Here's the snipped I'm running; ```ts const response = await env.AI.run('@cf/deepseek-ai/deepseek-r1

Here's the snipped I'm running;

const response = await env.AI.run('@cf/deepseek-ai/deepseek-r1-distill-qwen-32b', {
    messages: [
      {
        role: 'user',
        content: 'Make a cup of earl grey tea. Use the tool provided.',
      },
    ],
    tools: [
      {
        name: 'make_tea',
        description: 'Make a cup of tea',
        parameters: {
          type: 'object',
          properties: {
            tea_type: {
              type: 'string',
              description: 'The type of tea to make',
              enum: ['earl grey', 'chamomile', 'peppermint'],
            },
          },
        },
      },
    ],
  } satisfies BaseAiTextGeneration['inputs']);

  log.info('generateCloudflare', { response });

const response = await env.AI.run('@cf/deepseek-ai/deepseek-r1-distill-qwen-32b', {
    messages: [
      {
        role: 'user',
        content: 'Make a cup of earl grey tea. Use the tool provided.',
      },
    ],
    tools: [
      {
        name: 'make_tea',
        description: 'Make a cup of tea',
        parameters: {
          type: 'object',
          properties: {
            tea_type: {
              type: 'string',
              description: 'The type of tea to make',
              enum: ['earl grey', 'chamomile', 'peppermint'],
            },
          },
        },
      },
    ],
  } satisfies BaseAiTextGeneration['inputs']);

  log.info('generateCloudflare', { response });

const response = await env.AI.run('@cf/deepseek-ai/deepseek-r1-distill-qwen-32b', {
    messages: [
      {
        role: 'user',
        content: 'Make a cup of earl grey tea. Use the tool provided.',
      },
    ],
    tools: [
      {
        name: 'make_tea',
        description: 'Make a cup of tea',
        parameters: {
          type: 'object',
          properties: {
            tea_type: {
              type: 'string',
              description: 'The type of tea to make',
              enum: ['earl grey', 'chamomile', 'peppermint'],
            },
          },
        },
      },
    ],
  } satisfies BaseAiTextGeneration['inputs']);

  log.info('generateCloudflare', { response });

const response = await env.AI.run('@cf/deepseek-ai/deepseek-r1-distill-qwen-32b', {
    messages: [
      {
        role: 'user',
        content: 'Make a cup of earl grey tea. Use the tool provided.',
      },
    ],
    tools: [
      {
        name: 'make_tea',
        description: 'Make a cup of tea',
        parameters: {
          type: 'object',
          properties: {
            tea_type: {
              type: 'string',
              description: 'The type of tea to make',
              enum: ['earl grey', 'chamomile', 'peppermint'],
            },
          },
        },
      },
    ],
  } satisfies BaseAiTextGeneration['inputs']);

  log.info('generateCloudflare', { response });

 {
  response: {
    response: "Okay, so I need to make a cup of Earl Grey tea using the tools provided. Let me think about what I know about making tea and what tools I might have access to. First, I know that Earl Grey is a black tea with a bergamot flavor, so it's usually served hot and might be drunk with milk or just on its own.\n" +
      '\n' +
      "I should start by figuring out what tools I need. The user mentioned to use the tool provided, but didn't specify what it is. So I'll assume I have a teapot, a kettle for boiling water, a teaspoon for measuring tea, a cup, maybe a strainer, and perhaps a milk pitcher if I want to add milk. I should also consider whether the tools are electric or manual, but I'll go with basic assumptions.\n" +
      '\n' +
      "First step: Boil water. I'll need to fill the kettle with fresh water and bring it to a boil. The temperature for black tea is usually around 90-100°C, but I think boiling water is fine. Wait, no, sometimes it's better to let the water cool a bit after boiling to prevent over-extracting the tea. But Earl Grey is a black tea, so maybe it's okay to use boiling water.\n" +
      '\n',
    usage: { prompt_tokens: 20, completion_tokens: 256, total_tokens: 276 }
  }
}

