节点式生成流程
Node-based generative pipelines
Build ComfyUI-style graphs that produce outputs meeting constraints.
20 条本项目编写的提案 · 分类 v1.1 · 新增基准运行 0 次。下方验证方式与部分得分规则是设计，不是执行结果。
- 典型应用
- ComfyUI · Invoke · Houdini
- 小类 GUI 需求标签
HY· 混合
任务提案 · 20
展开查看完整原文与建议检查方式；两种界面均保留提案英文原文。
R06.11.01.01-T01 Build an SDXL + depth ControlNet graph and render at a fixed seed
原始指令
In ComfyUI (local, models preinstalled), build a graph: load input/room.png, compute a depth map (Depth Anything preprocessor), SDXL base with ControlNet depth strength 0.8, prompt from brief.txt, seed 42, 30 steps, dpmpp_2m karras, CFG 6, 1024x1024. Save the image to output/room_sdxl and the workflow to workflows/room_depth.json.
- 平台
mac· macOSwin· Windowslin· Linuxweb· 任意系统（网页）- 应用
- ComfyUI
- 交互表面
brow· 浏览器- GUI 需求 · 任务设定
HY· 混合- GUI 需求 · 普通权限
G2· GUI 必要- 交互原语
drag· 拖放click· 指向与点击type· 文字与表单- 工作产物
WP05· 时序媒体- 条件
- 未声明
- 提案难度
- 3 / 5
建议验证方式
Workflow JSON: required node classes linked (checkpoint→sampler, depth preprocessor→ControlNetApply), params exact. Output 1024x1024 PNG; re-running workflow reproduces it bit-exact; depth of output (same estimator) vs input depth Pearson ≥0.8.
建议部分得分
35% graph structure; 25% parameters; 20% output matches re-run; 20% depth adherence
R06.11.01.01-T02 Set up an img2img pass with a LoRA at fixed strength
原始指令
In ComfyUI, create an img2img workflow on input/sketch_cat.png using SD1.5 checkpoint dreamshaper_8, LoRA watercolor_v2 at model/clip strength 0.7, denoise 0.45, seed 7, 25 steps. Save output to output/cat_wc_00001_.png and workflow to workflows/cat_img2img.json.
- 平台
mac· macOSwin· Windowslin· Linuxweb· 任意系统（网页）- 应用
- ComfyUI
- 交互表面
brow· 浏览器- GUI 需求 · 任务设定
HY· 混合- GUI 需求 · 普通权限
G2· GUI 必要- 交互原语
drag· 拖放click· 指向与点击type· 文字与表单- 工作产物
WP05· 时序媒体- 条件
- 未声明
- 提案难度
- 2 / 5
建议验证方式
Workflow JSON: VAEEncode of input feeds KSampler latent, LoraLoader strengths 0.7/0.7, denoise 0.45, seed 7. Output re-run bit-exact; output dimensions equal input; SSIM to input in [0.45, 0.85].
建议部分得分
40% graph; 30% parameters; 30% output reproducible and in SSIM band
R06.11.01.01-T03 Inpaint only the sky region and leave the rest untouched
原始指令
In ComfyUI, inpaint input/street.jpg using mask input/sky_mask.png to replace the overcast sky with 'clear dusk sky, orange gradient' (SDXL inpainting model, seed 11). Composite the result back so pixels outside the mask are identical to the original. Save output/street_dusk.png and workflows/sky_inpaint.json.
- 平台
mac· macOSwin· Windowslin· Linuxweb· 任意系统（网页）- 应用
- ComfyUI
- 交互表面
brow· 浏览器- GUI 需求 · 任务设定
HY· 混合- GUI 需求 · 普通权限
G2· GUI 必要- 交互原语
drag· 拖放click· 指向与点击- 工作产物
WP05· 时序媒体- 条件
- 未声明
- 提案难度
- 3 / 5
建议验证方式
Outside mask (eroded 3 px): max abs diff ≤1/255 vs original. Inside mask: mean hue in orange range and luminance gradient top→bottom increasing; CLIP score for 'dusk sky' ≥0.24 on sky crop. Workflow uses mask-composite node.
