mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-05-03 17:27:37 +08:00
a7780fe05f
The audit of v4.1 surfaced ~70 issues across the five scripts and three
reference docs — most user-visible (silent file overwrites, status-error
misclassified as success, X-API-Key leaked to S3 on /api/view redirect,
Cloud endpoints that 404 because they were renamed). v5.0.0 fixes those
and fills the gaps that previously forced users to write their own glue
(WebSocket monitoring, batch/sweep, img2img upload helper, dep auto-fix,
log fetch, health check, example workflows).
Critical fixes
- run_workflow.py: poll_status now checks status_str==error BEFORE
completed:true, so a failed run no longer reports success
- run_workflow.py: download_output streams to disk via safe_path_join,
preserves server subfolder structure (no silent overwrites), and
retries with exponential backoff
- run_workflow.py: refuses to overwrite a link with a literal in
inject_params (would silently break wiring)
- _common.py: _StripSensitiveOnRedirectSession (subclasses
requests.Session.rebuild_auth) drops X-API-Key/Cookie on cross-host
redirects — fixes a real key-leak path through Cloud's signed-URL
download flow. Tested
- Cloud routing (verified live): /history → /history_v2,
/models/<f> → /experiment/models/<f>, plus folder aliases for the
unet ↔ diffusion_models and clip ↔ text_encoders rename
- check_deps.py: distinguishes 200/empty vs 404 folder_not_found vs
403 free-tier; emits concrete fix_command per missing dep
- extract_schema.py: prompt vs negative_prompt determined by tracing
KSampler.{positive,negative} connections (incl. through Reroute /
Primitive nodes) instead of meta-title heuristic; symmetric
duplicate-name resolution; cycle-safe trace_to_node
- hardware_check.py: multi-GPU pick-best, Apple variant detection,
Rosetta detection, WSL2, ROCm --json, disk-space check, optional
PyTorch probe; powershell preferred over deprecated wmic
- comfyui_setup.sh: prefers pipx → uvx → pip --user (with PEP-668
fallback); idempotent — skips relaunch if server already up;
configurable port/workspace; persistent log; SIGINT trap
New scripts
- run_batch.py — count or sweep (cartesian product), parallel up to
cloud tier limit
- ws_monitor.py — real-time WebSocket viewer; saves preview frames
- auto_fix_deps.py — runs comfy node install / model download for
whatever check_deps reports missing (with --dry-run)
- health_check.py — single command that runs the verification checklist
(comfy-cli + server + checkpoints + optional smoke test that cancels
itself to avoid burning compute)
- fetch_logs.py — pull traceback / status messages for a prompt_id
Coverage expansion
- Param patterns now cover Flux (BasicScheduler, BasicGuider,
RandomNoise, ModelSamplingFlux), SD3, Wan/Hunyuan/LTX video,
IPAdapter, rgthree, easy-use, AnimateDiff
- Embedding refs in CLIPTextEncode strings extracted as model deps
- ckpt_name / vae_name / lora_name / unet_name now controllable so
workflows can be retargeted per run
Examples
- workflows/{sd15,sdxl,flux_dev}_txt2img.json
- workflows/sdxl_{img2img,inpaint}.json
- workflows/upscale_4x.json
- workflows/{animatediff_video,wan_video_t2v}.json + README
Tests
- 117 tests (105 unit + 8 cloud integration + 4 cross-host security)
- Cloud tests auto-skip without COMFY_CLOUD_API_KEY; verified end-to-end
against live cloud API
Backwards compatibility
- All existing CLI flags continue to work; new behavior is opt-in
(--ws, --input-image, --randomize-seed, --flat-output, etc.)
79 lines
2.2 KiB
JSON
79 lines
2.2 KiB
JSON
{
|
|
"_comment": "Flux Dev text-to-image using the modern sampler chain (BasicScheduler/Guider/SamplerCustomAdvanced). Required: flux1-dev.safetensors (UNET), t5xxl_fp16.safetensors + clip_l.safetensors (CLIP), ae.safetensors (VAE).",
|
|
"6": {
|
|
"class_type": "CLIPTextEncode",
|
|
"_meta": {"title": "Prompt"},
|
|
"inputs": {"text": "a serene mountain landscape at golden hour, photorealistic", "clip": ["11", 0]}
|
|
},
|
|
"8": {
|
|
"class_type": "VAEDecode",
|
|
"_meta": {"title": "VAE Decode"},
|
|
"inputs": {"samples": ["13", 0], "vae": ["10", 0]}
|
|
},
|
|
"9": {
|
|
"class_type": "SaveImage",
|
|
"_meta": {"title": "Save Image"},
|
|
"inputs": {"filename_prefix": "flux_dev", "images": ["8", 0]}
|
|
},
|
|
"10": {
|
|
"class_type": "VAELoader",
|
|
"_meta": {"title": "VAE"},
|
|
"inputs": {"vae_name": "ae.safetensors"}
|
|
},
|
|
"11": {
|
|
"class_type": "DualCLIPLoader",
|
|
"_meta": {"title": "DualCLIPLoader"},
|
|
"inputs": {
|
|
"clip_name1": "t5xxl_fp16.safetensors",
|
|
"clip_name2": "clip_l.safetensors",
|
|
"type": "flux"
|
|
}
|
|
},
|
|
"12": {
|
|
"class_type": "UNETLoader",
|
|
"_meta": {"title": "UNET Loader"},
|
|
"inputs": {"unet_name": "flux1-dev.safetensors", "weight_dtype": "default"}
|
|
},
|
|
"13": {
|
|
"class_type": "SamplerCustomAdvanced",
|
|
"_meta": {"title": "Sampler Custom"},
|
|
"inputs": {
|
|
"noise": ["25", 0],
|
|
"guider": ["22", 0],
|
|
"sampler": ["16", 0],
|
|
"sigmas": ["17", 0],
|
|
"latent_image": ["27", 0]
|
|
}
|
|
},
|
|
"16": {
|
|
"class_type": "KSamplerSelect",
|
|
"_meta": {"title": "Sampler Select"},
|
|
"inputs": {"sampler_name": "euler"}
|
|
},
|
|
"17": {
|
|
"class_type": "BasicScheduler",
|
|
"_meta": {"title": "Scheduler"},
|
|
"inputs": {
|
|
"scheduler": "simple",
|
|
"steps": 20,
|
|
"denoise": 1.0,
|
|
"model": ["12", 0]
|
|
}
|
|
},
|
|
"22": {
|
|
"class_type": "BasicGuider",
|
|
"_meta": {"title": "Guider"},
|
|
"inputs": {"model": ["12", 0], "conditioning": ["6", 0]}
|
|
},
|
|
"25": {
|
|
"class_type": "RandomNoise",
|
|
"_meta": {"title": "Noise"},
|
|
"inputs": {"noise_seed": 42}
|
|
},
|
|
"27": {
|
|
"class_type": "EmptySD3LatentImage",
|
|
"_meta": {"title": "Latent"},
|
|
"inputs": {"width": 1024, "height": 1024, "batch_size": 1}
|
|
}
|
|
}
|