Replace the session <select> dropdown with a searchable scrollable list.
Sessions already come sorted by most recent from the backend. Added
search input that filters sessions by name in real time.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
New filter buttons for Steps, CFG, and Upscale (combined mode + model
name). Applied in both the new-items filter path and the full
executePipeline filter path.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Scale to fit all columns across viewport width, center horizontally,
and position the top row just below the header bar instead of using
a hardcoded 20px offset.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
autoFitZoom() now measures header and json-container heights to
calculate actual available viewport space. Fits to both width and
height constraints and centers vertically in the remaining space.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- Replace set() with ordered list dedup for batch encoding so prompts
generate in the order they're written in the config array
- Track cumulative upscale duration so the time metric includes both
generation and all upscale steps instead of just the last upscale
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Slider in Label Mode settings (6-16px range) controls overlay text size.
Uses CSS custom property for instant updates. Persisted to localStorage.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Labels now display strength values (e.g. "loraName:1.0:0.8") instead
of just the filename, matching the config_json format.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Move torch and safetensors imports inside huggingface_vae_decode() so
CivitAI and Distribution functions still work if those packages are
missing. Update stale "Uses urllib" comments to reference the gateway.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
test_worker_connection, notify_workers_to_start, and stop_all_workers
now use gateway functions. No more inline urllib imports.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
All 6 urllib call patterns (download, register, claim, submit,
heartbeat, fail) now use gateway functions from network_utils.py.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
GET, POST JSON, POST multipart, and streaming download functions for
LAN-only worker coordination between ComfyUI instances.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
HF_ENDPOINTS now imported from network_utils as single source of truth.
Tensor serialization and query string construction moved to gateway.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Allowlisted endpoints with validation. Handles tensor serialization,
query string construction, and HTTP transport.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Centralizes all outbound network requests into a single module for
easier Comfy Registry security review. Starts with CivitAI API.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Keep diffusers as a dependency but without a version constraint to
avoid conflicts with other custom nodes that may need different versions.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Remove diffusers from requirements.txt to avoid conflicts with other
custom nodes that may pin older versions. Wrap the import in remote_vae.py
with try/except so the node loads fully even without diffusers — only
Remote VAE features are unavailable, with a clear error message guiding
users on how to fix it.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Re-add AI-CONTEXT.md, ProjectStructure.md, README.md, and Roadmap.md
to git tracking. Only docs/plans/ remains gitignored as local-only.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Replace flat upscale configs with pipeline/steps/repeat architecture:
- Pipelines run independently from base image
- Steps chain sequentially within a pipeline
- Steps support repeat count for iterative refinement
Add "Save Pre-Upscaled Output" option to also keep the base image.
Add "Adjust Prompt During HiRes Fix" with prepend/append/replace
behaviors. HiRes-adjusted prompts are batch pre-encoded for efficiency.
Results written to manifest metadata and exposed as label overlays.
Fix fmtVal scoping error in buildLabelOverlay (was referenced outside
the upscale block where it was defined).
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
computeLabelGlobalValues() now runs after loadSession() assigns data
so unique-only filtering works immediately. processNewData() calls
refreshLabelOverlays() so existing card labels update when new images
change what's unique.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
New nodes now show the session landing page instead of auto-loading
"my_session". Uses _configured_from_workflow flag to distinguish fresh
nodes from saved workflows. Also fixes session cards Y-axis overflow.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
ProjectStructure.md, README.md, Roadmap.md, AI-CONTEXT.md, and docs/
are local development references — not needed in the repo.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Three bugs fixed:
1. Upscaled images used bare 'filename=...' instead of full '/view?filename=...&type=output&subfolder=...' URL format, causing 404s in dashboard
2. Upscaled manifest entries missing 'id' and 'rejected' fields, causing holes in dashboard grid
3. Base (non-upscaled) images were still saved to pending_batch when upscaling was enabled — now only upscaled final versions appear in output
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Skip upscale combos that require a model when none is selected.
