venice-image-generate
Skill2 starsChanged 5 months agoMITView on GitHub
Generate images with Venice. Covers POST /image/generate (Venice-native), POST /images/generations (OpenAI-compatible), GET /image/styles (style presets), request fields (prompt, dimensions, cfg_scale, seed, variants, style_preset, aspect_ratio, resolution, safe_mode, watermark), and response formats.
- Reads credentials
- Sends data out
4 other projects use a version of this, 1 of them edited.
Adopted by
Most recently taken up by
- davidanthonyn/claude-skillstheir own version, first seen Oct 20, 2026
- jhy0285/monofieldtheir own version, first seen Oct 13, 2026
- veniceai/skillsedited, first seen Oct 13, 2026
- jpoindexter/theft-kittheir own version, first seen May 20, 2026
Other versions4 projects use a version of this.
Word for word · 0
None found.
Edited · 1
- veniceai/skills★ 17118% same
Wrote their own version · 3
- jhy0285/monofield★ 6same name
- jpoindexter/theft-kit★ 1same name
- davidanthonyn/claude-skills★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository19 other files it gives its agents.
- cheaptokensSkill
- venice-api-keysSkill
- venice-api-overviewSkill
- venice-audio-musicSkill
- venice-audio-speechSkill
- venice-audio-transcriptionSkill
- venice-augmentSkill
- venice-authSkill
- venice-billingSkill
- venice-charactersSkill
- venice-chatSkill
- venice-crypto-rpcSkill
- venice-embeddingsSkill
- venice-errorsSkill
- venice-image-editSkill
- venice-modelsSkill
- venice-responsesSkill
- venice-videoSkill
- venice-x402Skill
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 0 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 88
Use this if you're already on the OpenAI SDK.
- Very specific: line 121
If you need variants, seed, negative_prompt, cfg_scale, or style_preset, switch to /image/generate.
≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Venice Image Generation
Two text-to-image endpoints:
POST /api/v1/image/generate— Venice-native, full control (negative prompts, CFG, seed, up to 4 variants).POST /api/v1/images/generations— OpenAI-compatible, fewer knobs but drop-in for the OpenAI SDK.
Plus:
GET /api/v1/image/styles— list of style preset names forstyle_preset.
For editing / upscaling / multi-image / background removal, see venice-image-edit.
Use when
- You need to generate images from text prompts.
- You need multiple variants in one call.
- You're porting from OpenAI's
images.generateand want a zero-change SDK swap. - You want to browse style presets before committing to one.
/image/generate — Venice-native
Request
curl https://api.venice.ai/api/v1/image/generate \
-H "Authorization: Bearer $VENICE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "z-image-turbo",
"prompt": "A beautiful sunset over a mountain range",
"width": 1024,
"height": 1024,
"cfg_scale": 7.5,
"steps": 8,
"seed": 123456789,
"variants": 1,
"format": "webp",
"style_preset": "3D Model",
"safe_mode": true
}'Fields
| Field | Type | Default | Notes |
model | string | — | Required. Image model ID. GET /models?type=image. |
prompt | string | — | Required. Max promptCharacterLimit from the model's model_spec.constraints (typically 1500–7500). |
negative_prompt | string | — | Describe what not to show. Same character cap as prompt. |
width, height | int | 1024, 1024 | ≤ 1280 each. Must be divisible by constraints.widthHeightDivisor on the model's model_spec. |
aspect_ratio | string | — | "1:1", "16:9", "9:16", … — used by models like Nano Banana instead of width/height. |
resolution | string | — | "1K", "2K", "4K" — used by resolution-driven models. |
cfg_scale | number | model default | 0 < x ≤ 20. Higher = more prompt adherence. |
steps | int | 8 | Inference steps. Some models ignore it (e.g. Turbo). |
seed | int | 0 | -999999999..999999999. Use 0/omit for random. |
variants | int | 1 | 1–4. Only if return_binary: false. |
lora_strength | int | — | 0–100 when model uses Loras. |
style_preset | string | — | Value from GET /image/styles. |
format | "webp"/"png"/"jpeg" | webp | Response image format. |
return_binary | bool | false | true → binary image/* response; false → JSON with base64. |
embed_exif_metadata | bool | false | Embed prompt info in EXIF. |
hide_watermark | bool | false | Venice may still watermark certain content. |
safe_mode | bool | true | Blurs adult content. |
enable_web_search | bool | false | Only some models. Charges extra. |
inpaint | — | — | Deprecated since May 19 2025. A new inpaint API is forthcoming. |
Response (JSON, return_binary: false)
{
"id": "...",
"images": ["<base64>", "<base64>"],
"timing": {...},
"request": {...}
}With return_binary: true, response is raw image/webp (or png/jpeg) with matching Content-Type.
