alphacentri/comfyui-nvidia
1
0
Fork 0
Code Issues Pull Requests Actions Packages Releases Activity
13 Commits 1 Branch 3 Tags
b815cd6a5fca89a809d75f876e6dc6cddea17d18
Commit Graph
3 Commits
Author SHA1 Message Date
57_WolveandClaude Opus 4.7 45d5541be0 smart_image_gen v0.2: per-style sampler/CFG/steps/CLIP-skip + prompt prefixes 
Researched each of the seven SDXL checkpoints on Civitai and encoded the
creator-recommended generation defaults per style instead of one global
set. Material differences:

  - photo (CyberRealistic): dpmpp_2m_sde / karras / CFG 4 / 28 steps / CLIP 1
  - juggernaut: dpmpp_2m_sde / karras / CFG 4.5 / 35 steps / CLIP 1
  - pony: euler_a / normal / CFG 7.5 / 25 steps / CLIP 2
  - general (Talmendo): dpmpp_2m / karras / CFG 8 / 30 steps / CLIP 2
  - furry-nai (Reed): euler_a / normal / CFG 5 / 30 steps / CLIP 2
  - furry-noob (IndigoVoid): euler_a-only / normal / CFG 4.5 / 20 / CLIP 2
  - furry-il (NovaFurry): euler_a / normal / CFG 4 / 30 steps / CLIP 2

Three prompt-prefix dialects auto-prepended (NEVER cross-contaminated):
photoreal models get nothing, Pony gets the full
score_9..score_4_up chain (mandatory), and the NoobAI/Illustrious
furry models get their booru quality + year-tag prefixes
(masterpiece/best quality/absurdres/newest/etc). Workflow now includes
a CLIPSetLastLayer node so per-style CLIP skip works.

Routing default for generic "furry" flipped from Reed (NAI) to NovaFurry
(Illustrious) — current sweet-spot consensus. Removed global
DEFAULT_STEPS/DEFAULT_CFG valves; per-style values are canonical.

Sources: each model's Civitai page (CyberRealisticXL, Juggernaut,
Pony V6 XL, TalmendoXL, Reed FurryMix, IndigoVoid FurryFused,
NovaFurryXL) and Pony/Illustrious prompting guides.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
 2026-04-19 12:45:34 -05:00
57_WolveandClaude Opus 4.7 cd0034cd99 Flesh out per-style negatives in smart_image_gen Tool 
Each style now gets a proper baseline covering quality, anatomy, and
watermark/signature suppression — plus the appropriate style-leak guards
(no-cartoon for photo, no-human for furry, score_4–6 suppression for
pony). Quality terms only; no NSFW filtering by default since several
checkpoints in this set are commonly used for adult work and would
fight a baked-in content filter. If SFW-by-default is wanted, add an
explicit safe-mode flag rather than expanding NEGATIVES.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
 2026-04-19 12:39:24 -05:00
57_WolveandClaude Opus 4.7 392b26167f Add smart_image_gen Tool for per-prompt checkpoint routing 
Open WebUI Tool the LLM invokes instead of the built-in image action.
Auto-routes among the seven SDXL checkpoints (photo / juggernaut /
pony / general / furry-{nai,noob,il}) based on either an explicit
`style` arg or first-match-wins regex over the prompt. Constructs the
ComfyUI workflow inline, submits via /prompt, polls /history, returns
the result as a base64 data-URI markdown image so no extra hosting is
needed. Per-style default negatives. ComfyUI URL / steps / CFG /
timeout are admin-tunable Valves.

Filters can't see image-gen requests in Open WebUI (the routers skip
the filter chain), so the LLM-driven Tool is the only path that
gives intent-aware routing without changing the chat UX.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
 2026-04-19 12:17:02 -05:00