建议部分得分
40% outside pixels identical; 35% sky replaced per prompt; 25% workflow saved and reproducible
R06.11.01.01-T04 Batch-generate product variants from a prompt CSV
原始指令
In ComfyUI build a workflow that reads 12 rows from input/variants.csv (sku, prompt), generates one 1024x1024 SDXL image per row with seed = 1000 + row index, and saves each as output/<sku>.png. Save the workflow as workflows/variants.json and run it once.
- 平台
mac· macOSwin· Windowslin· Linuxweb· 任意系统（网页）- 应用
- ComfyUI
- 交互表面
brow· 浏览器- GUI 需求 · 任务设定
HY· 混合- GUI 需求 · 普通权限
G2· GUI 必要- 交互原语
drag· 拖放type· 文字与表单code· 代码与命令- 工作产物
WP05· 时序媒体- 条件
- 未声明
- 提案难度
- 3 / 5
建议验证方式
12 PNGs named by sku, 1024x1024; PNG metadata seeds 1000–1011 matching rows; CLIP similarity of each image to its row prompt ≥0.25 and higher than to any other row prompt for ≥10/12. Workflow re-run reproduces 3 sampled outputs.
建议部分得分
25% 12 files named; 25% seeds; 35% prompt fidelity; 15% reproducible
R06.11.01.01-T05 Upscale to 4096 px without visible tile seams
原始指令
In ComfyUI take output/hero_1024.png and build an upscale chain: 4x-UltraSharp model upscale, then a tiled diffusion refine at denoise 0.25 (tile 1024, overlap 128) to exactly 4096x4096. Save output/hero_4k.png and workflows/upscale_4k.json.
- 平台
mac· macOSwin· Windowslin· Linuxweb· 任意系统（网页）- 应用
- ComfyUI
- 交互表面
brow· 浏览器- GUI 需求 · 任务设定
HY· 混合- GUI 需求 · 普通权限
G2· GUI 必要- 交互原语
drag· 拖放click· 指向与点击- 工作产物
WP05· 时序媒体- 条件
- 未声明
- 提案难度
- 3 / 5
建议验证方式
Output 4096x4096. Seam metric: gradient discontinuity along tile boundaries (every 896 px) ≤1.2x background gradient level. Downscaled to 1024, SSIM vs source ≥0.85. Workflow includes upscale model and tiled sampler with overlap 128.
建议部分得分
20% size exact; 40% no seams; 25% content fidelity; 15% workflow
R06.11.01.01-T06 Repair a broken shared workflow so it runs end to end
原始指令
workflows/broken_portrait.json from a colleague fails in ComfyUI: a missing custom node (unavailable here), an SD1.5 VAE wired to an SDXL model, and a width not divisible by 8. Fix it using only installed nodes so it produces the intended 832x1216 portrait, keeping prompts and seed. Save as workflows/portrait_fixed.json and render.
- 平台
mac· macOSwin· Windowslin· Linuxweb· 任意系统（网页）- 应用
- ComfyUI
- 交互表面
brow· 浏览器- GUI 需求 · 任务设定
HY· 混合- GUI 需求 · 普通权限
CL· CLI 足够- 交互原语
click· 指向与点击drag· 拖放vis· 视觉判断- 工作产物
WP05· 时序媒体- 条件
hidden· 隐藏 / 过期状态- 提案难度
- 3 / 5
建议验证方式
Fixed workflow executes headless via /prompt with 0 errors; all node classes are installed; VAE matches SDXL; output 832x1216; prompts and seed unchanged from original JSON.
建议部分得分
35% runs without error; 25% missing node replaced; 20% VAE fix; 20% size and prompts preserved
R06.11.01.01-T07 Transfer a painting style while preserving a face identity
原始指令
In ComfyUI create a portrait of the person in input/face_ref.jpg (synthetic identity) in the style of input/style_ref.jpg using IPAdapter (style) plus a face-identity adapter, SDXL, 1024x1024, seed 5. Save 4 outputs (seeds 5–8) to output/stylized/ and the workflow.