Use effective_size=2.0 for model_only mode instead of 1.0 which
would resize the model output back to original resolution.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Seed: expanded per-gen behavior + new full run seed behavior (random/increment/decrement before/after entire run)
- Canvas: fix flicker during simultaneous pan+zoom via requestAnimationFrame batching
- Upscaling: 3 session-level modes (HiRes fix, model upscale, model+HiRes) with tiled VAE support
- Cooldown: configurable GPU breaks between generations with optional VRAM clearing
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
The worker's generate_image() call was only passing basic parameters
(seed, steps, cfg, sampler, scheduler, denoise, attention_mode) but
missing all advanced/model-specific parameters that the local path
passes. This caused workers to produce different images than local runs.
Added missing parameters:
- model_sampling_override (noise schedule for Flux/SD3/AuraFlow)
- model_sampling_shift (shift values for model sampling)
- model_sampling_flux_max_shift / model_sampling_flux_base_shift
- use_advanced_sampling (SamplerCustomAdvanced vs standard KSampler)
- advanced_guider / advanced_scheduler
- flux_guidance_value
- width / height (for Flux2Scheduler computation)
All parameters were already present in the job config dict from
expand_configs() but were never forwarded to generate_image().
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Removed standalone edit button (editor accessible via dropdown menu)
- Dropdown and Clear on their own row, custom WxH inputs on a second row
- Custom resolutions file moved to benchmarks/USCG-custom-resolutions.json
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Removed max-height and overflow-y:auto from all submenu levels so
nested menus can extend freely without being clipped by parent containers.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Replaced tiny native <select> with large custom dropdown button
- 3-level nested submenu: Model Type > Orientation (Landscape/Portrait/Square) > Sizes
- Massively expanded built-in presets: SD1.5, SDXL, Illustrious/Pony, Flux, Wan/Video, HiRes/Upscale
- Custom Resolutions Editor modal for creating persistent user-defined resolutions
organized into named categories
- Custom resolutions saved to ComfyUI output/USCG-custom-resolutions.json
- Custom category always appears first in the dropdown menu
- Edit button (pencil emoji) for quick access to the custom editor
- Backend: GET/POST /configbuilder/custom_resolutions endpoints
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Three bugs fixed:
1. Global Prompt data was incorrectly loaded into Custom Prompts when
loading a session. Added _prompt_source flag ("global"/"custom") to
configs so the round-trip loader can distinguish between them and
restore global prompts to the correct section.
2. Checkbox toggle was not visually broken but appeared non-functional
because bug #1 caused global prompts to populate custom prompt fields,
making the state confusing. Now correctly separated.
3. Prompt combination count in the section header was only computed at
render time and never updated when groups changed. Added live update
via updatePromptCountDisplay() in the onChange callback.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Previously, check_if_job_completed() with optional inputs would only
match on sampler/scheduler/steps/cfg/denoise/seed — skipping model,
prompt, and lora checks. This caused false positive matches, skipping
jobs even when the user changed models via optional input nodes.
Now returns -1 (no match) immediately when has_optional_inputs=True,
forcing all jobs to re-generate since upstream changes can't be detected.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
The conditioning serialization was only preserving pooled_output, dropping
critical keys like attention_mask that Wan/T5 models need for proper
sampling. This caused KSampler to produce NaN latents on distributed workers.
Includes backwards compatibility with old serialization format.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Worker now clones latent and frees UNet tensors + CUDA cache before
VAE decode, giving Dynamic VRAM clean memory for VAE loading.
decode_latent_with_vae now detects NaN in input/output, logs diagnostic
info, retries with float32, and handles bfloat16->numpy conversion.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Worker threads run outside ComfyUI's execution engine which wraps
everything in torch.inference_mode(). Without it, Dynamic VRAM's lazy
weight loading produces NaN during VAE decode, causing black images.
Matches ComfyUI's execution.py:703 pattern.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
