towsty/aigen
1
0
Fork 0
Code Issues Pull Requests 1 Actions Packages Projects Releases Wiki Activity
362 Commits 2 Branches 0 Tags
7799529788abff136fee50a073122deb105f687d
Commit Graph
362 Commits
This Branch
This Branch
All Branches
Author SHA1 Message Date
Towsty 7799529788 Extend Prompt Builder with sequence characters, outfits, and scene toggles. 
Characters live on the sequence with per-scene on/off and outfit picks; Copy scene exports only the active tab; legacy saves still open.
 2026-10-02 08:50:31 -05:00
Towsty 790c33fcf0 Fix Prompt Builder Nitro build by inlining sequence helpers in utils. 
The relative re-export of shared/prompt-sequences.mjs left an unresolved import in the SSR bundle.
 2026-10-02 08:11:09 -05:00
Towsty 1bf97568bf Add Prompt Builder page for multi-scene prompt sequences. 
Name, save, and load ordered scenes on the server; assemble copyable text with a Batch-compatible double blank line between scenes.
 2026-10-02 07:15:00 -05:00
Towsty 5788d74001 Add desktop Batch toggle, fix xAIGen library hide/selection, per-engine steps/CFG, and mobile prompt editor. 
Desktop Batch splits only on double blank lines when enabled; library hide actually conceals thumbs and pinned clicks stick; steps/CFG restore per image model; mobile opens a near-fullscreen prompt editor.
 2026-10-01 17:06:25 -05:00
Towsty 4f40641050 Split blank-line paragraphs in the desktop prompt into ordered image batch jobs. 2026-09-30 23:34:47 -05:00
Towsty 14dcd234f3 Let finished caption jobs be dismissed from the Queue panel. 2026-09-30 23:18:44 -05:00
Towsty 15ef891b26 Add image-to-text Describe on the bench via exclusive llama.cpp caption jobs. 2026-09-30 22:50:19 -05:00
TowstyandCursor 9481791ac5 Keep fetching library pages after the first 50 so the whole folder is reachable. 
Co-authored-by: Cursor <cursoragent@cursor.com>
 2026-09-30 00:28:22 -05:00
TowstyandCursor 17bb42bea4 Serve the stage from a 1600px preview instead of the grid thumb. 
Co-authored-by: Cursor <cursoragent@cursor.com>
 2026-09-29 20:57:01 -05:00
TowstyandCursor ccf852cb0c Clear Queuing when the optimistic job snapshot avoids structuredClone. 
Co-authored-by: Cursor <cursoragent@cursor.com>
 2026-09-29 20:45:23 -05:00
TowstyandCursor 4ec8ffa8d6 Serve the bench before the catalog and never await ffmpeg on /thumb. 
Co-authored-by: Cursor <cursoragent@cursor.com>
 2026-09-29 20:35:28 -05:00
TowstyandCursor a465dd68ec Stop polling the library catalog and keep the stage on thumbs. 
Co-authored-by: Cursor <cursoragent@cursor.com>
 2026-09-29 20:15:03 -05:00
TowstyandCursor cfabfd37ee Queue Generate with an immediate local card and stop blocking reload on library or object_info. 
Co-authored-by: Cursor <cursoragent@cursor.com>
 2026-09-29 19:46:55 -05:00
TowstyandCursor ffdaa7ce42 Remount stage media on selectedId and show thumb before the archive still. 
Co-authored-by: Cursor <cursoragent@cursor.com>
 2026-09-29 19:45:51 -05:00
TowstyandCursor aa0aa871e4 Add paginated library JSON and dedicated still thumbs that never stream archive masters. 
Co-authored-by: Cursor <cursoragent@cursor.com>
 2026-09-29 19:45:22 -05:00
TowstyandCursor 845ee5bbf6 Set the selected still on Use image instead of an empty Photos card. 
Co-authored-by: Cursor <cursoragent@cursor.com>
 2026-09-29 15:40:35 -05:00
TowstyandCursor ba83520923 Move stage actions into a top chrome bar with Copy and Load menus. 
Co-authored-by: Cursor <cursoragent@cursor.com>
 2026-09-29 09:09:00 -05:00
TowstyandCursor 322e5a276e Persist the bench draft and hide input thumbs only. 
Co-authored-by: Cursor <cursoragent@cursor.com>
 2026-09-29 08:14:13 -05:00
TowstyandCursor 5f6a7aa9bc Rename library actions and always store promptRaw on ingest. 
Co-authored-by: Cursor <cursoragent@cursor.com>
 2026-09-29 08:14:13 -05:00
TowstyandCursor 930bbf7c7b Keep MiniMax hold from injecting amplitude and speed. 
Co-authored-by: Cursor <cursoragent@cursor.com>
 2026-09-29 08:14:13 -05:00
TowstyandCursor c4e74628ee Show the Qwen LoRA card with qwen-stem picks and apply them on generate. 
Co-authored-by: Cursor <cursoragent@cursor.com>
 2026-09-28 22:47:59 -05:00
TowstyandCursor fe560d7e40 Slim the phone stage to icons, chevrons, and a More sheet. 
Co-authored-by: Cursor <cursoragent@cursor.com>
 2026-09-28 22:21:13 -05:00
TowstyandCursor d61f99d6fd Put still actions on the stage and split output vs input hide. 
Co-authored-by: Cursor <cursoragent@cursor.com>
 2026-09-28 21:26:29 -05:00
Towsty f9903ed76e Square Library modal thumbs and add stage previous/next. 2026-09-28 20:40:45 -05:00
TowstyandCursor a33cadb6c2 Load Library modal thumbs with the same tiles and fetch as /library. 
Co-authored-by: Cursor <cursoragent@cursor.com>
 2026-09-28 20:25:16 -05:00
TowstyandCursor 5b0d7370ed Show Typed and Used prompt fields on still Details. 
Co-authored-by: Cursor <cursoragent@cursor.com>
 2026-09-28 20:11:18 -05:00
TowstyandCursor 7242d0faef Replace the under-stage filmstrip with a Library modal and stage eye. 
Co-authored-by: Cursor <cursoragent@cursor.com>
 2026-09-28 20:11:14 -05:00
TowstyandCursor e06afe4a17 Fix Photos Add, Remove, and Replace against the library picker. 
Remove clears the Photos array and backing image fields; Add opens the picker with disk upload and drops empty drafts on cancel.