- 平台
mac· macOSwin· Windowslin· Linuxweb· 任意系统（网页）- 应用
- ComfyUI
- 交互表面
brow· 浏览器- GUI 需求 · 任务设定
HY· 混合- GUI 需求 · 普通权限
G2· GUI 必要- 交互原语
drag· 拖放vis· 视觉判断click· 指向与点击- 工作产物
WP05· 时序媒体- 条件
- 未声明
- 提案难度
- 4 / 5
建议验证方式
For each output: ArcFace cosine to face_ref ≥0.55; style distance (VGG Gram) to style_ref ≤ threshold calibrated on gold set and lower than to 5 distractor styles. 4 files, seeds in metadata.
建议部分得分
40% identity kept (10 points each); 40% style match; 20% files and workflow
R06.11.01.01-T08 Generate a seamless 16-frame animated loop
原始指令
In ComfyUI with AnimateDiff installed, generate a 16-frame 512x512 loop of 'campfire flames, night forest' at 8 fps with seed 3, export output/campfire.webp (looping) and output/campfire.mp4, and save the workflow. The loop must not jump between last and first frame.
- 平台
mac· macOSwin· Windowslin· Linuxweb· 任意系统（网页）- 应用
- ComfyUI · AnimateDiff
- 交互表面
brow· 浏览器- GUI 需求 · 任务设定
HY· 混合- GUI 需求 · 普通权限
G2· GUI 必要- 交互原语
drag· 拖放click· 指向与点击av· 音视频时序- 工作产物
WP05· 时序媒体- 条件
- 未声明
- 提案难度
- 4 / 5
建议验证方式
Both files 16 frames, 512x512, 8 fps. Loop seam: mean abs diff(frame15, frame0) ≤1.5x median adjacent-frame diff. Temporal flicker (mean luminance std over time) under threshold. CLIP 'campfire' ≥0.25 on middle frame.
建议部分得分
25% format; 35% seamless loop; 20% low flicker; 20% content
R06.11.01.01-T09 Package a reusable brand-background subgraph
原始指令
In ComfyUI create a group node (subgraph) 'BrandBackground' that takes a product image and hex color, removes the background, places the product centred on a gradient of that color at 2000x2000 with 8% margin, and outputs the image. Expose only inputs image and color. Save as a template and use it in workflows/brand_demo.json.
- 平台
mac· macOSwin· Windowslin· Linuxweb· 任意系统（网页）- 应用
- ComfyUI
- 交互表面
brow· 浏览器- GUI 需求 · 任务设定
HY· 混合- GUI 需求 · 普通权限
G2· GUI 必要- 交互原语
drag· 拖放click· 指向与点击type· 文字与表单- 工作产物
WP05· 时序媒体- 条件
- 未声明
- 提案难度
- 3 / 5
建议验证方式
Template file exists with exactly 2 exposed inputs. brand_demo.json executes on 3 test products: output 2000x2000, product bbox margins 8±1%, background corner colors within ΔE2000≤3 of the input hex gradient endpoints.
建议部分得分
30% subgraph with 2 inputs; 20% template saved; 50% outputs correct on 3 tests
R06.11.01.01-T10 Queue the variant workflow through the HTTP API (control pair of T04)
原始指令
Control pair of T04. With ComfyUI running headless and workflows/variants_api.json (API format) provided, write queue.py that posts one prompt per CSV row to /prompt with seed 1000 + index, waits on /history and copies results to output_api/<sku>.png.
- 平台
mac· macOSwin· Windowslin· Linux- 应用
- ComfyUI
- 交互表面
api· API / SDK- GUI 需求 · 任务设定
AP· API 足够- GUI 需求 · 普通权限
AP· API 足够- 交互原语
code· 代码与命令- 工作产物
WP05· 时序媒体- 条件
- 未声明
- 提案难度
- 2 / 5
建议验证方式
Same output checks as T04 on output_api/; server log shows 12 /prompt calls from queue.py and no browser session.
