Towsty
0c6a035d04
Coordinate shared GPU access across studio instances
2026-09-06 16:32:18 -05:00
Towsty and Cursor
5ffb65706f
Use content-hash names for Qwen VL still uploads too.
...
Keeps the same overwrite behavior as video/image Comfy uploads so prompt jobs do not leave unique copies in Shared input.
Co-authored-by: Cursor <cursoragent@cursor.com >
2026-09-04 08:21:06 -05:00
Towsty and Cursor
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
Towsty and Cursor
f8db0d626a
Add LoRA stacks with per-item strengths and named video/image generation presets so setups survive reload without mixing Klein onto MiniMax. Keep LTX Pink Cherry and xAIGen LoRAs on xAIGen, and run Recommend on Beast.
...
Co-authored-by: Cursor <cursoragent@cursor.com >
2026-08-28 15:24:44 -05:00
Towsty and Cursor
91948dd329
Start Sidecar Qwen VL from Recommend when the prompt enhancer is offline.
...
Co-authored-by: Cursor <cursoragent@cursor.com >
2026-08-27 22:56:29 -05:00
Towsty and Cursor
40cd17f35c
Add MiniMax and PinkCherry LTX as pickable video engines, with still or text start.
...
Shot 1 can run text-to-video; later shots still extend from the last frame. Recommend output is also normalized into shot-script cards.
Co-authored-by: Cursor <cursoragent@cursor.com >
2026-08-27 19:38:53 -05:00
Towsty and Cursor
df5ac24622
Add sidecar Qwen VL prompt recommend, fix queued shot bursts, and leave unused MiniMax identity slots empty.
...
Co-authored-by: Cursor <cursoragent@cursor.com >
2026-08-27 17:04:43 -05:00
Towsty