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/

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

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)

qwen-edit-turbo latest: bake Qwen4Play_v2 lora (on by default), drop Amateur-Photo lora

Upload qwen-edit-nsfw-v4.json

Delete workflows/qwen-edit-turbo-v4.json

Add qwen-edit-nsfw-v4 API workflow

Add qwen-edit-nsfw-v4 workflow (v4 pipeline on Rapid-AIO-NSFW checkpoint)

download_missing_models: plan IPAdapterUnifiedLoader's implicit clip_vision/ipadapter files (preset -> filename mapping)

Add ip-adapter-plus_sd15 (SD1.5 variant for IPAdapterUnifiedLoader PLUS preset)

Upload aestx777-style-composition-final.json

remove workflows/aestx9-style-composition.json

remove workflows/aestx9-single-ipadapter.json

remove workflows/aestx9-prev-single-ipadapter.json

remove workflows/aestx-workflows/api/aestx9-style-composition.json

remove workflows/aestx-workflows/api/aestx9-single-ipadapter.json

remove workflows/aestx-workflows/api/aestx9-prev-single-ipadapter.json

aestx9: API payload for aestx9-style-composition.json

aestx9: aestx9-style-composition.json — max composition adherence + max style transfer

aestx9: API payload for aestx9-prev-single-ipadapter.json

aestx9: aestx9-prev-single-ipadapter.json — max composition adherence + max style transfer

aestx9: API payload for aestx9-single-ipadapter.json

aestx9: aestx9-single-ipadapter.json — max composition adherence + max style transfer

aestx: copy drag-and-drop workflow aestx-style-composition.json to top-level workflows/

aestx: copy drag-and-drop workflow aestx-prev-single-ipadapter.json to top-level workflows/

aestx: copy drag-and-drop workflow aestx-single-ipadapter.json to top-level workflows/

aestx models: mirror depth_anything_vitl14.pth

aestx models: mirror CLIP-ViT-H-14-laion2B-s32B-b79K.safetensors

aestx models: mirror ip-adapter-plus_sdxl_vit-h.safetensors

aestx models: mirror diffusers_xl_depth_full.safetensors

aestx models: mirror juggernautXL_v9Rdphoto2Lightning.safetensors

aestx models: mirror juggernautXL_v8Rundiffusion.safetensors

aestx: add README.md (drop-in UI + tested API versions)

aestx: add aestx-style-composition.json (drop-in UI + tested API versions)

aestx: add aestx-prev-single-ipadapter.json (drop-in UI + tested API versions)

aestx: add aestx-single-ipadapter.json (drop-in UI + tested API versions)

aestx: add aestx-style-composition.json (drop-in UI + tested API versions)

aestx: add aestx-prev-single-ipadapter.json (drop-in UI + tested API versions)

aestx: add aestx-single-ipadapter.json (drop-in UI + tested API versions)

Upload 3 files

Remove paper folders — centralized in private aleph65/Papers

makeup-extract: install + run scripts for Makeup Extraction of 3D Representation (EG2023) (single photo -> FLAME UV materials + extracted makeup layers)

facelift: add export pass (2048px orbit RGBA renders + OpenCV cameras + run_meta, versioned output layout)

facelift: install + run scripts for FaceLift (single photo -> 3D Gaussian head)

download_missing_models: serial downloads by default, 10s stall watchdog with auto-restart (x3) then curl fallback, add --last flag

Add 3dgazenet: 3DGazeNet gaze estimation + dense eye mesh scripts (native env, like p3dm/ffhq-uv/deca) + stevie example outputs

Add deca: DECA detailed 3D face reconstruction scripts (native env, like p3dm/ffhq-uv) + stevie example outputs

Add ffhq-uv: FFHQ-UV RGB fitting scripts (native env, like p3dm) + stevie example outputs

p3dm: README.md - export raw fit data (frame ckpt, float npys, cropbox, seg, landmarks) by default; fix --force glob collision

p3dm: p3dm_run.sh - export raw fit data (frame ckpt, float npys, cropbox, seg, landmarks) by default; fix --force glob collision