13 Commits

Author SHA1 Message Date
TBNilles 399acabd58 feat(model-manager): "Free GPU memory" button to unload ComfyUI models
ComfyUI caches the last model when RAM is plentiful (unified memory), so
memory doesn't drop after switching models even though models are being
swapped, not accumulated. Add a sidebar "Free GPU memory" button that
proxies ComfyUI's POST /free (unload_models + free_memory) via a new
/api/comfyui/free endpoint (COMFYUI_URL env). Verified it releases ~7GB.
README documents this plus the --disable-smart-memory auto-unload option.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-06-07 17:14:37 -04:00
TBNilles c2b0f202bf fix: run VAE in fp32 to stop black/blank generated images
fp16 VAE produces NaNs on many SD1.5/SDXL checkpoints, yielding black
images (often mistaken for NSFW censorship - there is no NSFW filter in
the generator). Switch COMFYUI_FLAGS from --fp16-vae to --fp32-vae in
.env.example and document the fix in the README. Verified end-to-end:
a test generation now produces a real image (mean ~86) instead of black.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-06-07 16:56:46 -04:00
TBNilles 15e0dc3772 feat(model-manager): base-model multi-select filter on CivitAI browse
Add a checkbox dropdown to filter the CivitAI catalog by one or more base
models (SD 1.5, SDXL, Pony, Illustrious, Flux, etc.), mapped to the API's
`baseModels` array param. Backend search accepts comma-separated
base_models; button shows the selected count with a Clear action.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-06-07 16:37:33 -04:00
TBNilles 505f212c4d feat(model-manager): flag Early Access models in CivitAI browse
CivitAI Early Access versions require purchased access and otherwise fail
with 401. Surface version `availability` from the API as an `early_access`
flag (per card and per version), show an amber "EARLY ACCESS" tag on the
card, label such entries in the version dropdown, and warn before
attempting to download one.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-06-07 16:27:33 -04:00
TBNilles 6871a6d460 feat(model-manager): add "Delete all" gallery button + clearer 401 errors
- Gallery: DELETE /api/gallery/all removes every image under output/;
  "Delete all" button with in-app confirm and a deleted/failed count.
- Downloads: surface a clear, actionable message when CivitAI/HuggingFace
  returns 401/403 (model requires login/early-access, or the key/token
  lacks access) instead of a bare error, both at resolve time and during
  the download stream.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-06-07 16:19:48 -04:00
TBNilles 44f7b5a697 feat(comfyuimini): add "Manage Photos" sidebar link to the Gallery
ComfyUIMini's built-in gallery is view-only. Inject a "Manage Photos"
link into its sidebar (via the shared head.ejs partial at build time, so
no fork) that points to the Model Manager's delete-capable Gallery. The
URL is built client-side from the browser host; the port is baked from
the MODEL_MANAGER_PORT build arg (default 8189).

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-06-07 15:46:04 -04:00
TBNilles c9fa3fcab5 feat(model-manager): generated-photo Gallery + device-routing landing
- Gallery view: grid of generated photos from ComfyUI's output/, full-size
  lightbox, and permanent delete (with confirm). Paginated ("Load more").
- Backend: GET /api/gallery, GET /gallery/file (path-guarded image serve),
  DELETE /api/gallery (path-guarded; clear error on permission denial).
- Mount ./output read-write into model-manager so the gallery can delete.
- Device-routing landing at /start: phones -> ComfyUIMini, desktops ->
  the Gallery; ?force=mobile|desktop overrides. Ports come from the new
  /api/ui-config (COMFYUI_PORT / COMFYUIMINI_PORT env).
- Responsive tweaks so the gallery is usable if opened directly on a phone.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-06-07 15:41:46 -04:00
TBNilles e8115e7aa6 feat(model-manager): add CivitAI browse view + fix civitai.red / 401
- New "Browse CivitAI" view: thumbnail grid with search, type/sort/period
  filters and NSFW toggle; click a model card to download it (per-card
  version picker for multi-version models). Cursor + page based "Load more".
- Backend: /api/civitai/search and /api/civitai/download endpoints; new
  civitai_search() catalog helper.
- Fix 401 on paste: recognize the civitai.red mirror (and any civitai.*
  host), normalize API calls to civitai.com, and always resolve the
  model-version so type + filename are auto-detected for every CivitAI URL.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-06-07 14:50:10 -04:00
TBNilles 359043ad67 feat: add StabilityMatrix-style Model Manager service
New FastAPI container (port 8189) to download and manage models:
- Installed Models, Add/Download (CivitAI/HuggingFace/direct URL), Settings views
- Persistent SQLite storage for API keys and download history (./sparkyui-data)
- Downloads land in ./models, auto-sorted into ComfyUI's standard subfolders
- Default COMFYUI_HOST_PATH and SPARKYUI_DATA_PATH to the project root
- Wire docker-compose service, env defaults, gitignore, README docs

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-06-07 06:19:44 -04:00
Evan Carmen 15fc70663f Add ComfyUIMini mobile-friendly UI integration
New features:
- ComfyUIMini container (Node.js Alpine, ~150MB) for mobile/tablet access
- Separate container architecture with shared Docker network
- Health checks on both services with proper dependency ordering
- Shared output volume for image gallery feature

Files added:
- comfyuimini/Dockerfile - Node.js 20 Alpine with tsx runtime
- comfyuimini/.dockerignore - Build context filtering

Files updated:
- docker-compose.yml - Added comfyuimini service, network, health checks
- .env.example - Added COMFYUIMINI_PORT and COMFYUIMINI_REF
- README.md - Architecture diagram, ComfyUIMini docs, updated credits

Access points:
- ComfyUI (Desktop): http://<host>:8188
- ComfyUIMini (Mobile): http://<host>:3000

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2026-01-03 23:45:13 -06:00
Evan Carmen 434a90741c Add What's Included section, fix repo URL
- Add "What's Included" section listing ComfyUI, ComfyUI-Manager,
  SageAttention, and PyTorch versions
- Update clone URL to actual GitHub repo (ecarmen16/SparkyUI)
- ComfyUI-Manager is auto-installed on first container run

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2026-01-03 21:27:42 -06:00
Evan Carmen 687ce72dd3 Add Grace-Blackwell unified memory optimizations
Key changes based on HurbaLurba's DGX Spark research:

- Remove --gpu-only flag (fights unified memory fabric)
- Add --disable-pinned-memory, --force-fp16, --dont-upcast-attention
- Add CUDA env vars for unified memory: CUDA_MANAGED_FORCE_DEVICE_ALLOC,
  PYTORCH_NO_CUDA_MEMORY_CACHING, OMP_NUM_THREADS=20
- Document unified memory architecture best practices
- Add host-level GPU optimization instructions (clock locking, vboost)
- Document SageAttention PR #297 status (merged then reverted)
- Add credits section

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2026-01-03 21:01:25 -06:00
Evan Carmen 1f5aeb5248 Initial commit: SparkyUI - ComfyUI for DGX Spark (Blackwell GB10)
Docker-based ComfyUI setup for NVIDIA DGX Spark ARM64 + sm_121:
- CUDA 13.0.2 base (required for compute_121 support)
- PyTorch 2.9.1+cu130 ARM64 wheels
- SageAttention compiled with TORCH_CUDA_ARCH_LIST="12.1"
- Triton/torch.compile disabled (no sm_121 support yet)
- ComfyUI-Manager auto-installed at runtime
- Configurable model/data paths via .env

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2026-01-03 20:28:30 -06:00