towsty/aigen
1
0
Fork 0
Code Issues Pull Requests 1 Actions Packages Projects Releases Wiki Activity
330 Commits 2 Branches 0 Tags
a51118d92ab2702ba4b3623ab694413833733912
Commit Graph
28 Commits
Author SHA1 Message Date
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 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 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 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 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 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
TowstyandCursor df885d5732 Replace stale host agent on boot and document one-click Startup install. 
Co-authored-by: Cursor <cursoragent@cursor.com>
 2026-09-15 18:15:19 -05:00
TowstyandCursor fae3b23e37 Finish YuE2 host setup, weight download paths, and v1 cleanup. 
Co-authored-by: Cursor <cursoragent@cursor.com>
 2026-09-14 18:46:35 -05:00
TowstyandCursor d1ff05089f Document YuE2 install, weight cleanup, and regression tests. 
Co-authored-by: Cursor <cursoragent@cursor.com>
 2026-09-14 18:46:35 -05:00
Towsty 064f1db933 Read production LoRA names in Studio 2 2026-09-12 21:05:11 -05:00
Towsty 9b1d8ae798 Clarify output image actions and preserve user VRAM policy 2026-09-09 16:38:48 -05:00
Towsty badf59d914 Restore automatic video batch continuation and prepare stable Comfy loading 2026-09-09 06:58:35 -05:00
Towsty 1e0cff9dea Add local queued video upscale with Real-ESRGAN and RIFE 2026-09-08 17:55:02 -05:00
Towsty 4c97980646 Avoid YuEGP pinned-memory exhaustion on 32GB Windows hosts 2026-09-08 07:04:13 -05:00
Towsty 7665285a0d Preserve extension quality with original segments and reliable refinement 2026-09-08 06:25:40 -05:00
Towsty c2b6032e49 Replace Comfy YuE with standalone YuEGP profile 1 2026-09-07 20:24:47 -05:00
Towsty 174d40a7dc Simplify generation controls with task navigation and settings drawer 2026-09-07 08:36:33 -05:00
Towsty 0c6a035d04 Coordinate shared GPU access across studio instances 2026-09-06 16:32:18 -05:00
TowstyandCursor 0e1222d035 Name outputs from the input, engine, and LoRA keys instead of aigen_0001. Image-edit presets now store prompts, and aspect fill pads stills without stretching. 
Co-authored-by: Cursor <cursoragent@cursor.com>
 2026-08-30 16:24:49 -05:00
TowstyandCursor 0fa64ea765 Keep last-frame continuity when character stills are attached. 
Co-authored-by: Cursor <cursoragent@cursor.com>
 2026-08-30 08:21:57 -05:00
TowstyandCursor 5fe91e6bae Show Flux and Krea as Image v2 engine cards, and run Krea on edit, compose, and refine. 
Krea image-to-image uses encode plus denoise graphs, not Klein reference latents, and still fails closed if the Krea models are missing.

Co-authored-by: Cursor <cursoragent@cursor.com>
 2026-08-29 07:29:31 -05:00
TowstyandCursor ab5477c999 Keep the Klein Concept LoRA on xAIGen only. 
AIGen hides the sliders, ignores snofs strengths, and strips the SNOFS node so that file cannot be queued from the public studio.

Co-authored-by: Cursor <cursoragent@cursor.com>
 2026-08-29 07:08:33 -05:00
TowstyandCursor f6663444f5 Add Krea as a second Image v2 Generate engine beside Flux. 
Generate can queue krea_v2_generate.json without sharing Klein encoders or falling back if Krea assets are missing.

Co-authored-by: Cursor <cursoragent@cursor.com>
 2026-08-29 07:05:01 -05:00
TowstyandCursor b35f9af10d Add Image v2 Generate for Klein text-to-image. 
New sibling graph and mode so T2I does not borrow Edit, Compose, or Refine. Stills are ignored; size is width x height only.

Co-authored-by: Cursor <cursoragent@cursor.com>
 2026-08-28 22:56:33 -05:00
TowstyandCursor a2895b8054 Add Image v2 Refine for on-device regional edits. 
Mask painter and denoise strength sit beside Edit and Compose. The canned hand/chest prompt helper is gone so that text stays yours.

Co-authored-by: Cursor <cursoragent@cursor.com>
 2026-08-28 22:03:20 -05:00
TowstyandCursor 21fe2412f9 Add Image v2 as a sibling of Image edit, with separate Klein graphs. 
Keep the v1 Image tab on its dual-branch template. The host agent follows Desktop's live port so Coolify stays on :8198.

Co-authored-by: Cursor <cursoragent@cursor.com>
 2026-08-28 21:22:37 -05:00