 {
  response: {
    response: "Okay, so I need to make a cup of Earl Grey tea using the tools provided. Let me think about what I know about making tea and what tools I might have access to. First, I know that Earl Grey is a black tea with a bergamot flavor, so it's usually served hot and might be drunk with milk or just on its own.\n" +
      '\n' +
      "I should start by figuring out what tools I need. The user mentioned to use the tool provided, but didn't specify what it is. So I'll assume I have a teapot, a kettle for boiling water, a teaspoon for measuring tea, a cup, maybe a strainer, and perhaps a milk pitcher if I want to add milk. I should also consider whether the tools are electric or manual, but I'll go with basic assumptions.\n" +
      '\n' +
      "First step: Boil water. I'll need to fill the kettle with fresh water and bring it to a boil. The temperature for black tea is usually around 90-100°C, but I think boiling water is fine. Wait, no, sometimes it's better to let the water cool a bit after boiling to prevent over-extracting the tea. But Earl Grey is a black tea, so maybe it's okay to use boiling water.\n" +
      '\n',
    usage: { prompt_tokens: 20, completion_tokens: 256, total_tokens: 276 }
  }
}

 {
  response: {
    response: "Okay, so I need to make a cup of Earl Grey tea using the tools provided. Let me think about what I know about making tea and what tools I might have access to. First, I know that Earl Grey is a black tea with a bergamot flavor, so it's usually served hot and might be drunk with milk or just on its own.\n" +
      '\n' +
      "I should start by figuring out what tools I need. The user mentioned to use the tool provided, but didn't specify what it is. So I'll assume I have a teapot, a kettle for boiling water, a teaspoon for measuring tea, a cup, maybe a strainer, and perhaps a milk pitcher if I want to add milk. I should also consider whether the tools are electric or manual, but I'll go with basic assumptions.\n" +
      '\n' +
      "First step: Boil water. I'll need to fill the kettle with fresh water and bring it to a boil. The temperature for black tea is usually around 90-100°C, but I think boiling water is fine. Wait, no, sometimes it's better to let the water cool a bit after boiling to prevent over-extracting the tea. But Earl Grey is a black tea, so maybe it's okay to use boiling water.\n" +
      '\n',
    usage: { prompt_tokens: 20, completion_tokens: 256, total_tokens: 276 }
  }
}

 {
  response: {
    response: "Okay, so I need to make a cup of Earl Grey tea using the tools provided. Let me think about what I know about making tea and what tools I might have access to. First, I know that Earl Grey is a black tea with a bergamot flavor, so it's usually served hot and might be drunk with milk or just on its own.\n" +
      '\n' +
      "I should start by figuring out what tools I need. The user mentioned to use the tool provided, but didn't specify what it is. So I'll assume I have a teapot, a kettle for boiling water, a teaspoon for measuring tea, a cup, maybe a strainer, and perhaps a milk pitcher if I want to add milk. I should also consider whether the tools are electric or manual, but I'll go with basic assumptions.\n" +
      '\n' +
      "First step: Boil water. I'll need to fill the kettle with fresh water and bring it to a boil. The temperature for black tea is usually around 90-100°C, but I think boiling water is fine. Wait, no, sometimes it's better to let the water cool a bit after boiling to prevent over-extracting the tea. But Earl Grey is a black tea, so maybe it's okay to use boiling water.\n" +
      '\n',
    usage: { prompt_tokens: 20, completion_tokens: 256, total_tokens: 276 }
  }
}

Ddmaretskyi Here's the snipped I'm running; ```ts const response = await env.AI.run('@cf/dee...

Isaac McFadyen•3/13/25, 6:05 PM

Notice how the completion_tokens are 256; the model wasn't actually done, but got cut off because max_tokens defaults to 256 as of a few weeks ago. You'll want to specify a higher maxTokens in your request in order to allow the model to finish it's thought.

JoaoCupido•3/13/25, 6:34 PM

Speaking of max_tokens, I can't seem to change max_tokens with the messages property in any chat model, and I have no clue why. I have done this via URL (api.cloudflare.com/client/v4/accounts/$CLOUDFLARE_ACCOUNT_ID/ai/run/@cf/meta/llama-3-8b-instruct).

IIsaac McFadyen Notice how the completion_tokens are 256; the model wasn't actually done, but go...

dmaretskyiOP•3/13/25, 7:06 PM

hi, thanks for the suggestion! I've increased the token count to 4096 and this is the response I get now:

