CommunityImagegithub.com

ai-image-gen-termux

AI image gen on Termux. Colab SD is the free pro route.

What is ai-image-gen-termux?

ai-image-gen-termux is a Codex agent skill that aI image gen on Termux. Colab SD is the free pro route.

Works with~Claude Code✓Codex CLI~Cursor✓Gemini CLI
npx skills add https://github.com/makwanaalpesh811-a11y/ai-image-gen-termux-skill/tree/HEAD

Installed? Explore more Image skills: steipete/songsee, affaan-m/frontend-design, mattpocock/improve-codebase-architecture · View all 6 →

Ask in your favorite AI

Open a new chat with this agent skill pre-loaded.

Documentation

AI Image Generation on Termux

Hermes itself cannot generate images — it's a text model. Any image work requires calling an external model. On Termux, three routes exist; only one is reliably free and high-quality.

Route Selection (use in this order)

RouteFreeQualityVerdict
AWS Bedrock (Titan/SDXL/Nova)✅ $200 / 6 mo⭐⭐⭐⭐⭐Best on Termux — pure-Python boto3
Google Colab + SD-XL✅ T4 GPU⭐⭐⭐⭐⭐Free unlimited, needs Colab session
Pollinations.ai✅ no key⭐⭐Quick drafts only
Leonardo.ai150 credits/day⭐⭐⭐⭐Signup + web
OpenRouter image models❌ needs billing⭐⭐⭐⭐⭐'Missing Authentication header' even with key
Gemini API direct (image)❌ paid only⭐⭐⭐⭐⭐'Quota exceeded' on free tier
Stable Diffusion local--Won't run on Termux (needs GPU)

Rule: When user asks 'can you generate an image', answer honestly — Hermes is a text model, you call an external service. Do not pretend to synthesize images yourself.

AWS Bedrock Route (Best for Termux — pure Python)

boto3 is pure Python and installs on Termux cleanly. AWS CLI v2 install script fails on Termux (needs glibc) — do not use the AWS CLI path, use boto3 directly.

Setup

pip install boto3
# Save creds to ~/.aws/credentials (chmod 600)

Credentials file:

[default]
aws_access_key_id = AKIA...
aws_secret_access_key = ...

Free tier

  • $200 credit / 6 months (new AWS accounts)
  • Cost varies by model (check Bedrock pricing page — Titan was $0.01/image, Nova Canvas is higher)
  • Model deprecation check first: Bedrock has retired multiple image models. As of 2026-10, amazon.titan-image-generator-v1/v2:0 return ResourceNotFoundException: model version has reached the end of its life, and stability.stable-diffusion-xl-v1/v0 are also EOL.
  • Recommended model: amazon.nova-canvas-v1:0 (Amazon's current image model). Requires access request in Bedrock console.
  • Discovery via SDK: boto3.client('bedrock').list_foundation_models() returns all approved models. The correct filter parameter is one of byProvider, byCustomizationType, byOutputModality, byInferenceType (NOT by='modelType'). Iterate modelSummaries and filter capabilities for 'ImageGeneration'.
  • Regions: us-east-1 (N. Virginia) or us-west-2 (Oregon)

Generate

import boto3, base64, json
bedrock = boto3.client('bedrock-runtime', region_name='us-east-1')
body = json.dumps({"promptText": prompt, "numberOfImages": 1, "imageConfig": {"dimension": "1024x1024"}})
resp = bedrock.invoke_model(modelId='amazon.nova-canvas-v1:0', body=body)
data = json.loads(resp['body'].read().decode('utf-8'))
with open('out.png', 'wb') as f:
    f.write(base64.b64decode(data['images'][0]['b64Image']))

Note: amazon.nova-canvas-v1:0 uses imageConfig.dimension (512x512, 768x768, 1024x1024, 1024x1536, 1536x1024) instead of the older Titan/SDXL quality param. Older quality: "standard" param is not accepted on Nova.

IAM User creation (5 min, before requesting model access)

  1. IAM → Users → Add user → username bedrock-images
  2. Permissions: Attach policies directly (not "Add user to group")
  3. Search AmazonBedrockFullAccess (or AdministratorAccess for all-in-one)
  4. Create user → Security credentials → Create access key
  5. Use case: Local code (not CLI) — accepts warning about AWS Toolkit alternative (Termux has no AWS Toolkit)
  6. Do NOT provide Console access unless user wants web login as that user

Bedrock Console → Model access → Request amazon.nova-canvas-v1:0 (and any others). Approval is 5-10 min.

