From f189e3a2ccc4de8898974225109e3cf4ef9b6c76 Mon Sep 17 00:00:00 2001 From: Morpheus Date: Mon, 12 Oct 2026 20:23:22 +0000 Subject: [PATCH] Add local Ideogram 4 T2I workflow and test matrix --- optimized/T2I/README.md | 2 +- optimized/T2I/ideogram/README.md | 59 +++++++++++++++++++++++++++ optimized/T2I/ideogram/variables.json | 11 +++++ optimized/T2I/ideogram/workflow.json | 17 ++++++++ 4 files changed, 88 insertions(+), 1 deletion(-) create mode 100644 optimized/T2I/ideogram/README.md create mode 100644 optimized/T2I/ideogram/variables.json create mode 100644 optimized/T2I/ideogram/workflow.json diff --git a/optimized/T2I/README.md b/optimized/T2I/README.md index 3ac4d1c..b77648b 100644 --- a/optimized/T2I/README.md +++ b/optimized/T2I/README.md @@ -1,6 +1,6 @@ # T2I workflows -Use [`flux/`](flux/) or [`qwen/`](qwen/) for the best tested text-to-image baseline. Prompts, seeds, and dimensions are intended to be replaced per task; sampler, scheduler, CFG, and steps are the optimization controls. +Use [`flux/`](flux/), [`qwen/`](qwen/), or [`ideogram/`](ideogram/) for the best tested text-to-image baseline. Prompts, seeds, and dimensions are intended to be replaced per task; sampler, scheduler, CFG, and steps are the optimization controls. Static variables are recorded in [`variables.json`](variables.json). The test plans live in each model README. diff --git a/optimized/T2I/ideogram/README.md b/optimized/T2I/ideogram/README.md new file mode 100644 index 0000000..a66172e --- /dev/null +++ b/optimized/T2I/ideogram/README.md @@ -0,0 +1,59 @@ +# Ideogram 4 — optimized local T2I + +Local Ideogram 4 text-to-image workflow for the RTX 3070 server. It is +especially useful for posters, magazine covers, labels, and other images where +the prompt includes literal text. + +## Baseline + +- Main model: `ideogram4_int8_convrot.safetensors` +- Unconditional companion: `ideogram4_unconditional_int8_convrot.safetensors` +- Text encoder: `qwen3vl_8b_w4a8.safetensors`, type `ideogram4` +- VAE: `flux2-vae.safetensors` +- Latent/output: 768×1024 portrait +- Sampler: Euler +- Scheduler: Ideogram 4 Scheduler, `mu=0.5`, `std=1.75` +- Steps: 8 +- CFG: 7.0 +- CFG override: 3.0 from 70% to 100% +- Seed: 20261012 for the controlled baseline + +The Fal model is retained as a comparison only; it produced more stylised, +noisier results. The hosted `IdeogramV4` API node was not used because this +server is not authenticated for Comfy API partner nodes. + +## Initial observations + +- The 512×512 local smoke test completed successfully. +- The 768×1024 standard Ideogram 4 run took about 6 minutes at 12 steps. +- The 768×1024 Fal comparison took about 7 minutes at 12 steps. +- The 8-step Fal run completed in about 5 minutes 18 seconds, but remained + painterly and noisy. + +## Quality/time test matrix + +Keep the prompt and seed fixed for sampler tests. Keep all other settings fixed +when changing steps or resolution. A row is not promoted until its output is +visually reviewed for typography, anatomy, texture, and artefacts. + +| ID | Resolution | Steps | Sampler | mu/std | CFG | Purpose | Status | +|---|---:|---:|---|---|---:|---|---| +| IDEO-T2I-01 | 768×1024 | 8 | Euler | 0.5/1.75 | 7 | Baseline speed/quality | Queued | +| IDEO-T2I-02 | 768×1024 | 6 | Euler | 0.5/1.75 | 7 | Faster lower bound | Queued | +| IDEO-T2I-03 | 768×1024 | 10 | Euler | 0.5/1.75 | 7 | Quality increase | Queued | +| IDEO-T2I-04 | 768×1024 | 12 | Euler | 0.5/1.75 | 7 | Existing