/images/generations — OpenAI-compatible
Use this if you're already on the OpenAI SDK. Field names match openai.images.generate().
import OpenAI from 'openai'
const client = new OpenAI({
apiKey: process.env.VENICE_API_KEY,
baseURL: 'https://api.venice.ai/api/v1',
})
const res = await client.images.generate({
model: 'z-image-turbo',
prompt: 'A beautiful sunset over mountain ranges',
size: '1024x1024',
response_format: 'b64_json',
})
const b64 = res.data[0].b64_jsonMapped fields
| Field | Values | Notes |
model | string, default "default" | Unknown model IDs fall back to Venice's default. |
prompt | string, ≤ 1500 chars | Required. |
size | auto, 256x256, 512x512, 1024x1024, 1536x1024, 1024x1536, 1792x1024, 1024x1792 | — |
output_format | jpeg / png / webp | Defaults to png. |
response_format | b64_json / url | url returns a data: URL (not a hosted URL). |
moderation | auto (safe mode on) / low (safe mode off) | — |
n | 1 | Venice only supports a single image per call here. |
quality, style (vivid/natural), background, output_compression, user | — | Accepted for OpenAI compat, not used by Venice. |
If you need variants, seed, negative_prompt, cfg_scale, or style_preset, switch to /image/generate.
/image/styles — list presets
curl https://api.venice.ai/api/v1/image/styles \
-H "Authorization: Bearer $VENICE_API_KEY"Returns a list of styles[], each with a name you can pass to style_preset. Cache this — it's small and stable.
Choosing a model
curl "https://api.venice.ai/api/v1/models?type=image" \
-H "Authorization: Bearer $VENICE_API_KEY"Inspect per-model model_spec:
constraints.widthHeightDivisor—widthandheightmust both be divisible by this.constraints.aspectRatios[]+defaultAspectRatio— if present, the model supports aspect-ratio-driven sizing.constraints.resolutions[]+defaultResolution— if present, the model supportsresolution(1K/2K/4K).constraints.steps.{default,max}— step bounds (some models ignorestepsentirely).constraints.promptCharacterLimit— max prompt length (also applies tonegative_prompt).pricing.generation.usd— flat USD per image, orpricing.resolutions[].usdfor resolution-tiered models.
Pick a model that matches the feature + size combo you plan to use.
Common patterns
Fixed-seed A/B test
{"model": "z-image-turbo", "prompt": "...", "seed": 42, "variants": 4}Aspect-ratio-driven model (Nano Banana family)
{"model": "nano-banana-2", "prompt": "...", "aspect_ratio": "16:9", "resolution": "2K"}(Other nano-banana variants: nano-banana-pro. Always verify the current ID via GET /models?type=image.)
Style preset + negative
{
"model": "z-image-turbo",
"prompt": "a red sports car in a parking lot",
"negative_prompt": "blurry, people, clouds",
"style_preset": "3D Model"
}Stream binary to disk (Node)
const res = await fetch('https://api.venice.ai/api/v1/image/generate', {
method: 'POST',
headers: { Authorization: `Bearer ${process.env.VENICE_API_KEY}`, 'Content-Type': 'application/json' },
body: JSON.stringify({ model: 'z-image-turbo', prompt: '...', return_binary: true }),
})
if (!res.ok) throw new Error(await res.text())
const buf = Buffer.from(await res.arrayBuffer())
await fs.writeFile('out.webp', buf)Errors
| Code | Meaning |
400 | Bad params (e.g. dimensions not divisible by widthHeightDivisor, prompt too long, variants>1 with return_binary). |
401 | Auth or Pro-only model. |
402 | Insufficient balance. Bearer: plain { "error": "Insufficient balance" }; x402: PAYMENT_REQUIRED body + PAYMENT-REQUIRED header. |
415 | Wrong Content-Type (send application/json for this endpoint). |
429 | Rate limited. |
500 / 503 | Inference or capacity issue — retry with jitter. |
(Content-policy violations on /image/generate come back as 400 with an error string, not 422 — the 422 shape is specific to audio generation paths.)
Gotchas
- Each model picks one sizing idiom: either
width/height,aspect_ratio+resolution, or (OpenAI-compat)size. Match the model'sconstraints. variants > 1requiresreturn_binary: false(JSON with base64 array).stepsis ignored by fast/turbo models; they hardcode step count internally.hide_watermark: trueis advisory — Venice may still watermark content flagged by safety classifiers.- Old
inpaintfield is deprecated; don't use it. - For OpenAI-compat,
response_format: "url"returns a data URL, not a hosted URL — plan for that if you're saving to storage.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

