Image Studio: switch base model to qwen3.5:9b (non-abliterated)

The abliterated 9B was the source of the tool-call format mangling
(both Native XML leaks and Default Python-syntax leaks). Standard
qwen3.5:9b is the same family, same 9B size (6.6 GB), vision-capable
and native tool calling actually works.

The image content uncensored-ness was always going to come from the
SDXL checkpoints in ComfyUI — the LLM is just a dispatcher. Picking
a well-behaved tool-caller for that role doesn't compromise output
content.

Updated:
  - image_studio.json base_model_id → qwen3.5:9b
  - init-models.sh: pulls qwen3.5:9b as a standard registry pull,
    in addition to the existing abliterated 9B (which stays for
    other chat models)
  - image_studio.md setup table + vision section explaining why
    we chose standard over abliterated for the dispatcher role

function_calling stays as 'default' and tool_choice as 'required'
for now — they don't hurt with a reliable tool-caller and operators
can flip back to native + drop tool_choice once they verify it
works for them (which also removes the need for a separate Task
Model for title generation).

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This commit is contained in:
57_WolveandClaude Opus 4.7 committed 2026-04-19 17:09:42 -05:00
1 parent 1ae451ad5f
commit 20d4bd5b72
3 files changed
+24 -14

No files matched your search

+5
View File
@@ -55,6 +55,11 @@ pull() {
# mirror-ollama-model.sh, upload to S3, then list them here.
s3_pull "huihui_ai/qwen3.5-abliterated:9b" "qwen3.5-abliterated-9b.tgz"
# Standard non-abliterated Qwen 3.5 9B — 6.6 GB, vision + native tool
# calling. Used as the Image Studio dispatcher (the abliterated 9B above
# is fine for chat but mangles native tool-call formatting).
pull "qwen3.5:9b"
# ─── Direct registry pulls ──────────────────────────────────────────────────
for model in dolphin3:8b llama3.1:8b ministral-3:8b mistral-nemo:12b qwen3.6:latest; do
pull "$model"