建议部分得分
40% 12 jobs queued; 40% outputs correct; 20% seeds
R06.11.01.01-T11 Outpaint a landscape to a wider canvas in Invoke
原始指令
In Invoke (Unified Canvas), extend input/lake_1024.png from 1024x1024 to 1536x1024 by outpainting 256 px on each side with an SDXL model, keeping the original centre region unchanged and the horizon continuous. Save the merged canvas to output/lake_wide.png.
- 平台
mac· macOSwin· Windowslin· Linux- 应用
- Invoke
- 交互表面
desk· 桌面 GUI- GUI 需求 · 任务设定
G2· GUI 必要- GUI 需求 · 普通权限
G2· GUI 必要- 交互原语
drag· 拖放geom· 精确几何vis· 视觉判断- 工作产物
WP05· 时序媒体- 条件
- 未声明
- 提案难度
- 3 / 5
建议验证方式
Output 1536x1024; centre 1024 region SSIM ≥0.98 vs input; horizon line detected in extensions within 6 px of original horizon height at the boundaries; boundary seam gradient ≤1.3x background. Invoke DB has the canvas session with bbox edits. Agent VM has no terminal, curl or Python, so Invoke's REST API is reachable only through the Invoke UI; the server access log is checked for non-UI origins.
建议部分得分
15% size; 35% centre preserved; 30% horizon continuity; 20% no seams
R06.11.01.01-T12 Build a regional-prompt workflow in the Invoke node editor
原始指令
In Invoke's Workflow editor build a workflow that splits a 1344x768 canvas into left/right regions using masks/left.png and right.png, prompting 'snowy pine forest' on the left and 'tropical beach' on the right with a shared style prompt, seed 21. Save it to the workflow library as 'SplitScene' and generate one image.
- 平台
mac· macOSwin· Windowslin· Linux- 应用
- Invoke
- 交互表面
desk· 桌面 GUI- GUI 需求 · 任务设定
G2· GUI 必要- GUI 需求 · 普通权限
G2· GUI 必要- 交互原语
drag· 拖放click· 指向与点击type· 文字与表单- 工作产物
WP05· 时序媒体- 条件
- 未声明
- 提案难度
- 4 / 5
建议验证方式
Workflow library entry SplitScene: regional guidance nodes reference both masks with correct prompts. Output 1344x768: CLIP zero-shot on left crop prefers 'snow forest' over 'beach' and vice versa on right (margin ≥0.03). Agent VM has no terminal, curl or Python, so Invoke's REST API is reachable only through the Invoke UI; the server access log is checked for non-UI request origins.
建议部分得分
40% workflow structure; 15% saved to library; 45% regional content correct
R06.11.01.01-T13 Install a local model and file outputs into a named board
原始指令
In Invoke, use the Model Manager to install models/juggernautXL.safetensors from local disk with VAE sdxl_vae, create a board 'Client-Moodboard', and generate 4 images from prompt.txt at 1024x1024 seeds 100–103 directly into that board.
- 平台
mac· macOSwin· Windowslin· Linux- 应用
- Invoke
- 交互表面
desk· 桌面 GUI- GUI 需求 · 任务设定
G2· GUI 必要- GUI 需求 · 普通权限
AP· API 足够- 交互原语
click· 指向与点击type· 文字与表单- 工作产物
WP08· 应用 / 系统状态- 条件
- 未声明
- 提案难度
- 2 / 5
建议验证方式
Invoke SQLite: model record with path and default VAE; board 'Client-Moodboard' holds exactly 4 images whose metadata show the model, seeds 100–103, 1024x1024 and the prompt. Agent VM has no terminal, curl or Python, so the REST API and invokeai.db are reachable only through the Invoke UI; server access log checked for non-UI origins.
建议部分得分
35% model installed with VAE; 20% board; 45% four images with metadata
R06.11.01.01-T14 Wedge render 27 variations with Houdini TOPs
原始指令
In Houdini, scene shots/vase.hip: build a TOP network that wedges 3 parameters (glaze roughness 0.1/0.4/0.8, light angle 30/60/90°, camera focal 35/50/85) and renders each combo with Karma at 960x540 to render/vase_r{rough}_l{angle}_f{focal}.png, plus a contact sheet render/contact.png.
