modelbeast/server/operators/mflux_image_edit/manifest.json
MODELBEAST f0bac67edb Local mflux operators: seedvr2_upscale + mflux_image_edit (free, ungated)
Two new local image-prep operators through the already-installed mflux 0.18 (no
new heavy install, ungated weights):
- seedvr2_upscale: mflux-upscale-seedvr2 (ByteDance SeedVR2, MIT) — faithful
  local upscale, free alternative to cloud fal_upscale
- mflux_image_edit: mflux-generate-qwen-edit (Qwen-Image-Edit, Apache-2.0) —
  local prompt-based image editing, free alternative to fal_image_edit

Research verdict on dinov3 (recorded): waiting for Meta approval is the only
legitimate path — TRELLIS.2's DiT is trained on DINOv3 ViT-L/16 features so the
encoder can't be swapped, and the only ungated mirrors are unauthorized
re-uploads. trellis_mac stays blocked on the pending gate.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-07-13 01:37:56 +10:00

21 lines
1.0 KiB
JSON

{
"id": "mflux_image_edit",
"name": "Edit Image (local, Qwen)",
"category": "image-prep",
"description": "Image + instruction → edited image entirely on this Mac via mflux Qwen-Image-Edit (ungated/Apache-2.0). Free local alternative to fal_image_edit / nano-banana edit — 'remove the sticker', 'make it studio-lit on white', material/lighting changes. First run downloads weights.",
"accepts": ["image"],
"produces": ["image"],
"resources": "gpu",
"entry": "run.py",
"python": "/Users/m3ultra/Documents/MODELBEAST/venvs/mflux/bin/python",
"params_schema": {
"type": "object",
"properties": {
"prompt": {"type": "string", "default": "", "description": "Edit instruction (what to change)"},
"steps": {"type": "integer", "default": 25, "minimum": 1, "maximum": 50, "description": "Inference steps"},
"seed": {"type": "integer", "default": 42, "description": "Random seed"},
"guidance": {"type": "number", "default": 4.0, "minimum": 0, "maximum": 10, "description": "Guidance scale"}
}
}
}