(info) generateCloudflare {
  stream: {
    response: 'Okay, so I need to make a cup of Earl Grey tea using the tools provided. Hmm, let me think about what tools I might have. Usually, when making tea, you need a kettle, a teapot, a teacup, tea bags or loose tea, hot water, maybe a strainer, and sugar or milk if you want it. \n' +
      '\n' +
      "Wait, the user said to use the tool provided, but didn't specify what that tool is. Maybe it's just a regular teapot? Or maybe a tea infuser? I'm not sure. Well, I guess I'll go with the basics.\n" +
      '\n' +
      "First, I should probably boil some water. If I have a kettle, I can fill it with water and turn it on. While the water is boiling, I can prepare the teapot. If I'm using loose tea, I'll need a tea infuser or a strainer to prevent the leaves from getting into the cup. \n" +
      '\n' +
      "Once the water is boiling, I should let it cool a bit because Earl Grey tea is best when brewed with water that's just below boiling point, maybe around 90-95 degrees Celsius. If I pour boiling water directly on the tea, it might make it too strong or bitter. \n" +
      '\n' +
      "So, I'll pour a little bit of hot water into the teapot to warm it up and then discard that water. Then, I'll add the tea leaves or the tea bag. If I'm using loose tea, I'll put the infuser in the teapot. For a standard cup, maybe about a teaspoon of loose tea or one tea bag. \n" +
      '\n' +
      "Next, I'll pour the hot water over the tea. I'll make sure to cover the teapot to keep the heat in. The steeping time is important. Earl Grey usually takes about 3-5 minutes. If I steep it too long, it might become too strong.\n" +
      '\n' +
      "After steeping, I'll pour the tea into the cup. If I used an infuser, I'll remove it now. I can add sugar or honey if I want it sweet, or maybe a splash of milk. Some people like it with lemon, so that's an option too.\n" +
      '\n' +
      "Wait, did I forget anything? Oh, maybe I should consider the type of cup. If it's a ceramic cup, that's good for retaining heat. Glass might be nice if I want to see the tea. Also, maybe I should clean the teapot and tools afterwards to keep them ready for next time.\n" +
      '\n' +
      "I think that's the basic process. Let me summarize the steps to make sure I didn't miss anything.\n" +
      '</think>\n' +
      '\n' +
      'To make a cup of Earl Grey tea, follow these organized steps:\n' +
      '\n' +
      '1. **Boil Water**: Fill a kettle with water and bring it to a boil. Allow the water to cool slightly to around 90-95°C (194-203°F) to avoid bitterness.\n' +
      '\n' +
      '2. **Prepare the Teapot**: Warm the teapot by pouring a small amount of hot water into it, then discard the water.\n' +
      '\n' +
      '3. **Add Tea**: Place 1 teaspoon of loose Earl Grey tea leaves into a tea infuser or add one Earl Grey tea bag to the teapot.\n' +
      '\n' +
      '4. **Steep the Tea**: Pour the hot water over the tea and cover the teapot. Steep for 3-5 minutes to achieve the desired strength.\n' +
      '\n' +
      '5. **Serve**: Carefully pour the tea into a cup. Remove the infuser or tea bag.\n' +
      '\n' +
      '6. **Customize**: Add sugar, honey, milk, or lemon as preferred.\n' +
      '\n' +
      '7. **Clean Up**: Rinse the teapot and infuser to keep them ready for future use.\n' +
      '\n' +
      'Enjoy your Earl Grey tea!',
    usage: { prompt_tokens: 20, completion_tokens: 761, total_tokens: 781 }
  }
}