- 平台
mac· macOSwin· Windowslin· Linux- 应用
- Houdini
- 交互表面
desk· 桌面 GUI- GUI 需求 · 任务设定
HY· 混合- GUI 需求 · 普通权限
CL· CLI 足够- 交互原语
drag· 拖放click· 指向与点击type· 文字与表单- 工作产物
WP05· 时序媒体- 条件
licensed· 授权专业软件- 提案难度
- 4 / 5
建议验证方式
27 PNGs with exact names, 960x540; per-file embedded/attr metadata matches name; renders differ as expected (roughness raises highlight spread metric monotonic). contact.png is 9x3 grid of thumbnails in wedge order. .hip contains TOP net with wedge node.
建议部分得分
30% 27 renders named; 25% parameter correctness; 20% contact sheet; 25% TOP net saved
R06.11.01.01-T15 Author a procedural building generator as a Houdini Digital Asset
原始指令
In Houdini create HDA 'test::building::1.0' with parameters floors (1–30), width/depth (m), window spacing, roof type (flat/gable). Output packed geometry with groups windows, walls, roof and a primitive attribute floor_id. Save to otls/building.hda and an example .hip with a 12-floor gable building.
- 平台
mac· macOSwin· Windowslin· Linux- 应用
- Houdini
- 交互表面
desk· 桌面 GUI- GUI 需求 · 任务设定
HY· 混合- GUI 需求 · 普通权限
CL· CLI 足够- 交互原语
drag· 拖放type· 文字与表单geom· 精确几何- 工作产物
WP04· 三维 / 空间模型- 条件
licensed· 授权专业软件- 提案难度
- 5 / 5
建议验证方式
hython test cooks HDA at 5 parameter sets: building height = floors × 3.2 m ±1 cm; window count = floors × floor(perimeter/spacing) ±1 per floor; groups exist and partition prims; floor_id range 0..floors-1; gable roof has ridge apex. Parameter ranges enforced.
建议部分得分
20% HDA interface; 35% geometry scaling correct; 25% groups/attributes; 20% roof variants
R06.11.01.01-T16 Scatter rocks on gentle slopes with spacing and export USD
原始指令
In Houdini scene terrain/hill.hip, scatter 500 instances of rock variants (rock_a/b/c.bgeo) onto the heightfield only where slope < 30° and outside road_mask, with minimum spacing 0.5 m, random yaw and scale 0.8–1.2, then export instanced USD to export/rocks.usd via Solaris.
- 平台
mac· macOSwin· Windowslin· Linux- 应用
- Houdini
- 交互表面
desk· 桌面 GUI- GUI 需求 · 任务设定
HY· 混合- GUI 需求 · 普通权限
CL· CLI 足够- 交互原语
drag· 拖放click· 指向与点击vis· 视觉判断- 工作产物
WP04· 三维 / 空间模型- 条件
licensed· 授权专业软件- 提案难度
- 4 / 5
建议验证方式
Parse rocks.usd PointInstancer: 500 instances, 3 prototypes; at every instance terrain slope <30° and road_mask=0; min pairwise distance ≥0.5 m; scales in [0.8,1.2]; yaw distribution non-degenerate.
建议部分得分
15% count; 35% slope/mask constraints; 20% spacing; 30% scale/yaw and USD valid
R06.11.01.01-T17 Reconstruct a lost pipeline that reproduces a reference image exactly
原始指令
The client approved output/approved.png but its metadata was stripped. notes.txt says: SDXL base, one of 3 listed checkpoints, seed in 9000–9010, sampler euler or dpmpp_2m, 28 or 30 steps, prompt in prompt.txt, 1024x1024. In ComfyUI find the configuration that reproduces approved.png and save workflows/approved_rebuilt.json.