Pitfalls

  • Model access takes 5-10 min to approve after request — test will fail with AccessDenied until approved.
  • Never ask user to paste keys in chat — the AWS Agent Toolkit setup instructions explicitly forbid this; have them write to ~/.aws/credentials directly. If they already pasted, save immediately and treat as potentially compromised (rotate from AWS Console).
  • Prefix check on keys: AKIA... = permanent access key (correct for scripts). ASK... = temporary session credential (expires in hours, needs session token). If user pastes an ASK key, they're copying from the AWS console header instead of the IAM user security-credentials page — point them to the right place.
  • Model end-of-life is silent in boto3 — the SDK returns ResourceNotFoundException, not a deprecation notice. Check model status on bedrock.amazonaws.com or by attempting a test invoke before writing a generate script.
  • Working script: ~/gen_image.py, output: ~/Hermes_Almari/04_AI_IMAGE_GEN/aws_generated/. Credentials at ~/.aws/credentials (also mirrored to ~/Hermes_Almari/99_COLLABORATION/aws/aws_credentials.env).

Free Fast Route: Pollinations.ai

curl -sL "https://image.pollinations.ai/prompt/<url-encoded-prompt>?width=1920&height=1080&nologo=true&seed=<int>" \
  -o out.jpg --max-time 180
  • Only sana model, mediocre quality (user rejected it).
  • Pitfall: Retries often return 2-byte files (rate limit / timeout). Retry loop with sleep 10 between, verify size >10KB. On 3 failures move on — don't hammer.
  • Batch wrapper: ~/gen_images.sh prompts.txt out_dir/ (one prompt per line).

Pro Route: Colab + Stable Diffusion XL

Generate a self-contained Colab notebook, have the user paste + run. Free T4 GPU, unlimited images, professional quality.

Minimal notebook cell

!pip install -q diffusers transformers accelerate
from diffusers import StableDiffusionXLPipeline
from diffusers import EulerDiscreteScheduler
import torch

pipe = StableDiffusionXLPipeline.from_pretrained(
    "stabilityai/stable-diffusion-xl-base-1.0",
    torch_dtype=torch.float16, use_safetensors=True,
).to("cuda")
pipe.scheduler = EulerDiscreteScheduler.from_config(pipe.scheduler.config)

def gen(prompt, seed=42, steps=30, cfg=6.0):
    g = torch.Generator("cuda").manual_seed(seed)
    return pipe(prompt, num_inference_steps=steps, guidance_scale=cfg, generator=g)

# For batch: loop over a prompts list, save each to ./outputs/

Save output folder via google.colab.files.download (zip).

Prompt engineering for historical / cinematic scenes

Working modifier stack (append to base scene description):

<subject>, cinematic, photorealistic, epic, detailed, dramatic lighting, 8k, masterpiece

For historical scenes include: era, location, style anchor (medieval painting, documentary photograph, period drama film still). Include seed for reproducibility across shots.

Pitfall: Long prompts (>50 tokens) sometimes get silently truncated by SD-XL. Keep under ~40 tokens; use negative_prompt for unwanted elements rather than stuffing exclusions into positive prompt.

Integration with Slideshow Video

Feed generated images to ffmpeg for zoom/blur slideshow (see anime-vlog-workflow skill for the exact zoompan recipe).

Environment Notes

  • /tmp/ writes fail on Termux — always use $HOME/ paths for output.
  • AWS CLI v2 install script requires glibc — Termux uses bionic libc. curl awscli | bash will download but the resulting binary won't execute. Use pip install boto3 directly instead; boto3 is pure Python and works.
  • boto3 client creation succeeds without credentials (returns BedrockRuntime object) — only actual invoke_model calls fail without creds. Don't mistake a successful boto3.client(...) for auth being configured.
  • Gemini API image gen requires paid tier — free-tier key returns Quota exceeded for metric: generativelanguage.googleapis.com/generate_content_free_tier_requests on gemini-*-image endpoints. Don't retry; that's a billing-tier block, not a transient error.
  • OpenRouter image models require billing — even with a valid OPENROUTER_API_KEY, /chat/completions calls to google/gemini-*-image, openai/gpt-5-image* return Missing Authentication header unless the account has billing enabled. Free OpenRouter keys only work for text models.
  • Verify image validity by size — corrupt/failed downloads come back as 2-100 byte files, not valid JPEGs. Check os.path.getsize() > 10000 before treating as success.
  • Working image-gen dir: ~/Hermes_Almari/04_AI_IMAGE_GEN/.

Files

  • ~/gen_images.sh — Pollinations batch wrapper
  • ~/Hermes_Almari/04_AI_IMAGE_GEN/ — output dir

Related Skills