(info) generateCloudflare {
  stream: {
    response: 'Okay, so I need to make a cup of Earl Grey tea using the tools provided. Hmm, let me think about what tools I might have. Usually, when making tea, you need a kettle, a teapot, a teacup, tea bags or loose tea, hot water, maybe a strainer, and sugar or milk if you want it. \n' +
      '\n' +
      "Wait, the user said to use the tool provided, but didn't specify what that tool is. Maybe it's just a regular teapot? Or maybe a tea infuser? I'm not sure. Well, I guess I'll go with the basics.\n" +
      '\n' +
      "First, I should probably boil some water. If I have a kettle, I can fill it with water and turn it on. While the water is boiling, I can prepare the teapot. If I'm using loose tea, I'll need a tea infuser or a strainer to prevent the leaves from getting into the cup. \n" +
      '\n' +
      "Once the water is boiling, I should let it cool a bit because Earl Grey tea is best when brewed with water that's just below boiling point, maybe around 90-95 degrees Celsius. If I pour boiling water directly on the tea, it might make it too strong or bitter. \n" +
      '\n' +
      "So, I'll pour a little bit of hot water into the teapot to warm it up and then discard that water. Then, I'll add the tea leaves or the tea bag. If I'm using loose tea, I'll put the infuser in the teapot. For a standard cup, maybe about a teaspoon of loose tea or one tea bag. \n" +
      '\n' +
      "Next, I'll pour the hot water over the tea. I'll make sure to cover the teapot to keep the heat in. The steeping time is important. Earl Grey usually takes about 3-5 minutes. If I steep it too long, it might become too strong.\n" +
      '\n' +
      "After steeping, I'll pour the tea into the cup. If I used an infuser, I'll remove it now. I can add sugar or honey if I want it sweet, or maybe a splash of milk. Some people like it with lemon, so that's an option too.\n" +
      '\n' +
      "Wait, did I forget anything? Oh, maybe I should consider the type of cup. If it's a ceramic cup, that's good for retaining heat. Glass might be nice if I want to see the tea. Also, maybe I should clean the teapot and tools afterwards to keep them ready for next time.\n" +
      '\n' +
      "I think that's the basic process. Let me summarize the steps to make sure I didn't miss anything.\n" +
      '</think>\n' +
      '\n' +
      'To make a cup of Earl Grey tea, follow these organized steps:\n' +
      '\n' +
      '1. **Boil Water**: Fill a kettle with water and bring it to a boil. Allow the water to cool slightly to around 90-95°C (194-203°F) to avoid bitterness.\n' +
      '\n' +
      '2. **Prepare the Teapot**: Warm the teapot by pouring a small amount of hot water into it, then discard the water.\n' +
      '\n' +
      '3. **Add Tea**: Place 1 teaspoon of loose Earl Grey tea leaves into a tea infuser or add one Earl Grey tea bag to the teapot.\n' +
      '\n' +
      '4. **Steep the Tea**: Pour the hot water over the tea and cover the teapot. Steep for 3-5 minutes to achieve the desired strength.\n' +
      '\n' +
      '5. **Serve**: Carefully pour the tea into a cup. Remove the infuser or tea bag.\n' +
      '\n' +
      '6. **Customize**: Add sugar, honey, milk, or lemon as preferred.\n' +
      '\n' +
      '7. **Clean Up**: Rinse the teapot and infuser to keep them ready for future use.\n' +
      '\n' +
      'Enjoy your Earl Grey tea!',
    usage: { prompt_tokens: 20, completion_tokens: 761, total_tokens: 781 }
  }
}

dmaretskyiOP•3/13/25, 7:07 PM

I noticed that the opening <think> tag is missing

dmaretskyiOP•3/13/25, 7:07 PM

but also the model doesn't seem to recognize that it has access to a tool

Isaac McFadyen•3/13/25, 7:13 PM

Hmm yeah. Interesting.

Isaac McFadyen•3/13/25, 7:14 PM

Not sure about the latter but I'm guessing the leading <think> tag is missing because it's part of the prompt used by Workers AI (this is what tools like llama.cpp do in order to force the model to start it's response with thinking).

Isaac McFadyen•3/13/25, 7:14 PM

That said, for compatibility it should be manually added by Workers AI if it's part of the prompt.

Isaac McFadyen•3/13/25, 7:14 PM

CC @michelle ^ not 100% sure that's what's happening, but since multiple users are running into this it might be worth a bug fix

IIsaac McFadyen CC @michelle ^ not 100% sure that's what's happening, but since multiple users a...

Isaac McFadyen•3/14/25, 5:16 AM

Per https://huggingface.co/blog/open-r1/update-3

Incidentally, this is also what DeepSeek does with their distilled models

So yes, guessing that the <think> tag is just being prefilled and Workers AI isn't adding it back into the response.

karenr•3/14/25, 5:47 AM

quick question. from the cloudflare workers ai, what's the best model for image compression?

Kkarenr quick question. from the cloudflare workers ai, what's the best model for image ...

Torianna•3/14/25, 10:50 AM

You wouldn't want to use AI to compress, you'd want to use something like WebP, AVIF, etc

Torianna•3/14/25, 10:50 AM

Those repackage your image into a smaller file, while keeping about the same quality

Torianna•3/14/25, 10:52 AM

Now if you want to compress inside Workers, that's a little bit more tricky, but you can look up Cloudflare Images. You get free (I think) image transformations so long as you don't store images there

TTorianna You wouldn't want to use AI to compress, you'd want to use something like WebP, ...

karenr•3/14/25, 10:57 AM

Yeah, this is what I actually did. was wondering if using AI for compression is a better choice. Thanks @Torianna

Torianna•3/14/25, 10:57 AM

I don't think there's any public models

Torianna•3/14/25, 10:58 AM

I know Google is working on one, but that's internal

karenr•3/14/25, 11:01 AM

Google - oh really?
yeah.. current models are multimodal AI model with both vision and language capabilities not specific to compression

TTorianna I don't think there's any public models

Isaac McFadyen•3/14/25, 3:24 PM

Nvidia has one and it's teeeechnically public but not really? i.e. it's integrated into their new Neural Shader stuff but I don't believe the model is open-weight.