quality reference | Complete | +| IDEO-T2I-05 | 768×1024 | 8 | Euler CFG++ | 0.5/1.75 | 7 | Sampler comparison | Planned | +| IDEO-T2I-06 | 768×1024 | 8 | Euler ancestral | 0.5/1.75 | 7 | Sampler comparison | Planned | +| IDEO-T2I-07 | 768×1024 | 8 | res_multistep | 0.5/1.75 | 7 | Sampler comparison | Planned | +| IDEO-T2I-08 | 512×768 | 8 | Euler | 0.5/1.75 | 7 | Portrait speed test | Planned | +| IDEO-T2I-09 | 1024×1024 | 8 | Euler | 0.5/1.75 | 7 | Square quality test | Planned | +| IDEO-T2I-10 | 768×1024 | 8 | Euler | 0.0/1.75 | 7 | Scheduler mu comparison | Planned | + +Results belong in `results/.png` with a matching JSON record containing +the exact prompt, seed, resolution, settings, runtime, and visual verdict. + +## Reuse + +Replace `REPLACE_PROMPT` in `workflow.json` and `variables.json`, then preserve +the technical baseline unless the test matrix calls for a change. For literal +text, use short exact quoted strings and explicitly forbid extra words. diff --git a/optimized/T2I/ideogram/variables.json b/optimized/T2I/ideogram/variables.json new file mode 100644 index 0000000..9f678b0 --- /dev/null +++ b/optimized/T2I/ideogram/variables.json @@ -0,0 +1,11 @@ +{ + "prompt": "REPLACE_PROMPT", + "negative_prompt": "Not used by this Ideogram 4 graph; negative conditioning is zeroed.", + "seed": 20261012, + "width": 768, + "height": 1024, + "model": "ideogram4_int8_convrot.safetensors", + "unconditional_model": "ideogram4_unconditional_int8_convrot.safetensors", + "clip": "qwen3vl_8b_w4a8.safetensors", + "vae": "flux2-vae.safetensors" +} diff --git a/optimized/T2I/ideogram/workflow.json b/optimized/T2I/ideogram/workflow.json new file mode 100644 index 0000000..f0e0c15 --- /dev/null +++ b/optimized/T2I/ideogram/workflow.json @@ -0,0 +1,17 @@ +{ + "1": {"class_type": "VAELoader", "inputs": {"vae_name": "flux2-vae.safetensors"}}, + "2": {"class_type": "CLIPLoader", "inputs": {"clip_name": "qwen3vl_8b_w4a8.safetensors", "type": "ideogram4", "device": "default"}}, + "3": {"class_type": "CLIPTextEncode", "inputs": {"text": "REPLACE_PROMPT", "clip": ["2", 0]}}, + "4": {"class_type": "ConditioningZeroOut", "inputs": {"conditioning": ["3", 0]}}, + "5": {"class_type": "UNETLoader", "inputs": {"unet_name": "ideogram4_int8_convrot.safetensors", "weight_dtype": "default"}}, + "6": {"class_type": "UNETLoader", "inputs": {"unet_name": "ideogram4_unconditional_int8_convrot.safetensors", "weight_dtype": "default"}}, + "7": {"class_type": "CFGOverride", "inputs": {"model": ["5", 0], "cfg": 3.0, "start_percent": 0.7, "end_percent": 1.0}}, + "8": {"class_type": "DualModelGuider", "inputs": {"model": ["7", 0], "positive": ["3", 0], "model_negative": ["6", 0], "negative": ["4", 0], "cfg": 7.0}}, + "9": {"class_type": "EmptyFlux2LatentImage", "inputs": {"width": 768, "height": 1024, "batch_size": 1}}, + "10": {"class_type": "KSamplerSelect", "inputs": {"sampler_name": "euler"}}, + "11": {"class_type": "Ideogram4Scheduler", "inputs": {"steps": 8, "width": 768, "height": 1024, "mu": 0.5, "std": 1.75}}, + "12": {"class_type": "RandomNoise", "inputs": {"noise_seed": 20261012}}, + "13": {"class_type": "SamplerCustomAdvanced", "inputs": {"noise": ["12", 0], "guider": ["8", 0], "sampler": ["10", 0], "sigmas": ["11", 0], "latent_image": ["9", 0]}}, + "14": {"class_type": "VAEDecode", "inputs": {"samples": ["13", 0], "vae": ["1", 0]}}, + "15": {"class_type": "SaveImage", "inputs": {"images": ["14", 0], "filename_prefix": "ideogram4-t2i"}} +}