Co-authored-by: Cursor <cursoragent@cursor.com>
 2026-09-26 17:06:39 -05:00
TowstyandCursor 50319e03a9 Map Photos roles to Qwen image_1/image_2 and inject encode tags silently. 
Mention phrases become <imageN> only in the TextEncode string; the inspector never shows Comfy tokens.

Co-authored-by: Cursor <cursoragent@cursor.com>
 2026-09-26 16:01:49 -05:00
TowstyandCursor 5c2248a3fd Replace Hero/Edit-source chrome with Photos role cards. 
Inspector stills use plain-English roles and Mention phrases; Qwen Generate hides Photos entirely.

Co-authored-by: Cursor <cursoragent@cursor.com>
 2026-09-26 16:00:37 -05:00
TowstyandCursor 58c5458c87 Store the Edit TextEncode prompt on library stills, not a Start still caption. 
Edit + Enhance always leads with the keep/<image1> stanza and typed change; PE describe dumps are dropped, and Typed stays promptRaw.

Co-authored-by: Cursor <cursoragent@cursor.com>
 2026-09-26 15:14:20 -05:00
TowstyandCursor c46e827c68 Force <image1> on every Qwen Edit PE rewrite. 
PE-I2I no longer bans tags for single-still edits, and the runner rewrites natural photo/image wording to <image1> so Start still stays bound.

Co-authored-by: Cursor <cursoragent@cursor.com>
 2026-09-26 15:04:04 -05:00
TowstyandCursor a51118d92a Pass through PE refusals to the raw prompt and pin adult PE system prompts. 
Enhance no longer fails the studio job when the rewrite refuses or comes back empty; host prompt copies keep the official steps plus the adult appendix after a node re-clone.

Co-authored-by: Cursor <cursoragent@cursor.com>
 2026-09-26 14:46:24 -05:00
TowstyandCursor 99b61e67d7 Keep Enhance + Generate as one queue row with shared progress. 
The PE stage now stays on the same jobId so the header and queue badge agree, and jobs behind it do not promote when enhance finishes.

Co-authored-by: Cursor <cursoragent@cursor.com>
 2026-09-26 14:42:22 -05:00
TowstyandCursor 30be4bd5b0 Wire Qwen Edit Start still to image_1 and PE-I2I identity keep. 
Edit no longer invents strangers when the prompt omits <image1> or PE drops image tokens; Hero stays Klein-only.

