From f91078b1ffa484c424f78814f54de4d5846e4daa Mon Sep 17 00:00:00 2001 From: Alexander Piskun <13381981+bigcat88@users.noreply.github.com> Date: Thu, 13 Nov 2025 20:05:26 +0200 Subject: [PATCH 1/3] add PR template for API-Nodes (#10736) --- .github/PULL_REQUEST_TEMPLATE/api-node.md | 21 ++++++++ .github/workflows/api-node-template.yml | 58 +++++++++++++++++++++++ 2 files changed, 79 insertions(+) create mode 100644 .github/PULL_REQUEST_TEMPLATE/api-node.md create mode 100644 .github/workflows/api-node-template.yml diff --git a/.github/PULL_REQUEST_TEMPLATE/api-node.md b/.github/PULL_REQUEST_TEMPLATE/api-node.md new file mode 100644 index 000000000..f62744878 --- /dev/null +++ b/.github/PULL_REQUEST_TEMPLATE/api-node.md @@ -0,0 +1,21 @@ + + +## API Node PR Checklist + +### Scope +- [ ] **Is API Node Change** + +### Pricing & Billing +- [ ] **Need pricing update** +- [ ] **No pricing update** + +If **Need pricing update**: +- [ ] Metronome rate cards updated +- [ ] Auto‑billing tests updated and passing + +### QA +- [ ] **QA done** +- [ ] **QA not required** + +### Comms +- [ ] Informed **@Kosinkadink** diff --git a/.github/workflows/api-node-template.yml b/.github/workflows/api-node-template.yml new file mode 100644 index 000000000..0775f9979 --- /dev/null +++ b/.github/workflows/api-node-template.yml @@ -0,0 +1,58 @@ +name: Append API Node PR template + +on: + pull_request_target: + types: [opened, reopened, synchronize, edited, ready_for_review] + paths: + - 'comfy_api_nodes/**' # only run if these files changed + +permissions: + contents: read + pull-requests: write + +jobs: + inject: + runs-on: ubuntu-latest + steps: + - name: Ensure template exists and append to PR body + uses: actions/github-script@v7 + with: + script: | + const { owner, repo } = context.repo; + const number = context.payload.pull_request.number; + const templatePath = '.github/PULL_REQUEST_TEMPLATE/api-node.md'; + const marker = ''; + + const { data: pr } = await github.rest.pulls.get({ owner, repo, pull_number: number }); + + let templateText; + try { + const res = await github.rest.repos.getContent({ + owner, + repo, + path: templatePath, + ref: pr.base.ref + }); + const buf = Buffer.from(res.data.content, res.data.encoding || 'base64'); + templateText = buf.toString('utf8'); + } catch (e) { + core.setFailed(`Required PR template not found at "${templatePath}" on ${pr.base.ref}. Please add it to the repo.`); + return; + } + + // Enforce the presence of the marker inside the template (for idempotence) + if (!templateText.includes(marker)) { + core.setFailed(`Template at "${templatePath}" does not contain the required marker:\n${marker}\nAdd it so we can detect duplicates safely.`); + return; + } + + // If the PR already contains the marker, do not append again. + const body = pr.body || ''; + if (body.includes(marker)) { + core.info('Template already present in PR body; nothing to inject.'); + return; + } + + const newBody = (body ? body + '\n\n' : '') + templateText + '\n'; + await github.rest.pulls.update({ owner, repo, pull_number: number, body: newBody }); + core.notice('API Node template appended to PR description.'); From 2fde9597f4b02c5f06c1a5ceb3ca2fa6d74966ec Mon Sep 17 00:00:00 2001 From: ric-yu Date: Thu, 13 Nov 2025 15:11:52 -0800 Subject: [PATCH 2/3] feat: add create_time dict to prompt field in /history and /queue (#10741) --- server.py | 2 ++ 1 file changed, 2 insertions(+) diff --git a/server.py b/server.py index 5d773b10a..d059d3dc9 100644 --- a/server.py +++ b/server.py @@ -2,6 +2,7 @@ import os import sys import asyncio import traceback +import time import nodes import folder_paths @@ -733,6 +734,7 @@ class PromptServer(): for sensitive_val in execution.SENSITIVE_EXTRA_DATA_KEYS: if sensitive_val in extra_data: sensitive[sensitive_val] = extra_data.pop(sensitive_val) + extra_data["create_time"] = int(time.time() * 1000) # timestamp in milliseconds self.prompt_queue.put((number, prompt_id, prompt, extra_data, outputs_to_execute, sensitive)) response = {"prompt_id": prompt_id, "number": number, "node_errors": valid[3]} return web.json_response(response) From 94c298f9625b0fd9af8ea07a73075fdefe0d9e57 Mon Sep 17 00:00:00 2001 From: rattus <46076784+rattus128@users.noreply.github.com> Date: Fri, 14 Nov 2025 10:02:03 +1000 Subject: [PATCH 3/3] flux: reduce VRAM usage (#10737) Cleanup a bunch of stack tensors on Flux. This take me from B=19 to B=22 for 1600x1600 on RTX5090. --- comfy/ldm/flux/layers.py | 33 ++++++++++++++++++++++++++------- 1 file changed, 26 insertions(+), 7 deletions(-) diff --git a/comfy/ldm/flux/layers.py b/comfy/ldm/flux/layers.py index a3eab0470..f4bf56e01 100644 --- a/comfy/ldm/flux/layers.py +++ b/comfy/ldm/flux/layers.py @@ -167,39 +167,55 @@ class DoubleStreamBlock(nn.Module): img_modulated = self.img_norm1(img) img_modulated = apply_mod(img_modulated, (1 + img_mod1.scale), img_mod1.shift, modulation_dims_img) img_qkv = self.img_attn.qkv(img_modulated) + del img_modulated img_q, img_k, img_v = img_qkv.view(img_qkv.shape[0], img_qkv.shape[1], 3, self.num_heads, -1).permute(2, 0, 3, 1, 4) + del img_qkv img_q, img_k = self.img_attn.norm(img_q, img_k, img_v) # prepare txt for attention txt_modulated = self.txt_norm1(txt) txt_modulated = apply_mod(txt_modulated, (1 + txt_mod1.scale), txt_mod1.shift, modulation_dims_txt) txt_qkv = self.txt_attn.qkv(txt_modulated) + del txt_modulated txt_q, txt_k, txt_v = txt_qkv.view(txt_qkv.shape[0], txt_qkv.shape[1], 3, self.num_heads, -1).permute(2, 0, 3, 1, 4) + del txt_qkv txt_q, txt_k = self.txt_attn.norm(txt_q, txt_k, txt_v) if self.flipped_img_txt: + q = torch.cat((img_q, txt_q), dim=2) + del img_q, txt_q + k = torch.cat((img_k, txt_k), dim=2) + del img_k, txt_k + v = torch.cat((img_v, txt_v), dim=2) + del img_v, txt_v # run actual attention - attn = attention(torch.cat((img_q, txt_q), dim=2), - torch.cat((img_k, txt_k), dim=2), - torch.cat((img_v, txt_v), dim=2), + attn = attention(q, k, v, pe=pe, mask=attn_mask, transformer_options=transformer_options) + del q, k, v img_attn, txt_attn = attn[:, : img.shape[1]], attn[:, img.shape[1]:] else: + q = torch.cat((txt_q, img_q), dim=2) + del txt_q, img_q + k = torch.cat((txt_k, img_k), dim=2) + del txt_k, img_k + v = torch.cat((txt_v, img_v), dim=2) + del txt_v, img_v # run actual attention - attn = attention(torch.cat((txt_q, img_q), dim=2), - torch.cat((txt_k, img_k), dim=2), - torch.cat((txt_v, img_v), dim=2), + attn = attention(q, k, v, pe=pe, mask=attn_mask, transformer_options=transformer_options) + del q, k, v txt_attn, img_attn = attn[:, : txt.shape[1]], attn[:, txt.shape[1]:] # calculate the img bloks img += apply_mod(self.img_attn.proj(img_attn), img_mod1.gate, None, modulation_dims_img) + del img_attn img += apply_mod(self.img_mlp(apply_mod(self.img_norm2(img), (1 + img_mod2.scale), img_mod2.shift, modulation_dims_img)), img_mod2.gate, None, modulation_dims_img) # calculate the txt bloks txt += apply_mod(self.txt_attn.proj(txt_attn), txt_mod1.gate, None, modulation_dims_txt) + del txt_attn txt += apply_mod(self.txt_mlp(apply_mod(self.txt_norm2(txt), (1 + txt_mod2.scale), txt_mod2.shift, modulation_dims_txt)), txt_mod2.gate, None, modulation_dims_txt) if txt.dtype == torch.float16: @@ -249,12 +265,15 @@ class SingleStreamBlock(nn.Module): qkv, mlp = torch.split(self.linear1(apply_mod(self.pre_norm(x), (1 + mod.scale), mod.shift, modulation_dims)), [3 * self.hidden_size, self.mlp_hidden_dim], dim=-1) q, k, v = qkv.view(qkv.shape[0], qkv.shape[1], 3, self.num_heads, -1).permute(2, 0, 3, 1, 4) + del qkv q, k = self.norm(q, k, v) # compute attention attn = attention(q, k, v, pe=pe, mask=attn_mask, transformer_options=transformer_options) + del q, k, v # compute activation in mlp stream, cat again and run second linear layer - output = self.linear2(torch.cat((attn, self.mlp_act(mlp)), 2)) + mlp = self.mlp_act(mlp) + output = self.linear2(torch.cat((attn, mlp), 2)) x += apply_mod(output, mod.gate, None, modulation_dims) if x.dtype == torch.float16: x = torch.nan_to_num(x, nan=0.0, posinf=65504, neginf=-65504)