IIsaac McFadyen CC @michelle ^ not 100% sure that's what's happening, but since multiple users a...

dmaretskyiOP•3/14/25, 3:25 PM

do you have a public bug tracker for this?

dmaretskyiOP•3/14/25, 3:25 PM

just so I can check when this gets resolved

Ddmaretskyi do you have a public bug tracker for this?

Isaac McFadyen•3/14/25, 3:25 PM

Nope but if I don't hear back from Michelle in a while I can try to escalate to others.

dmaretskyiOP•3/14/25, 3:25 PM

okay, thanks for your help!

Ddmaretskyi okay, thanks for your help!

Isaac McFadyen•3/14/25, 3:26 PM

I'm not sure if R1 works well with tools at all, based on what I've heard. But the missing opening <think> is probably a bug, I can't imagine it's intended.

JoaoCupido•3/14/25, 7:45 PM

Flux Schnell model still doesn't have a random seed implementation and image sizes (width x height), unlike Stable Diffusion models. When is this going to be implemented, if possible?

blindChicken•3/16/25, 5:58 PM

Has there been a change to the hermes-2-pro-mistral-7bhermes-2-pro-mistral-7b model. I have a very basic app based on CF's function calling tutorial. I made the app about a month ago and has been working fine since. But over the past few days it has stopped working and it appears that the model has changed the format of its response. Here is how it is responding now:

User Prompt: show me the color of an avocado?
AI result is: {
  response: '<tool_call>\n' +
    "{'arguments': {'r': 69, 'g': 139, 'b': 69}, 'name': 'switchLightColor'}\n" +
    '</tool_call>\n' +
    '\n' +
    'I have chosen a color that represents an avocado. The color of an avocado is typically a pale green with a hint of creaminess. To represent this, I have selected a color with a higher green value (139) and balanced amounts of red (69) and blue (69) values. This creates a color that is reminiscent of the natural hue of an avocado, bringing the essence of the fruit into the room.',
  usage: { prompt_tokens: 0, completion_tokens: 0, total_tokens: 0 }
}

User Prompt: show me the color of an avocado?
AI result is: {
  response: '<tool_call>\n' +
    "{'arguments': {'r': 69, 'g': 139, 'b': 69}, 'name': 'switchLightColor'}\n" +
    '</tool_call>\n' +
    '\n' +
    'I have chosen a color that represents an avocado. The color of an avocado is typically a pale green with a hint of creaminess. To represent this, I have selected a color with a higher green value (139) and balanced amounts of red (69) and blue (69) values. This creates a color that is reminiscent of the natural hue of an avocado, bringing the essence of the fruit into the room.',
  usage: { prompt_tokens: 0, completion_tokens: 0, total_tokens: 0 }
}

The tool call is being returned within the response and is correctly tagged with <tool_call><tool_call> but the response no longer returns a tool_callstool_calls prop, so my code isn't calling anything it only shows the malformed response.

blindChicken•3/16/25, 6:11 PM

If I replace hermes-2-pro-mistral-7bhermes-2-pro-mistral-7b with @cf/meta/llama-3.3-70b-instruct-fp8-fast@cf/meta/llama-3.3-70b-instruct-fp8-fast then it works fine. Something must have changed with the Mistral model

kalepail•3/16/25, 7:58 PM

I'm trying to use the @cf/meta/llama-guard-3-8b@cf/meta/llama-guard-3-8b. What's the proper way to tweak this to modify the UNSAFE CONTENT CATEGORIESUNSAFE CONTENT CATEGORIES? A lot of sexually explict stuff is getting through when the prompts aren't very long. I want a really robust NSFW content filter but asis this model isn't working well

BblindChicken Has there been a change to the `hermes-2-pro-mistral-7b` model. I have a very ba...

James•3/16/25, 8:26 PM

cc @michelle possible breaking change or incident with tool calling for this model?

James•3/16/25, 8:44 PM

@Isaac | AS213339 confirmed the regression and has raised an escalation with the team. Thanks for the report.

JJames @Isaac | AS213339 confirmed the regression and has raised an escalation with the...

