fix(mcp-image-gen): fix Heretic/FLUX2 integration bugs

- Fix syntax error in server.py (dangling docstring lines)
- Correct model filename: flux-2-klein-4b.safetensors (without -fp8)
- Fix _WORKFLOW_REGISTRY key to match actual downloaded filename
- Update get_models() to always include registry models as fallback
- Fix test expectations to match corrected model names
- All 37 tests passing
This commit is contained in:
Patrick Plate
2026-04-10 19:21:51 +02:00
parent 8f24168dcd
commit ea0c5d39c4
6 changed files with 531 additions and 38 deletions
+56 -32
View File
@@ -39,8 +39,14 @@ COMFYUI_DIR = Path(
# Maximum number of images allowed in a single batch call
MAX_COUNT = 10
# Path to the bundled FLUX.1-schnell workflow template
_WORKFLOW_PATH = Path(__file__).parent / "workflows" / "flux_schnell.json"
# Workflow registry: model filename → workflow JSON path
# This allows us to support multiple models (FLUX.1-schnell + FLUX.2 Klein with Heretic encoder)
_WORKFLOW_REGISTRY: dict[str, Path] = {
"flux1-schnell.safetensors": Path(__file__).parent / "workflows" / "flux_schnell.json",
"flux-2-klein-4b.safetensors": Path(__file__).parent / "workflows" / "flux2_klein_heretic.json",
}
_DEFAULT_MODEL = "flux1-schnell.safetensors"
# ---------------------------------------------------------------------------
@@ -181,21 +187,37 @@ class ComfyUIClient:
return resp.content
async def get_models(self) -> list[str]:
"""Return the list of available checkpoint model filenames."""
async with httpx.AsyncClient(timeout=10.0) as client:
resp = await client.get(
f"{self.base_url}/object_info/CheckpointLoaderSimple"
)
resp.raise_for_status()
data = resp.json()
# ComfyUI returns: {"CheckpointLoaderSimple": {"input": {"required": {"ckpt_name": [["model1.safetensors", ...], ...]}}}}
node_info = data.get("CheckpointLoaderSimple", {})
ckpt_list = (
node_info.get("input", {})
.get("required", {})
.get("ckpt_name", [[]])[0]
)
return ckpt_list if isinstance(ckpt_list, list) else []
"""Return the list of available checkpoint model filenames.
Combines models known to ComfyUI with our internal registry
(including FLUX.2 Klein with Heretic encoder).
"""
models = set()
# Get models from ComfyUI
try:
async with httpx.AsyncClient(timeout=10.0) as client:
resp = await client.get(
f"{self.base_url}/object_info/CheckpointLoaderSimple"
)
resp.raise_for_status()
data = resp.json()
node_info = data.get("CheckpointLoaderSimple", {})
ckpt_list = (
node_info.get("input", {})
.get("required", {})
.get("ckpt_name", [[]])[0]
)
if isinstance(ckpt_list, list):
models.update(ckpt_list)
except Exception:
# ComfyUI not reachable — fall back to registry only
pass
# Add our registered models
models.update(_WORKFLOW_REGISTRY.keys())
return sorted(list(models))
# ---------------------------------------------------------------------------
@@ -209,13 +231,20 @@ def build_flux_workflow(
height: int,
steps: int,
seed: int,
model: str,
model: str = _DEFAULT_MODEL,
) -> dict:
"""Build a ComfyUI API-format workflow dict for FLUX.1-schnell text-to-image.
"""Build a ComfyUI API-format workflow dict for the requested model.
This is a pure function — no I/O, fully testable.
Supports:
- "flux1-schnell.safetensors" (original)
- "flux-2-klein-4b-fp8.safetensors" (with Heretic-abliterated Qwen3-4B text encoder)
Falls back to FLUX.1-schnell if model is unknown.
This is a pure function — no I/O outside the registry, fully testable.
"""
with open(_WORKFLOW_PATH) as f:
workflow_path = _WORKFLOW_REGISTRY.get(model, _WORKFLOW_REGISTRY[_DEFAULT_MODEL])
with open(workflow_path) as f:
wf = json.load(f)
wf = copy.deepcopy(wf)
@@ -277,18 +306,13 @@ async def _generate_single(
) -> list:
"""Generate a single image and return [TextContent, ImageContent] or [TextContent] on error.
Args:
client: ComfyUIClient instance.
prompt: Positive text prompt.
negative_prompt: Negative text prompt.
width / height: Image dimensions.
steps: Inference steps.
seed: Seed value (-1 = random).
model: ComfyUI model filename.
resolved_output_dir: Resolved output directory Path.
name: User-supplied name prefix (unsanitized).
label: Human-readable label for TextContent prefix (e.g. "[lumen 1/3]").
Supports two models:
- flux1-schnell.safetensors (default, fast 4-step)
- flux-2-klein-4b.safetensors (with Heretic-abliterated Qwen3-4B text encoder — no refusals)
"""
if model not in _WORKFLOW_REGISTRY:
model = _DEFAULT_MODEL
logger.warning("Unknown model %s, falling back to %s", model, _DEFAULT_MODEL)
# Build and submit workflow
try:
workflow = build_flux_workflow(