Add local Ideogram 4 T2I workflow and test matrix

This commit is contained in:
Morpheus
2026-10-12 20:23:22 +00:00
parent f3fb8b1854
commit f189e3a2cc
4 changed files with 88 additions and 1 deletions
+1 -1
View File
@@ -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.
+59
View File
@@ -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/<test-id>.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.
+11
View File
@@ -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"
}
+17
View File
@@ -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"}}
}