shootthesound
48df2240d3
The Angelo — Overrides node now carries an optional second model stack (gen_model / gen_positive / gen_negative / gen_vae connection inputs plus gen_steps / gen_cfg / gen_sampler_name / gen_scheduler settings). When wired, Sampler Mode generates the base with the gen stack, decodes with the gen VAE, and re-encodes the pixels with the main edit VAE so the whole editing session runs on the edit model — generate with FLUX Krea / SDXL for the look, click-to-edit with Klein / Qwen-Image-Edit. Behaviour: - Edit Mode never reads the gen bundle; unwired = byte-identical to 2.5 - Seed + Smpl Denoise stay on the toolbar (seed controls keep working; denoise < 1.0 = img2img with the gen model, incl. off a loaded image) - gen_negative optional: falls back to a zeroed gen_positive (ConditioningZeroOut maths) - Preview/history pixels are the gen VAE decode (not the edit-VAE round-trip); base pixels cropped to /16 for any edit VAE ratio - Cached-base / loaded-image Sampler runs derive the gen latent by encoding the base pixels with the gen VAE - guider/sampler/sigmas trio deliberately not applied to the gen model (a wired GUIDER wraps the edit model's conds) Hardening from the bug-check pass (2 inline + 3 agent-review findings): - gen widgets live in optional inputs, not required: ComfyUI validates required inputs server-side BEFORE Python defaults apply, which would have rejected every pre-2.6 API-format export of the Overrides node - explicit None checks in overrides parsing (gen_cfg 0.0 is falsy and an `or` fallback silently sampled at the default) - partial gen-bundle wiring (any subset incl. gen_negative-only) raises a clear ValueError in Sampler Mode instead of silently falling back - wired-latent guard: wrong-channel latents raise a clear not-in-the- gen-model's-latent-space error; 5D video latents into a 4D gen model get their singleton frame axis squeezed instead of crashing deep in the UNet - console prints the gen resolution each run (an empty latent authored for a 16x edit VAE silently means half-size through an 8x gen VAE — undetectable from the latent alone, so make it visible) Fingerprint stays edit-model-fixed so Edit Mode never spuriously resets; _STATE untouched until the whole gen chain succeeds (cancel/OOM safe). Also: example_workflows/Krea_plus_Klein-workflow.json (FLUX Krea 2 + turbo LoRA at 1504x1504 through the Wan 2.1 VAE, Klein 9B editing) and full README coverage (Quick start section, Overrides wiring rules, Krea 2 + Wan 2.1 VAE pairing note).
16 lines
1.1 KiB
TOML
16 lines
1.1 KiB
TOML
[project]
|
||
name = "comfyui-angelo"
|
||
version = "2.6.0"
|
||
description = "Click-to-edit sampler for ComfyUI. Generate an image, then work it like a photo editor — click or paint to refine, drag or describe to inpaint, click an edge to outpaint, paint over something to remove it and rebuild the background, and one-click restore or upscale a whole photo. First-class support for FLUX 2 Klein 9B and Qwen-Image-Edit, plus any sampler-compatible model. Includes two-model workflows (generate with FLUX Krea / SDXL, edit with Klein or Qwen via the Overrides gen bundle), a Remove brush, Fullscreen editing mode, Quick Photo Refine, 2× Pixel + Shrink resizing, Outpaint, Reference anchoring, Xtra-Fine, Smart Inpaint, Fix All, Vary ×4, optional SAM 3 Detect, and a companion Overrides node for custom samplers."
|
||
license = { text = "MIT" }
|
||
readme = "README.md"
|
||
requires-python = ">=3.9"
|
||
|
||
[project.urls]
|
||
Repository = "https://github.com/shootthesound/ComfyUI-Angelo"
|
||
|
||
[tool.comfy]
|
||
PublisherId = "shootthesound"
|
||
DisplayName = "ComfyUI-Angelo"
|
||
Icon = "https://avatars.githubusercontent.com/u/110498357?v=4"
|