Aug 4 14:19 Add redux_experiment_final.zip (single-file archive) 14:19 Archive flux-redux experiment: final writeup, workflows, inputs, scripts, research, v4 outputs, comparison sheets, Claude memories (part 2) 14:19 Archive flux-redux experiment: final writeup, workflows, inputs, scripts, research, v4 outputs, comparison sheets, Claude memories 13:37 flux-v2 v4 rev: fix attn_bias+ControlNet conditioning bug (multiply 0.35), bfl-lora to BFL spec (guidance 10, LoRA 0.85), calibration-validated 12:20 flux-v2 rev: generic anatomy prompt as default positive, reusable negative node (inert at CFG 1.0, documented) 11:45 Promote flux-v2 workflows to workflows/: sweep-validated defaults (guidance 3.0/4.0, 896x1152 portrait pre-pass, saved crops, hires group), full 84-run matrix passed on inputs_v2 11:08 flux-v2 drafts: bake sweep winners (style-comp guidance 3.0; bfl 4.0 confirmed) 10:49 Add flux-v2 workflow drafts: 896x1152 portrait pre-pass, saved crops, hires group, bfl guidance 4.0 08:50 Add diffusion_models/flux1-dev.safetensors (flux-redux workflows) 08:49 Add diffusion_models/flux1-schnell.safetensors (flux-redux workflows) 08:40 Add loras/flux1-depth-dev-lora.safetensors (flux-redux workflows) 08:39 Add controlnet/FLUX.1-dev-ControlNet-Union-Pro-2.0.safetensors (flux-redux workflows) 08:39 Add style_models/flux1-redux-dev.safetensors (flux-redux workflows) 08:24 Add flux-redux workflow drafts (v1): style+composition (Union-Pro-2.0), fal dev replica, prompt, Replicate schnell replica, BFL depth-lora variant + research notes; frozen starting points in wip/flux-redux/ Aug 1 11:02 qwen-edit-turbo v7: bake Qwen4Play_v2 lora (off by default, lora_qwen4play toggles), drop Amateur-Photo lora; start.sh passes no VRAM flag (full-coverage loras OOM under --highvram; perf unchanged). Image: comfyui-serverless:qwen-edit-turbo-v7 09:38 Revert 705c3555cb : restore Amateur-Photo lora config for qwen-edit-turbo (the Qwen4Play image was never actually built/pushed; docs referenced a nonexistent qwen-edit-turbo-latest tag) 07:24 qwen-edit-turbo latest: bake Qwen4Play_v2 lora (on by default), drop Amateur-Photo lora 06:47 Upload qwen-edit-nsfw-v4.json 06:47 Delete workflows/qwen-edit-turbo-v4.json 06:36 Add qwen-edit-nsfw-v4 API workflow 06:36 Add qwen-edit-nsfw-v4 workflow (v4 pipeline on Rapid-AIO-NSFW checkpoint) Jul 29 11:18 download_missing_models: plan IPAdapterUnifiedLoader's implicit clip_vision/ipadapter files (preset -> filename mapping) 11:17 Add ip-adapter-plus_sd15 (SD1.5 variant for IPAdapterUnifiedLoader PLUS preset) 09:34 Upload aestx777-style-composition-final.json 09:34 remove workflows/aestx9-style-composition.json 09:34 remove workflows/aestx9-single-ipadapter.json 09:34 remove workflows/aestx9-prev-single-ipadapter.json 09:34 remove workflows/aestx-workflows/api/aestx9-style-composition.json 09:34 remove workflows/aestx-workflows/api/aestx9-single-ipadapter.json 09:34 remove workflows/aestx-workflows/api/aestx9-prev-single-ipadapter.json 09:23 aestx9: API payload for aestx9-style-composition.json 09:23 aestx9: aestx9-style-composition.json — max composition adherence + max style transfer 09:23 aestx9: API payload for aestx9-prev-single-ipadapter.json 09:23 aestx9: aestx9-prev-single-ipadapter.json — max composition adherence + max style transfer 09:23 aestx9: API payload for aestx9-single-ipadapter.json 09:23 aestx9: aestx9-single-ipadapter.json — max composition adherence + max style transfer 09:15 aestx: copy drag-and-drop workflow aestx-style-composition.json to top-level workflows/ 09:15 aestx: copy drag-and-drop workflow aestx-prev-single-ipadapter.json to top-level workflows/ 09:15 aestx: copy drag-and-drop workflow aestx-single-ipadapter.json to top-level workflows/ 09:13 aestx models: mirror depth_anything_vitl14.pth 09:13 aestx models: mirror CLIP-ViT-H-14-laion2B-s32B-b79K.safetensors 09:13 aestx models: mirror ip-adapter-plus_sdxl_vit-h.safetensors 09:13 aestx models: mirror diffusers_xl_depth_full.safetensors 09:12 aestx models: mirror juggernautXL_v9Rdphoto2Lightning.safetensors 09:12 aestx models: mirror juggernautXL_v8Rundiffusion.safetensors 09:11 aestx: add README.md (drop-in UI + tested API versions) 09:11 aestx: add aestx-style-composition.json (drop-in UI + tested API versions) 09:11 aestx: add aestx-prev-single-ipadapter.json (drop-in UI + tested API versions) 09:11 aestx: add aestx-single-ipadapter.json (drop-in UI + tested API versions) 09:11 aestx: add aestx-style-composition.json (drop-in UI + tested API versions) 
