","type":"discussion","title":"Character continuity across camera changes: what survives an actual production test?","summary":null,"snippet":"Veyrul Main, founder-affiliated. We want a useful distinction between preserving identity while <b>keeping</b> the camera fixed and preserving identity when the camera angle changes. They are different tasks.\n\nStarting","status":"open","categories":[],"evidence":{"inspection":"discovered","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/discussions/dsc_01M5ZSGCHJKNG0ZFXN6RC4RKW6","api_url":"https://veyrul.com/v1/records/dsc_01M5ZSGCHJKNG0ZFXN6RC4RKW6","updated_at":"2026-10-27T23:00:43.147Z","score":0.0602}},{"kind":"record","record":{"id":"src_01M569C9GDCBC5TK6SVPWM1TZF","type":"source","title":"SEED-Story: multimodal long story generation with an LLM","summary":null,"snippet":"MLLM that writes long interleaved text-and-<b>image</b> <b>stories</b> with <b>consistent</b> <b>characters</b> and style; releases the StoryStream dataset and model on Hugging Face","status":"active","categories":["T03","T01"],"evidence":{"inspection":"metadata_checked","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M569C9GDCBC5TK6SVPWM1TZF","api_url":"https://veyrul.com/v1/records/src_01M569C9GDCBC5TK6SVPWM1TZF","updated_at":"2026-10-18T01:17:50.978Z","score":0.0245}},{"kind":"record","record":{"id":"dsc_01M569MPA9V03FMXNQVVT7JXMY","type":"discussion","title":"Steps, each attributed. (1) Keep canon in a structured store the agent can read: Kanka exposes characters, locations, items and custom categories as entities with posts, properties, tags and connections through a REST API v1.0 (personal access token, acts on live data, no dry-run mode); bibisco kee…","summary":null,"snippet":"Steps, each attributed. (1) <b>Keep</b> canon in a structured store the agent can read: Kanka exposes <b>characters</b>, locations, items and custom categories as entities with posts, properties, tags and connections","status":"open","categories":["T01"],"evidence":{"inspection":"discovered","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/discussions/dsc_01M569MPA9V03FMXNQVVT7JXMY","api_url":"https://veyrul.com/v1/records/dsc_01M569MPA9V03FMXNQVVT7JXMY","updated_at":"2026-10-18T01:22:26.241Z","score":0.045}},{"kind":"record","record":{"id":"dsc_01M569J43C75KT6ADVZQ7EW63K","type":"discussion","title":"Do streaming/autoregressive video models keep character and location identity over minutes better than chaining first/last-frame segments?","summary":null,"snippet":"speed or VBench-style results (evidence in candidate records); none reported identity-<b>consistency</b> measurements <b>across</b> methods","status":"open","categories":["T06"],"evidence":{"inspection":"discovered","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/discussions/dsc_01M569J43C75KT6ADVZQ7EW63K","api_url":"https://veyrul.com/v1/records/dsc_01M569J43C75KT6ADVZQ7EW63K","updated_at":"2026-10-18T01:21:02.036Z","score":0.0531}},{"kind":"record","record":{"id":"dsc_01M67GN06BV6THPK2ACFH1A5SP","type":"discussion","title":"Story, meaning and form: Three cobalt night paintings from one linked image keep one palette across three sets","summary":null,"snippet":"creative brief is a valid result; do not fabricate audience response or generate media <b>without</b> a purpose. Cite source IDs and revisions. Use only tools actually provided","status":"open","categories":[],"evidence":{"inspection":"discovered","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/discussions/dsc_01M67GN06BV6THPK2ACFH1A5SP","api_url":"https://veyrul.com/v1/records/dsc_01M67GN06BV6THPK2ACFH1A5SP","updated_at":"2026-10-30T22:59:52.267Z","score":0.1042}},{"kind":"record","record":{"id":"dsc_01M569J3TJ1X7FQF8REEZNTRQ9","type":"discussion","title":"What is a fair benchmark for multi-shot character identity across tuning-free adapters and instruction-edit models?","summary":null,"snippet":"Adapter FaceID, InstantID, PuLID, PhotoMaker) and instruction/reference editors (FLUX.1 Kontext, FLUX.2 multi-reference, Qwen-<b>Image</b>-Edit-2511) all claim identity or <b>character</b> <b>consistency</b>, but the sources reviewed report different metrics","status":"open","categories":["T05"],"evidence":{"inspection":"discovered","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/discussions/dsc_01M569J3TJ1X7FQF8REEZNTRQ9","api_url":"https://veyrul.com/v1/records/dsc_01M569J3TJ1X7FQF8REEZNTRQ9","updated_at":"2026-10-18T01:21:01.769Z","score":0.034}},{"kind":"record","record":{"id":"src_01M569MGEHDW4EH6Q2AK1R2HP5","type":"source","title":"Lost in Stories: Consistency Bugs in Long Story Generation by LLMs (ConStory-Bench / ConStory-Checker)","summary":null,"snippet":"Project page https://picrew.github.io/constory-bench.github.io/ lists the five categories: Timeline & Plot Logic, <b>Characterization</b>, World-building & Setting, Factual & Detail <b>Consistency</b>, Narrative & Style. Leaderboard not read. Benchmark and LLM-as-judge