towsty/aigen
1
0
Fork 0
Code Issues Pull Requests 1 Actions Packages Projects Releases Wiki Activity

[WIP] Studio 2: sticky identity and isolated generation bench #1

Draft
towsty wants to merge 6 commits from studio-2 into main
pull from: studio-2
merge into: :main
Conversation 0 Commits 6 Files Changed 26
+1999 -109
6 Commits
Author SHA1 Message Date
TowstyandCursor 1b311d6529 Add Studio 2 caption jobs via Qwen2.5-VL GGUF on the host agent. 
Exclusive llama-server load/unload on the 5080, queued Describe UI with resultText, Copy, and Use as prompt.

Co-authored-by: Cursor <cursoragent@cursor.com>
 2026-09-30 22:06:10 -05:00
TowstyandCursor 1f10082087 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 16:22:55 -05:00
TowstyandCursor 4e61ee17b6 Wire Qwen 2.1 as Generate-only engine with 25/1 sampler defaults. 
Co-authored-by: Cursor <cursoragent@cursor.com>
 2026-09-20 15:53:44 -05:00
TowstyandCursor b95e8b2a87 Add studio2_qwen21_t2i Comfy graph for GGUF Qwen Image 2.1 T2I. 
Co-authored-by: Cursor <cursoragent@cursor.com>
 2026-09-20 15:53:44 -05:00
TowstyandCursor 277b49403c Add Qwen 2.1 host setup script and document Shared model paths. 
Co-authored-by: Cursor <cursoragent@cursor.com>
 2026-09-20 15:53:43 -05:00
TowstyandCursor 4831b32d20 Replace LoRA Thumbwheel spectrograms with range and numeric strengths. 
Co-authored-by: Cursor <cursoragent@cursor.com>
 2026-09-18 18:57:12 -05:00