- 平台
mac· macOSwin· Windowslin· Linuxweb· 任意系统（网页）- 应用
- ComfyUI
- 交互表面
brow· 浏览器- GUI 需求 · 任务设定
HY· 混合- GUI 需求 · 普通权限
HY· 混合- 交互原语
drag· 拖放vis· 视觉判断code· 代码与命令- 工作产物
WP05· 时序媒体- 条件
hidden· 隐藏 / 过期状态- 提案难度
- 5 / 5
建议验证方式
Execute approved_rebuilt.json: output equals approved.png with PSNR ≥45 dB (deterministic GPU settings). Workflow parameters equal the hidden ground truth (checkpoint, seed, sampler, steps).
建议部分得分
20% checkpoint; 30% seed; 20% sampler/steps; 30% exact reproduction
R06.11.01.01-T18 Generate a two-character scene matching given poses and roles
原始指令
In ComfyUI produce a 1216x832 image of two characters using input/pose_two.png (OpenPose skeletons): left is 'knight in silver armor', right is 'red-robed mage', with regional conditioning so attributes do not bleed. Seed 77; save output/duel.png and the workflow.
- 平台
mac· macOSwin· Windowslin· Linuxweb· 任意系统（网页）- 应用
- ComfyUI
- 交互表面
brow· 浏览器- GUI 需求 · 任务设定
HY· 混合- GUI 需求 · 普通权限
G2· GUI 必要- 交互原语
drag· 拖放vis· 视觉判断click· 指向与点击- 工作产物
WP05· 时序媒体- 条件
- 未声明
- 提案难度
- 5 / 5
建议验证方式
OpenPose re-detected on output: per-person keypoint PCK@0.1 ≥0.7 vs input skeletons. CLIP on left person crop: 'silver armor knight' > 'red robe mage' and reverse on right (margin ≥0.03). Workflow has ControlNet openpose and regional nodes.
建议部分得分
40% pose adherence; 40% attribute separation; 20% workflow
R06.11.01.01-T19 Cut out a product and composite it onto a template
原始指令
In ComfyUI build a workflow that removes the background from input/sneaker.jpg, places the cut-out on templates/bg_studio.png at 2000x2000 with its bottom edge on y=1700 and horizontally centred, adds a soft contact shadow, and saves output/sneaker_listing.png plus a transparent output/sneaker_cutout.png.
- 平台
mac· macOSwin· Windowslin· Linuxweb· 任意系统（网页）- 应用
- ComfyUI
- 交互表面
brow· 浏览器- GUI 需求 · 任务设定
HY· 混合- GUI 需求 · 普通权限
G2· GUI 必要- 交互原语
drag· 拖放click· 指向与点击vis· 视觉判断- 工作产物
WP05· 时序媒体- 条件
- 未声明
- 提案难度
- 3 / 5
建议验证方式
sneaker_cutout.png alpha IoU ≥0.95 vs ground-truth mask. Listing image 2000x2000; product bbox bottom at 1700±6 px, centre x 1000±6; shadow region darker than template by ≥8% luminance under the product.
建议部分得分
40% matte quality; 35% placement; 15% shadow; 10% both files saved
R06.11.01.01-T20 Generate a tileable PBR texture set with Copernicus
原始指令
In Houdini 20.5+ Copernicus (COPs), build a network that generates a 2048x2048 tileable 'mossy cobblestone' texture set: albedo, roughness, normal (OpenGL) and height, all derived from shared noise so features align. Export to tex/cobble_{map}.png.
- 平台
mac· macOSwin· Windowslin· Linux- 应用
- Houdini
- 交互表面
desk· 桌面 GUI- GUI 需求 · 任务设定
HY· 混合- GUI 需求 · 普通权限
CL· CLI 足够- 交互原语
drag· 拖放vis· 视觉判断- 工作产物
WP05· 时序媒体- 条件
licensed· 授权专业软件- 提案难度
- 3 / 5
建议验证方式
Four 2048² PNGs. Tileability: wrap-around edge difference ≤1.1x interior adjacent-pixel difference on all maps. Normal map derived from height (finite-difference normals correlate ≥0.8). Albedo/height edge maps correlate ≥0.6.
建议部分得分
20% four maps exported; 40% tileable; 25% normal consistent with height; 15% maps aligned
已有研究映射
以下沿用研究目录中的基准与小类映射，不是逐题标注、执行记录或产品背书。