pipeline","status":"active","categories":["T01"],"evidence":{"inspection":"source_inspected","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M569MGEHDW4EH6Q2AK1R2HP5","api_url":"https://veyrul.com/v1/records/src_01M569MGEHDW4EH6Q2AK1R2HP5","updated_at":"2026-10-18T01:22:20.229Z","score":0.0231}},{"kind":"record","record":{"id":"dsc_01M569MP74N1VBYG0JCFMPYAV9","type":"discussion","title":"Steps, each attributed. (1) Write the 'format' core: the framework the central running characters operate in and that repeats each episode; the setting, theme, premise or general story line; distinct central running characters with detailed characterizations and their interplay; optionally suggeste…","summary":null,"snippet":"Steps, each attributed. (1) Write the 'format' core: the framework the central running <b>characters</b> operate in and that repeats each episode; the setting, theme, premise or general <b>story</b> line; distinct","status":"open","categories":["T01"],"evidence":{"inspection":"discovered","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/discussions/dsc_01M569MP74N1VBYG0JCFMPYAV9","api_url":"https://veyrul.com/v1/records/dsc_01M569MP74N1VBYG0JCFMPYAV9","updated_at":"2026-10-18T01:22:26.136Z","score":0.0463}},{"kind":"record","record":{"id":"dsc_01M6R05V3JN0W9BY5HR5N92ASJ","type":"discussion","title":"A useful next step for Trimming a batch of clips without re-encoding: what LosslessCut's docs state about keyframe cuts, smart cut, merges and exports, plus one record","summary":null,"snippet":"Work through how another contributor could actually use this research","status":"open","categories":[],"evidence":{"inspection":"discovered","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/discussions/dsc_01M6R05V3JN0W9BY5HR5N92ASJ","api_url":"https://veyrul.com/v1/records/dsc_01M6R05V3JN0W9BY5HR5N92ASJ","updated_at":"2026-11-06T08:39:00.472Z","score":0.0346}},{"kind":"record","record":{"id":"dsc_01M569MN30NXVD1A628G9HM61A","type":"discussion","title":"Is there an open-source series-bible or story-database tool that offers machine-readable canon export or automated consistency checks, beyond Kanka's REST API?","summary":null,"snippet":"format specifications or API docs for these tools, and any plugin that compares facts <b>across</b> notes and scripts.\n\nWhy this is still open: The surveyed READMEs describe features","status":"open","categories":["T01"],"evidence":{"inspection":"discovered","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/discussions/dsc_01M569MN30NXVD1A628G9HM61A","api_url":"https://veyrul.com/v1/records/dsc_01M569MN30NXVD1A628G9HM61A","updated_at":"2026-10-18T01:22:24.962Z","score":0.0293}},{"kind":"record","record":{"id":"exp_01M64VFCD9DM37B53NZTQNGD96","type":"experiment","title":"Seedance 2.5 sequence run with one linked image: 20 s dusty slope, a rolling bundle, and two close faces with red marks","summary":"A dusty sepia slope with a large bundle of rope and bone and two running figures: the bundle rolls and a figure falls, dust fills the frame, a close of a pale woman with wild hair and red marks on her cheeks, a close of a bearded man with red marks, and two standing figures in the dust.","snippet":"A dusty sepia slope with a large bundle of rope","status":"completed","categories":["T06","T02"],"evidence":{"inspection":"source_inspected","execution":"reported_by_source","review":"unreviewed"},"url":"https://veyrul.com/experiments/exp_01M64VFCD9DM37B53NZTQNGD96","api_url":"https://veyrul.com/v1/records/exp_01M64VFCD9DM37B53NZTQNGD96","updated_at":"2026-10-29T22:48:32.395Z","score":0.0448}},{"kind":"guide_preview","preview":{"schema":"guide-preview/v1","id":"art_01M6HJ41GSVHZ6F62ZXKZP2K1C","type":"article","revision":2,"title":"StorySync: keeping one character consistent across a batch of story images without training","coverage":"A source note on a 2025 paper describing a training-free way to keep one subject looking the same across a set of images from a diffusion model. Helps illustrators and story-image pipeline builders compare methods. Based on two arXiv pages; nothing was run, the metrics are the authors' own and no code release is stated.","example":null,"tips":["The authors say the method depends on masks from cross-attention maps; if a mask misses the subject, that frame can drift from the others.","Fine-detail matching across frames can occasionally pair the wrong regions by colour or texture, so check each frame against the character sheet.","On FLUX.1 the authors report limited pose variety, so name the pose you need in each scene prompt."],"categories":["T05"],"tags":["storysync","subject-consistency","training-free","cross-image-attention","region-harmonization","story-images","character-sheet","paper","cc-by-4.0","documented-not-tested"],"evidence":{"inspection":"source_inspected","execution":"not_run","review":"unreviewed","review_revision":null},"media":[]}}],"truncated":true,"has_more":true,"next_cursor":"eyJyZWZlcmVuY2UiOiJNakEiLCJwcmV2aWV3IjpudWxsLCJxIjoiU3RvcnlTeW5jOiBrZWVwaW5nIG9uZSBjaGFyYWN0ZXIgY29uc2lzdGVudCBhY3Jvc3MgYSBiYXRjaCBvZiBzdG9yeSBpbWFnZXMgd2l0aG91dCB0cmFpbmluZyIsInR5cGVzIjpbXSwiY2F0ZWdvcmllcyI6W119","ordering":"bounded_reference_and_preview_lanes"}