Isaac McFadyen•3/16/25, 8:45 PM

^ Oh yes, thanks for mentioning; forgot to say that here.

Houston CF•3/16/25, 9:58 PM

@blindChicken @Isaac | AS213339 @James Are we seeing the results we expected now? We have deployed a fix for the " tool calling using hermes-2-pro-mistral-7b model" issue.

James•3/16/25, 9:59 PM

Looks good now, thank you!

JJames Looks good now, thank you!

blindChicken•3/17/25, 1:17 AM

We just tested it on our end and it appears to be working correctly. Thanks!

markvaldez•3/17/25, 6:11 PM

Hi, I don't see any way to rotate my REST bearer AI token..

markvaldez•3/17/25, 6:14 PM

I didn't create a token, it was created for me on the dashboard when I went to the AI Worker page

markvaldez•3/17/25, 6:39 PM

I applied as an Engineer at Cloudflare this past month, but I don't think I got past the resume screen. I live around the corner from the SF offices and have been there for a hackathon and lunch-and-learn HONO event the past 2 weeks. I can fix this issue: https://github.com/valdezm/dash.cloudflare.com/issues/1

GitHub

Cannot rotate REST AI Bearer token · Issue #1 · valdezm/dash.cloudf...

Problem A REST Bearer token was created for me and does not show up in my Account API Tokens using these instructions: https://developers.cloudflare.com/workers-ai/get-started/rest-api/#1-get-api-t...

markvaldez•3/17/25, 6:40 PM

https://tenor.com/view/bills-ugh-gif-9811803164280522639

Tenor

markvaldez•3/17/25, 6:41 PM

Send me a DM and I will happliy get to work

markvaldez•3/17/25, 6:43 PM

Also, you all are awesome

Alex Patterson•3/20/25, 3:30 AM

Seems like all the models on Workers AI have such small Context WIndows, is there any that will be added that come closer to Google Gemini?

si(dot).xth•3/20/25, 11:30 AM

my pillow fixed my issue:

raw data for simplicity and efficiency in handling large images, this method may lead to more API calls if the image is re-generated each time it's accessed (Caching handles that last part.)

base64 encoding to minimize API calls over performance (Easier to implement)

Raw data + cache is the only way to go

Original: Blob not supported for workers ai? URL.CreateObjectURL() is not implemented

AAlex Patterson Seems like all the models on Workers AI have such small Context WIndows, is ther...

Silvan•3/20/25, 12:01 PM

Having the same issue here. Trying to create a story is fairly hard this way but some models do have bigger context windows but many of the "good ones" are less than 10k

JMPA•3/20/25, 9:14 PM

hello, is inpaiting ai workers working currently?

JMPA•3/20/25, 9:15 PM

i tried 2 models and they dont works.

JMPA•3/20/25, 9:16 PM

stable-diffusion-v1-5-inpainting
API response status: 400 body: {"errors":[{"message":"AiError: Bad input: Error: Type mismatch of '/mask', 'array' not in 'string'","code":5006}],"success":false,"result":{},"messages":[]}
API error: 400 - {"errors":[{"message":"AiError: Bad input: Error: Type mismatch of '/mask', 'array' not in 'string'","code":5006}],"success":false,"result":{},"messages":[]}
Response with status 400 in 1363 ms.

JMPA•3/20/25, 10:19 PM

anyone there?

James•3/20/25, 10:27 PM

Is this something that worked previously and now doesn't? Can you provide any code to reproduce?

JJMPA hello, is inpaiting ai workers working currently?

Raylight•3/22/25, 6:59 AM

As James implied, it would be easier to help if you have a snippet showing the call to the model, but in general: The docs show the same set of parameters (e.g.

image

image

, maskmask) for several models, but the only model that does inpainting is @cf/runwayml/stable-diffusion-v1-5-inpainting@cf/runwayml/stable-diffusion-v1-5-inpainting.
Make sure to supply both

image

image

and maskmask when calling it. The format is mask: [...new Uint8Array(await maskImage.arrayBuffer())]mask: [...new Uint8Array(await maskImage.arrayBuffer())], where maskImagemaskImage could be the result of e.g. await fetch(/* mask image url */)await fetch(/* mask image url */).

Silvan•3/23/25, 11:09 AM

I really hope we get some “better” text generation models on here soon. i tried every single one for story creation and nothing came even remotely close to claude atm.

Here's the snipped I'm running; ```ts const response = await env.AI.run('@cf/deepseek-ai/deepseek-r1

Similar Threads