Co-authored-by: Cursor <cursoragent@cursor.com>
 2026-09-26 14:27:36 -05:00
TowstyandCursor ecc4c69a8b Wire Qwen Turbo toggle through Studio 2 and the runner. 
Force 6/1 when Turbo is on, skip negatives, keep PE in front, and fail closed if the r128 LoRA is missing.

Co-authored-by: Cursor <cursoragent@cursor.com>
 2026-09-26 12:42:00 -05:00
TowstyandCursor 17cbc99f8f Add Qwen 2.1 Viggle Turbo Comfy graphs. 
Use the unmerged ViggleTurboLora path with the official 6-step sigma schedule on the existing Q8 GGUF.

Co-authored-by: Cursor <cursoragent@cursor.com>
 2026-09-26 12:41:59 -05:00
TowstyandCursor 95873744cd Size Qwen 2.1 Generate from the bench aspect table. 
Wire EmptyLatentImage to the official ~1 MP grid so 16:9 lands at 1536×864, keep PE wh_ratio advisory, and leave Edit on the encode latent from image_1.

Co-authored-by: Cursor <cursoragent@cursor.com>
 2026-09-26 10:54:18 -05:00
TowstyandCursor 2842855c7b Wire Qwen Enhance prompt toggle through Studio 2 and the runner. 
Queue PE first when enabled, fail closed on parse_ok, free VRAM, then run the existing T2I or Edit graph with the rewrite.

Co-authored-by: Cursor <cursoragent@cursor.com>
 2026-09-26 10:25:44 -05:00
TowstyandCursor e0292c8d2a Add Qwen 2.1 PE-only Comfy graphs for prompt enhance. 
Keep PE CLIP separate from DiT so the 16 GB card can run rewrite then generate without loading both at once.

Co-authored-by: Cursor <cursoragent@cursor.com>
 2026-09-26 10:25:44 -05:00
TowstyandCursor bb27af506e Restore Studio 2 Load hydrate, sticky negatives, and strip actions. 
Co-authored-by: Cursor <cursoragent@cursor.com>
 2026-09-21 12:23:20 -05:00
TowstyandCursor df5ef0949e Make Library Reveal all / Hide all cover the whole grid. 
Co-authored-by: Cursor <cursoragent@cursor.com>
 2026-09-21 12:09:26 -05:00
TowstyandCursor 206984b6ec Add Reveal all / Hide all to Studio 2 input picker. 
Co-authored-by: Cursor <cursoragent@cursor.com>
 2026-09-20 21:04:55 -05:00
TowstyandCursor 52a01e0adc Enable Qwen 2.1 on Edit: wire picker, runner, and source-still validation. 
Co-authored-by: Cursor <cursoragent@cursor.com>
 2026-09-20 18:13:07 -05:00
TowstyandCursor 8609ba24a4 Add Qwen 2.1 Image Edit Comfy graph (GGUF + TextEncode + int8 cache). 
Co-authored-by: Cursor <cursoragent@cursor.com>
 2026-09-20 18:10:50 -05:00
TowstyandCursor 776d585345 Fix xAIGen LoRA picker to use isXaigenStudio like the server. 
Bench was checking only public.studio === 'xaigen', so when the instance
is branded xAIGen via instanceName the client stripped xaigen-* LoRAs.

Co-authored-by: Cursor <cursoragent@cursor.com>
 2026-09-20 17:34:53 -05:00
TowstyandCursor 608f7d8d47 Fix Qwen 2.1 GGUF load: promote Q8 norms to F32 and wire TextEncode latent. 
abenzerps Q8_0 ships 1D RMSNorms as packed Q8 (136 vs 128), which breaks
Comfy rms_rope; tagger now dequantizes small tensors and the graph uses
TextEncodeQwenImage21's 64-ch latent plus AuraFlow shift.

Co-authored-by: Cursor <cursoragent@cursor.com>
 2026-09-20 16:58:00 -05:00
TowstyandCursor 68731916ca Wire Qwen 2.1 as Generate-only engine with 25/1 sampler defaults. 
Co-authored-by: Cursor <cursoragent@cursor.com>
 2026-09-20 16:58:00 -05:00
TowstyandCursor 08d507c491 Add studio2_qwen21_t2i Comfy graph for GGUF Qwen Image 2.1 T2I. 
Co-authored-by: Cursor <cursoragent@cursor.com>
 2026-09-20 16:57:04 -05:00
TowstyandCursor d65420f34a Add Qwen 2.1 host setup script and document Shared model paths. 
Co-authored-by: Cursor <cursoragent@cursor.com>
 2026-09-20 16:57:04 -05:00