software by Stafford Williamsstafford williams

image-gen

ComfyUI is integrating external API models and demonstrate gpt-image-1 integrated with a ComfyUI workflow. The catch for now is you can’t supply your own API key/endpoint and rather require a ComfyUI account that you load with credits. Pricing reflects OpenAI list price.

comfy-ui, ai, image-gen • 2025-05-01 • 9:00am

The success of the new ChatGPT 4o image generation caused the rollout to be delayed but it’s now available to free users, rate limited to 3 generations per day.

generate a photo-realistic image of a woman on a giant block of cheese in the middle of a forest
generate a photo-realistic image of a woman on a giant block of cheese in the middle of a forest
ok, but now make her hold a sign that says 'woman on cheese in forest'
ok, but now make her hold a sign that says 'woman on cheese in forest'
ok but she should be wearing a red dress
ok but she should be wearing a red dress
ok but now she, and the cheese, should be upside down, while the rest of the image remains correctly orientated
ok but now she, and the cheese, should be upside down, while the rest of the image remains correctly orientated
that is wrong, because the forest is upside down, when only the woman and the cheese should be
that is wrong, because the forest is upside down, when only the woman and the cheese should be
ai, chatgpt, openai, image-gen • 2025-04-02 • 9:16pm

New image model family: Janus-Pro - DeepSeek creators just dropped a stable diffusion competitor.

Janus-Pro, which DeepSeek describes as a “novel autoregressive framework,” can both analyze and create new images… and most Janus-Pro models can only analyze small images with a resolution of up to 384 x 384.

ai, image-gen, deepseek • 2025-01-28 • 12:22pm

FLUX dropped and it’s blows Stable Diffusion 3 out of the water, though has very high resource requirements. I’m running the schnell version locally. Prompt adherence is great, text capability is incredible.

ai, image-gen, flux, model • 2024-08-05 • 10:58am

Stability AI holds on, appointing a new CEO.

ai, image-gen, stable-diffusion, moat • 2024-06-22 • 10:08am

SD3 weights dropped last night. I gave it a shot last night myself with their supplied comfyui workflows, as a base model it looks extremely promising, details are next level, though it still doesn’t appear to know jack about hands, faces still need hires fix. Very promising for a base model.

ai, image-gen, stable-diffusion, stability-ai, model • 2024-06-13 • 11:30am

Stable Diffusion 3: Research Paper

Stable Diffusion 3 outperforms state-of-the-art text-to-image generation systems such as DALL·E 3, Midjourney v6, and Ideogram v1 in typography and prompt adherence, based on human preference evaluations.

ai, image-gen, stable-diffusion, stability-ai • 2024-03-14 • 7:13pm